Add files using upload-large-folder tool

Browse files

Files changed (14) hide show

.gitattributes +1 -0
README.md +587 -0
config.json +49 -0
model-00001-of-00004.safetensors +3 -0
model-00002-of-00004.safetensors +3 -0
model-00003-of-00004.safetensors +3 -0
model-00004-of-00004.safetensors +3 -0
model.safetensors.index.json +1210 -0
pyproject.toml +30 -0
quant_log.csv +281 -0
quantize_config.json +21 -0
special_tokens_map.json +1032 -0
tokenizer.json +3 -0
tokenizer_config.json +0 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,587 @@

+---
+company: "ConfidentialMind"
+emoji: "🧠"
+colorFrom: "blue"
+colorTo: "purple"
+pinned: true
+authors: "JustJaro"
+---
+# ConfidentialMind 🚀🧠
+Generative AI Software Infrastructure Simplified 🎉
+[![Website](https://img.shields.io/badge/Website-confidentialmind.com-blue)](https://confidentialmind.com)
+[![Email](https://img.shields.io/badge/Email-info%40confidentialmind.com-orange)](mailto:[email protected])
+# 🔥 Quantized Model: Arcee-Blitz_gptq_g32_4bit 🦾 🔥
+<details>
+  <summary><strong>Model Details</strong></summary>
+- **Original Model:** [arcee-ai/Arcee-Blitz](https://huggingface.co/arcee-ai/Arcee-Blitz)
+- **Quantized Model:** Arcee-Blitz_gptq_g32_4bit (this repository)
+- **Quantization Method:** GPTQ (4-bit, group size 32)
+- **Quantization Library:** [GPTQModel](https://github.com/ModelCloud/GPTQModel/tree/main)
+- **Calibration Dataset:** neuralmagic/LLM_compression_calibration (using 1536 samples with seq len 6144)
+- **Quantized by:** [ConfidentialMind.com](https://www.confidentialmind.com)
+</details>
+<details>
+  <summary><strong>Usage</strong></summary>
+```python
+from gptqmodel import GPTQModel
+from transformers import AutoTokenizer
+# Use the local directory or JustJaro/Arcee-Blitz_gptq_g32_4bit after upload
+quantized_model_id = "/home/jaro/models/quantized/Arcee-Blitz_gptq_g32_4bit"  # or "JustJaro/Arcee-Blitz_gptq_g32_4bit"
+tokenizer = AutoTokenizer.from_pretrained(quantized_model_id)
+model = GPTQModel.load(quantized_model_id, device="cuda:0")  # or "cpu"
+input_text = "This is a test prompt"
+inputs = tokenizer(input_text, return_tensors="pt").to("cuda:0")
+outputs = model.generate(**inputs)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+</details>
+<details>
+  <summary><strong>Package Versions and Installation Instructions</strong></summary>
+See `pyproject.toml` for the exact UV project file. See the [GPTQModel](https://github.com/ModelCloud/GPTQModel/tree/main) repo for more details on how to install the package.
+Use the provided `pyproject.toml`:
+```bash
+uv venv
+source venv/bin/activate
+uv sync
+```
+</details>
+<details>
+  <summary><strong>Quantization Script</strong></summary>
+Below is the exact `quantize.py` script used to generate this model:
+```python
+#!/usr/bin/env python3
+"""
+This script loads a source Hugging Face model and a calibration dataset,
+quantizes the model using GPTQModel (with 4-bit precision and a dynamic group size),
+saves the quantized model with Transformers’ safe serialization under ~/models/quantized/,
+and then creates/updates a Hugging Face repository by uploading the model, tokenizer,
+and an auto–generated README.md that includes proper foldable sections, badges, and warnings.
+Usage example:
+    python quantize.py --source-model TinyLlama/TinyLlama-1.1B-Chat-v1.0 \
+                       --calibration-dataset wikitext/wikitext-2-raw-v1 \
+                       --seq-len 1024 --nsamples 256 --hf-token <YOUR_HF_TOKEN>
+"""
+import os
+import random
+import shutil
+import subprocess
+from enum import Enum
+from pathlib import Path
+from typing import List
+import torch
+import typer
+from datasets import load_dataset
+from dotenv import load_dotenv, find_dotenv
+from gptqmodel import GPTQModel, QuantizeConfig
+from gptqmodel.utils import Perplexity
+# For later pushing to the model hub
+from huggingface_hub import HfApi
+from transformers import AutoTokenizer, PreTrainedTokenizerBase
+load_dotenv(find_dotenv())
+HF_TOKEN = os.getenv("HF_TOKEN")
+app = typer.Typer()
+class GroupSize(str, Enum):
+    accurate: int = 32
+    balanced: int = 64
+    fast: int = 128
+def get_text_from_example(example: dict) -> str:
+    """
+    Returns text from a dataset example.
+    If the example contains a "text" field, that text is used.
+    Otherwise, if it has a "messages" field (a list of dicts with a "content" key),
+    the contents of all messages are concatenated.
+    """
+    if "text" in example and example["text"]:
+        return example["text"]
+    elif "messages" in example:
+        contents = [msg.get("content", "").strip() for msg in example["messages"]]
+        return " ".join([s for s in contents if s])
+    else:
+        return ""
+def get_calibration_dataset(
+    tokenizer: PreTrainedTokenizerBase,
+    nsamples: int,
+    seqlen: int,
+    calibration_dataset: str
+) -> List[dict]:
+    """
+    Loads and tokenizes a calibration dataset from the HF Hub (or a local file).
+    Only examples with at least 80% of seqlen characters (after extraction) are kept.
+    """
+    ds = None
+    try:
+        try:
+            if "/" in calibration_dataset:
+                parts = calibration_dataset.split("/", 1)
+                ds = load_dataset(parts[0], parts[1], split="train")
+            else:
+                ds = load_dataset(calibration_dataset, split="train")
+        except Exception as e:
+            print(f"Error loading dataset '{calibration_dataset}' via load_dataset: {e}")
+            ds = load_dataset(calibration_dataset, split="train")
+            print(f"Loaded calibration dataset from full remote path {calibration_dataset}.")
+    except Exception as e:
+        print(f"Error loading dataset '{calibration_dataset}' via load_dataset: {e}")
+        if os.path.exists(calibration_dataset):
+            try:
+                ds = load_dataset("json", data_files=calibration_dataset, split="train")
+                print(f"Loaded calibration dataset from local file {calibration_dataset}.")
+            except Exception as e2:
+                print(f"Error loading local json dataset from '{calibration_dataset}': {e2}")
+                return []
+        else:
+            return []
+    print(f"Dataset features: {ds.features}")
+    ds = ds.filter(lambda x: len(get_text_from_example(x)) <= int(seqlen * 0.8))
+    sample_range = min(nsamples, len(ds))
+    calibration_data = []
+    for i in range(sample_range):
+        example = ds[i]
+        text = get_text_from_example(example)
+        tokenized = tokenizer(text, truncation=True, max_length=seqlen, return_tensors="pt")
+        tokenized = {k: v.squeeze(0) for k, v in tokenized.items()}
+        calibration_data.append(tokenized)
+    return calibration_data
+def calculate_avg_ppl(model, tokenizer):
+    """
+    Computes the average perplexity on the wikitext-2-raw-v1 training split.
+    """
+    ppl = Perplexity(
+        model=model,
+        tokenizer=tokenizer,
+        dataset_path="wikitext",
+        dataset_name="wikitext-2-raw-v1",
+        split="train",
+        text_column="text",
+    )
+    ppl_values = ppl.calculate(n_ctx=512, n_batch=512)
+    avg = sum(ppl_values) / len(ppl_values)
+    return avg
+def get_pinned_package_versions():
+    """
+    Retrieves pinned package versions via 'uv pip freeze'.
+    """
+    try:
+        result = subprocess.run(["uv", "pip", "freeze"], capture_output=True, text=True, check=True)
+        packages_output = result.stdout.strip()
+        versions = {}
+        for line in packages_output.splitlines():
+            if "==" in line:
+                package_name, package_version = line.split("==", 1)
+                versions[package_name.lower()] = package_version
+        return versions
+    except subprocess.CalledProcessError as e:
+        typer.echo(f"Error running 'uv pip freeze': {e}", err=True)
+        return {}
+    except FileNotFoundError:
+        typer.echo("uv command not found. Make sure uv is installed and in your PATH.", err=True)
+        return {}
+def prepare_model_dir(model_dir: str):
+    """Removes the given directory if it exists and creates a new one."""
+    if os.path.exists(model_dir):
+        shutil.rmtree(model_dir)
+    os.makedirs(model_dir, exist_ok=True)
+def self_read_script():
+    """Returns the full text of this script."""
+    try:
+        script_path = os.path.abspath(__file__)
+        with open(script_path, "r") as f:
+            script_content = f.read()
+    except Exception as e:
+        script_content = "Error reading script content: " + str(e)
+    return script_content
+def get_my_user(hf_token):
+    """Retrieves your Hugging Face username from your token."""
+    api = HfApi(token=hf_token)
+    user_info = api.whoami()
+    try:
+        username = user_info.get("name") or user_info.get("username")
+    except Exception as e:
+        typer.echo(f"Error retrieving username from Hugging Face API: {e}. Using default username.")
+        username = api.whoami()
+    if not username:
+        typer.echo("Could not determine your Hugging Face username from the token. Using default username.", err=True)
+        username = "JustJaro"
+    return username
+def generate_readme(calibration_dataset, nsamples, quantized_model_dir, quantized_model_name,
+                    script_content, seq_len, source_model, username, avg_ppl, group_size_int):
+    """
+    Creates a README.md with dynamic sections:
+      • A front matter section with badges/links.
+      • A title that includes a randomly chosen emoji.
+      • A warning if the perplexity is too high (>30).
+      • Collapsible sections (using <details>) for model details, usage, installation, script,
+        quantization performance, disclaimer, contact, license, author and acknowledgements.
+      • Additional TODO items.
+    """
+    # pick a random emoji from the list (for each model, so it varies)
+    chosen_emoji = random.choice(["⚡️", "🐣", "🦾", "🤖", "🧠", "🧐", "🚀"])
+    # Warning if average perplexity is above 30
+    if avg_ppl > 30:
+        warning_text = f"\n**⚠️ WARNING: High Perplexity Detected!** The average perplexity is {avg_ppl:.2f}, which exceeds the recommended threshold.\n"
+    else:
+        warning_text = ""
+    # Front matter with badges and links
+    front_matter = (
+        "---\n"
+        'company: "ConfidentialMind"\n'
+        'emoji: "🧠"\n'
+        'colorFrom: "blue"\n'
+        'colorTo: "purple"\n'
+        "pinned: true\n"
+        'authors: "JustJaro"\n'
+        "---\n\n"
+        "# ConfidentialMind 🚀🧠\n\n"
+        "Generative AI Software Infrastructure Simplified 🎉\n\n"
+        "[![Website](https://img.shields.io/badge/Website-confidentialmind.com-blue)](https://confidentialmind.com)  \n"
+        "[![Email](https://img.shields.io/badge/Email-info%40confidentialmind.com-orange)](mailto:[email protected])\n\n"
+    )
+    # Title plus warning (if any)
+    title = f"# 🔥 Quantized Model: {quantized_model_name} {chosen_emoji} 🔥\n{warning_text}\n"
+    # Collapsible sections using <details> tags:
+    model_details_section = f"""<details>
+  <summary><strong>Model Details</strong></summary>
+- **Original Model:** [{source_model}](https://huggingface.co/{source_model})
+- **Quantized Model:** {quantized_model_name} (this repository)
+- **Quantization Method:** GPTQ (4-bit, group size {group_size_int})
+- **Quantization Library:** [GPTQModel](https://github.com/ModelCloud/GPTQModel/tree/main)
+- **Calibration Dataset:** {calibration_dataset} (using {nsamples} samples with seq len {seq_len})
+- **Quantized by:** [ConfidentialMind.com](https://www.confidentialmind.com)
+</details>
+"""
+    usage_section = f"""<details>
+  <summary><strong>Usage</strong></summary>
+```python
+from gptqmodel import GPTQModel
+from transformers import AutoTokenizer
+# Use the local directory or {username}/{quantized_model_name} after upload
+quantized_model_id = "{quantized_model_dir}"  # or "{username}/{quantized_model_name}"
+tokenizer = AutoTokenizer.from_pretrained(quantized_model_id)
+model = GPTQModel.load(quantized_model_id, device="cuda:0")  # or "cpu"
+input_text = "This is a test prompt"
+inputs = tokenizer(input_text, return_tensors="pt").to("cuda:0")
+outputs = model.generate(**inputs)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+</details>
+"""
+    package_section = """<details>
+  <summary><strong>Package Versions and Installation Instructions</strong></summary>
+See `pyproject.toml` for the exact UV project file. See the [GPTQModel](https://github.com/ModelCloud/GPTQModel/tree/main) repo for more details on how to install the package.
+Use the provided `pyproject.toml`:
+```bash
+uv venv
+source venv/bin/activate
+uv sync
+```
+</details>
+"""
+    script_section = f"""<details>
+  <summary><strong>Quantization Script</strong></summary>
+Below is the exact `quantize.py` script used to generate this model:
+```python
+{script_content}
+```
+</details>
+"""
+    performance_section = f"""<details>
+  <summary><strong>Quantization Performance</strong></summary>
+**Average perplexity (PPL) on wikitext-2-raw-v1 dataset:** {avg_ppl:.2f}
+</details>
+"""
+    disclaimer_section = """<details>
+  <summary><strong>Disclaimer</strong></summary>
+This model is for research purposes only. It may inherit limitations and biases from the original model and the quantization process. Please use responsibly and refer to the original model card for more details.
+</details>
+"""
+    contact_section = """<details>
+  <summary><strong>Contact</strong></summary>
+For any questions or support, please visit [ConfidentialMind](https://www.confidentialmind.com) or contact us directly.
+[![LinkedIn](https://img.shields.io/badge/LinkedIn-ConfidentialMind-blue)](https://www.linkedin.com/company/confidentialmind/)
+</details>
+"""
+    license_section = f"""<details>
+  <summary><strong>License</strong></summary>
+This model inherits the license from the original model. Please refer to the original model card for more details.
+Original model card: `{source_model}`
+</details>
+"""
+    author_section = """<details>
+  <summary><strong>Author</strong></summary>
+This model was quantized by [![LinkedIn](https://img.shields.io/badge/LinkedIn-Jaro-blue)](https://www.linkedin.com/in/jaroai/)
+</details>
+"""
+    ack_section = """<details>
+  <summary><strong>Acknowledgements</strong></summary>
+Quantization performed using the GPTQModel pipeline.
+**TODO:**
+- HELMET
+- Eluther evaluation harness
+</details>
+"""
+    # Combine all parts:
+    readme_content = (
+        front_matter +
+        title + "\n" +
+        model_details_section + "\n" +
+        usage_section + "\n" +
+        package_section + "\n" +
+        script_section + "\n" +
+        performance_section + "\n" +
+        disclaimer_section + "\n" +
+        contact_section + "\n" +
+        license_section + "\n" +
+        author_section + "\n" +
+        ack_section
+    )
+    readme_path = os.path.join(quantized_model_dir, "README.md")
+    with open(readme_path, "w") as f:
+        f.write(readme_content)
+    typer.echo("README.md created with detailed information.")
+@app.command()
+def main(
+    seq_len: int = typer.Option(4096, help="Sequence length for tokenization and calibration."),
+    nsamples: int = typer.Option(512, help="Number of samples to use for calibration."),
+    source_model: str = typer.Option("rombodawg/Rombos-LLM-V2.6-Qwen-14b",
+                                     help="Source model HF repository identifier."),
+    calibration_dataset: str = typer.Option("wikitext/wikitext-2-raw-v1",
+                                              help="Calibration dataset identifier (in 'dataset/config' format) or local file path."),
+    hf_token: str = typer.Option(HF_TOKEN, help="Hugging Face token for creating/updating your repo."),
+    upload_only: bool = typer.Option(False, help="Only upload the quantized model to the Hugging Face Hub."),
+    # Allow for 32, 64, 128 only using typer:
+    group_size: GroupSize = typer.Option(GroupSize.accurate, help="Group size for quantization: accurate (32), balanced (64), fast (128)."),
+    mse: bool = typer.Option(False, help="Use MSE instead of MAE for the loss function."),
+    size_multi: float = typer.Option(3.5, help="Model size multiplier depends on the source model. Default: 1."),
+):
+    # Prepare destination directory and model names.
+    model_name = source_model.split("/")[-1]
+    if size_multi != 1:
+        size_multiplier = size_multi
+        size_multiplier_len = size_multiplier / 2
+    else:
+        size_multiplier = 1
+        size_multiplier_len = 1
+    nsamples = int(nsamples * size_multiplier)
+    seq_len = int(seq_len * size_multiplier_len)
+    quantized_model_name = f"{model_name}_gptq_g{int(group_size.value)}_4bit"
+    quantized_model_dir = os.path.expanduser(os.path.join("~/models/quantized", quantized_model_name))
+    if not upload_only:
+        prepare_model_dir(quantized_model_dir)
+        typer.echo("Loading tokenizer from source model...")
+        tokenizer_obj = AutoTokenizer.from_pretrained(source_model, use_fast=True)
+        typer.echo("Loading calibration dataset...")
+        typer.echo(f"Calibration dataset: {calibration_dataset}")
+        calibration_data = get_calibration_dataset(tokenizer_obj, nsamples, seq_len, calibration_dataset)
+        if not calibration_data:
+            typer.echo("Calibration dataset is empty. Aborting.", err=True)
+            raise typer.Exit(code=1)
+        if mse:
+            mse_val = 0.01
+            quantize_config = QuantizeConfig(bits=4, group_size=int(group_size.value), damp_percent=0.015, mse=mse_val)
+        else:
+            quantize_config = QuantizeConfig(bits=4, group_size=int(group_size.value), damp_percent=0.01)
+        device = "cuda:0" if torch.cuda.is_available() else "cpu"
+        typer.echo(f"Loading model in {device} mode...")
+        model = GPTQModel.load(source_model, quantize_config)
+        typer.echo("Quantizing model...")
+        group_size_factor = int(128 / int(group_size.value))
+        batch_size = max(
+            1, int(int((nsamples * 0.1) / group_size_factor) * int(size_multiplier_len))
+        )
+        model.quantize(calibration_data, auto_gc=False, batch_size=batch_size)
+        package_versions = get_pinned_package_versions()
+        username = get_my_user(hf_token)
+        script_content = self_read_script()
+        typer.echo(f"Saving quantized model to {quantized_model_dir} using Transformers safe serialization...")
+        try:
+            model.save_pretrained(quantized_model_dir)
+            tokenizer_obj.save_pretrained(quantized_model_dir)
+        except Exception as ex:
+            typer.echo(f"Error during saving: {ex}. Aborting.")
+            raise
+        typer.echo(f"Model saved successfully to {quantized_model_dir}.")
+    else:
+        tokenizer_obj = AutoTokenizer.from_pretrained(source_model, use_fast=True)
+        package_versions = get_pinned_package_versions()
+        username = get_my_user(hf_token)
+        script_content = self_read_script()
+        device = "cuda:0" if torch.cuda.is_available() else "cpu"
+    # Load the (possibly quantized) model for evaluation.
+    model = GPTQModel.load(quantized_model_dir, device=device)
+    avg_ppl = calculate_avg_ppl(model, tokenizer_obj)
+    typer.echo(f"Average perplexity (PPL) on wikitext-2-raw-v1 dataset: {avg_ppl:.2f}")
+    deps = Path("./pyproject.toml")
+    shutil.copy(deps, quantized_model_dir)
+    # Note: pass the dynamic group size as an integer.
+    generate_readme(calibration_dataset, nsamples, quantized_model_dir,
+                    quantized_model_name, script_content, seq_len,
+                    source_model, username, avg_ppl, int(group_size.value))
+    GPTQModel.push_to_hub(quantized_path=quantized_model_dir, private=False,
+                           repo_id=quantized_model_name, token=HF_TOKEN)
+    typer.echo(f"Model pushed to Hugging Face repo: {quantized_model_name}")
+    demo_input = tokenizer_obj("test is", return_tensors="pt").to(device)
+    generated_ids = model.generate(**demo_input)
+    output_text = tokenizer_obj.decode(generated_ids[0])
+    typer.echo(f"Inference demo output: {output_text}")
+    typer.echo(f"Average perplexity (PPL) on calibration dataset: {avg_ppl:.2f}")
+if __name__ == "__main__":
+    app()
+```
+</details>
+<details>
+  <summary><strong>Quantization Performance</strong></summary>
+**Average perplexity (PPL) on wikitext-2-raw-v1 dataset:** 7.89
+</details>
+<details>
+  <summary><strong>Disclaimer</strong></summary>
+This model is for research purposes only. It may inherit limitations and biases from the original model and the quantization process. Please use responsibly and refer to the original model card for more details.
+</details>
+<details>
+  <summary><strong>Contact</strong></summary>
+For any questions or support, please visit [ConfidentialMind](https://www.confidentialmind.com) or contact us directly.
+[![LinkedIn](https://img.shields.io/badge/LinkedIn-ConfidentialMind-blue)](https://www.linkedin.com/company/confidentialmind/)
+</details>
+<details>
+  <summary><strong>License</strong></summary>
+This model inherits the license from the original model. Please refer to the original model card for more details.
+Original model card: `arcee-ai/Arcee-Blitz`
+</details>
+<details>
+  <summary><strong>Author</strong></summary>
+This model was quantized by [![LinkedIn](https://img.shields.io/badge/LinkedIn-Jaro-blue)](https://www.linkedin.com/in/jaroai/)
+</details>
+<details>
+  <summary><strong>Acknowledgements</strong></summary>
+Quantization performed using the GPTQModel pipeline.
+**TODO:**
+- HELMET
+- Eluther evaluation harness
+</details>

config.json ADDED Viewed

	@@ -0,0 +1,49 @@

+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "/home/jaro/.cache/huggingface/hub/models--arcee-ai--Arcee-Blitz/snapshots/cf20caa2bfbfabc71a79c6e73f1a7b1e59c86a9b",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 32768,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "bits": 4,
+    "checkpoint_format": "gptq",
+    "desc_act": true,
+    "group_size": 32,
+    "lm_head": false,
+    "meta": {
+      "damp_auto_increment": 0.0025,
+      "damp_percent": 0.01,
+      "mse": 0.0,
+      "quantizer": [
+        "gptqmodel:1.9.0"
+      ],
+      "static_groups": false,
+      "true_sequential": true,
+      "uri": "https://github.com/modelcloud/gptqmodel"
+    },
+    "pack_dtype": "int32",
+    "quant_method": "gptq",
+    "sym": true
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 100000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.3",
+  "use_cache": false,
+  "vocab_size": 131072
+}

model-00001-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4a38b6684aaa11195b0d31b96f76d077ae9d6d3a4bf55b42411f8c2cc4fb05a4
+size 3945078984

model-00002-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:631843111a978f14e5c4614e03eff72838fd11386e2f4c755dcba4a7e464e34b
+size 3955781912

model-00003-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0170110daf674db1ab21a8d5bc843a3f3cb5d391b0ec93a0a87f8df1c846a18a
+size 3955781968

model-00004-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:12e0dd3c447e9a3fc78b5da8c9a998ea93a29afcec2a94eb0ea7185f71f1f18e
+size 3690281024

model.safetensors.index.json ADDED Viewed

	@@ -0,0 +1,1210 @@

+{
+  "metadata": {
+    "total_size": 15546787840
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.down_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.down_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.gate_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.up_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.up_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.k_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.o_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.q_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.v_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.down_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.down_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.gate_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.up_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.up_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.k_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.o_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.q_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.v_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.down_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.down_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.gate_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.up_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.up_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.k_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.o_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.q_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.v_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.down_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.down_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.gate_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.up_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.up_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.k_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.o_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.q_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.v_proj.g_idx": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

pyproject.toml ADDED Viewed

	@@ -0,0 +1,30 @@

+[build-system]
+requires = ["uv", "setuptools>=61.0", "wheel"] # uv for uv-aware builds, setuptools for packaging
+build-backend = "setuptools.build_meta"
+[project]
+name = "cquantize"
+version = "0.1.0"
+description = "Quantization script module for confidentialmind-graph project for 4bit GPTQ quantizations (so far)"
+readme = "README.md"
+requires-python = ">=3.11,<=3.13.10" # 3.13.8 is used in the main project
+dependencies = [
+    "python-dotenv>=1.0.1",
+    "gptqmodel>=1.9.0",
+    "threadpoolctl>=3.5.0",
+    "tokenicer>=0.0.2",
+    "device-smi>=0.3.3",
+    "pillow>=11.1.0",
+    "torch>=2.6.0",
+    "accelerate>=1.3.0",
+    "safetensors>=0.5.2",
+    "transformers>=4.48.3",
+    "datasets>=3.3.0",
+    "huggingface-hub>=0.28.1",
+    "typer>=0.15.1",
+    "hf-transfer>=0.1.9",
+]
+[tool.setuptools.package-data]
+quantize = ["README.md", "*.py"] # Include README and Python files if packaged

quant_log.csv ADDED Viewed

	@@ -0,0 +1,281 @@

+layer,module,loss,damp,time
+0,self_attn.k_proj,0.00828,0.01000,2.650
+0,self_attn.v_proj,0.00013,0.01000,2.152
+0,self_attn.q_proj,0.01475,0.01000,2.218
+0,self_attn.o_proj,0.00001,0.01000,1.897
+0,mlp.up_proj,0.02958,0.01000,2.933
+0,mlp.gate_proj,0.03186,0.01000,2.727
+0,mlp.down_proj,0.00002,0.01000,21.743
+1,self_attn.k_proj,0.03723,0.01000,2.287
+1,self_attn.v_proj,0.00349,0.01000,2.020
+1,self_attn.q_proj,0.08149,0.01000,2.091
+1,self_attn.o_proj,0.00004,0.01000,1.811
+1,mlp.up_proj,0.10925,0.01000,2.826
+1,mlp.gate_proj,0.11763,0.01000,2.627
+1,mlp.down_proj,0.00008,0.01000,21.423
+2,self_attn.k_proj,0.04565,0.01000,2.264
+2,self_attn.v_proj,0.00546,0.01000,2.013
+2,self_attn.q_proj,0.10574,0.01000,2.092
+2,self_attn.o_proj,0.00014,0.01000,1.816
+2,mlp.up_proj,0.27427,0.01000,2.813
+2,mlp.gate_proj,0.29976,0.01000,2.608
+2,mlp.down_proj,0.01154,0.01450,23.564
+3,self_attn.k_proj,0.15649,0.01000,2.273
+3,self_attn.v_proj,0.02533,0.01000,2.010
+3,self_attn.q_proj,0.38040,0.01000,2.097
+3,self_attn.o_proj,0.00015,0.01000,1.785
+3,mlp.up_proj,0.47427,0.01000,2.938
+3,mlp.gate_proj,0.53622,0.01000,2.701
+3,mlp.down_proj,0.00048,0.01000,21.639
+4,self_attn.k_proj,0.15107,0.01000,2.268
+4,self_attn.v_proj,0.03076,0.01000,1.990
+4,self_attn.q_proj,0.38275,0.01000,2.097
+4,self_attn.o_proj,0.00042,0.01000,1.797
+4,mlp.up_proj,0.71489,0.01000,2.816
+4,mlp.gate_proj,0.81623,0.01000,2.621
+4,mlp.down_proj,0.00101,0.01000,21.362
+5,self_attn.k_proj,0.18817,0.01000,2.262
+5,self_attn.v_proj,0.04227,0.01000,2.014
+5,self_attn.q_proj,0.48195,0.01000,2.093
+5,self_attn.o_proj,0.00094,0.01000,1.793
+5,mlp.up_proj,1.02088,0.01000,2.829
+5,mlp.gate_proj,1.17544,0.01000,2.630
+5,mlp.down_proj,0.00181,0.01000,21.388
+6,self_attn.k_proj,0.21142,0.01000,2.245
+6,self_attn.v_proj,0.05290,0.01000,1.975
+6,self_attn.q_proj,0.54845,0.01000,2.053
+6,self_attn.o_proj,0.00099,0.01000,1.768
+6,mlp.up_proj,1.36681,0.01000,2.783
+6,mlp.gate_proj,1.53420,0.01000,2.606
+6,mlp.down_proj,0.00264,0.01000,21.382
+7,self_attn.k_proj,0.23278,0.01000,2.268
+7,self_attn.v_proj,0.08408,0.01000,2.000
+7,self_attn.q_proj,0.66976,0.01000,2.078
+7,self_attn.o_proj,0.00238,0.01000,1.778
+7,mlp.up_proj,1.70891,0.01000,2.810
+7,mlp.gate_proj,2.01624,0.01000,2.592
+7,mlp.down_proj,0.00419,0.01000,21.359
+8,self_attn.k_proj,0.29953,0.01000,2.245
+8,self_attn.v_proj,0.09998,0.01000,1.983
+8,self_attn.q_proj,0.83751,0.01000,2.071
+8,self_attn.o_proj,0.00282,0.01000,1.782
+8,mlp.up_proj,2.32344,0.01000,2.796
+8,mlp.gate_proj,2.82837,0.01000,2.612
+8,mlp.down_proj,0.00621,0.01000,21.278
+9,self_attn.k_proj,0.29190,0.01000,2.279
+9,self_attn.v_proj,0.10782,0.01000,1.986
+9,self_attn.q_proj,0.79361,0.01000,2.071
+9,self_attn.o_proj,0.00373,0.01000,1.782
+9,mlp.up_proj,2.92221,0.01000,2.781
+9,mlp.gate_proj,3.49547,0.01000,2.581
+9,mlp.down_proj,0.00815,0.01000,21.297
+10,self_attn.k_proj,0.38617,0.01000,2.257
+10,self_attn.v_proj,0.14215,0.01000,1.981
+10,self_attn.q_proj,1.01572,0.01000,2.071
+10,self_attn.o_proj,0.00504,0.01000,1.781
+10,mlp.up_proj,3.23938,0.01000,2.784
+10,mlp.gate_proj,3.88586,0.01000,2.587
+10,mlp.down_proj,0.01044,0.01000,21.310
+11,self_attn.k_proj,0.35614,0.01000,2.319
+11,self_attn.v_proj,0.15298,0.01000,2.000
+11,self_attn.q_proj,0.98578,0.01000,2.064
+11,self_attn.o_proj,0.00663,0.01000,1.786
+11,mlp.up_proj,3.58904,0.01000,2.794
+11,mlp.gate_proj,4.25822,0.01000,2.593
+11,mlp.down_proj,0.01198,0.01000,21.301
+12,self_attn.k_proj,0.52366,0.01000,2.264
+12,self_attn.v_proj,0.15971,0.01000,1.999
+12,self_attn.q_proj,1.30964,0.01000,2.082
+12,self_attn.o_proj,0.00660,0.01000,1.792
+12,mlp.up_proj,3.72447,0.01000,2.807
+12,mlp.gate_proj,4.19370,0.01000,2.599
+12,mlp.down_proj,0.01304,0.01000,21.341
+13,self_attn.k_proj,0.42075,0.01000,2.264
+13,self_attn.v_proj,0.17944,0.01000,1.997
+13,self_attn.q_proj,1.09393,0.01000,2.061
+13,self_attn.o_proj,0.00842,0.01000,1.783
+13,mlp.up_proj,3.80394,0.01000,2.786
+13,mlp.gate_proj,4.12361,0.01000,2.586
+13,mlp.down_proj,0.01382,0.01000,21.350
+14,self_attn.k_proj,0.57203,0.01000,2.249
+14,self_attn.v_proj,0.24761,0.01000,2.011
+14,self_attn.q_proj,1.53858,0.01000,2.089
+14,self_attn.o_proj,0.01084,0.01000,1.788
+14,mlp.up_proj,4.26406,0.01000,2.800
+14,mlp.gate_proj,4.47931,0.01000,2.600
+14,mlp.down_proj,0.01616,0.01000,21.569
+15,self_attn.k_proj,0.60444,0.01000,2.269
+15,self_attn.v_proj,0.28068,0.01000,2.010
+15,self_attn.q_proj,1.54346,0.01000,2.069
+15,self_attn.o_proj,0.01179,0.01000,1.798
+15,mlp.up_proj,4.84652,0.01000,2.809
+15,mlp.gate_proj,5.05187,0.01000,2.622
+15,mlp.down_proj,0.01939,0.01000,21.408
+16,self_attn.k_proj,0.48121,0.01000,2.278
+16,self_attn.v_proj,0.30930,0.01000,2.003
+16,self_attn.q_proj,1.42801,0.01000,2.082
+16,self_attn.o_proj,0.01597,0.01000,1.802
+16,mlp.up_proj,5.28666,0.01000,2.816
+16,mlp.gate_proj,5.19811,0.01000,2.613
+16,mlp.down_proj,0.02249,0.01000,21.427
+17,self_attn.k_proj,0.65851,0.01000,2.268
+17,self_attn.v_proj,0.42666,0.01000,2.009
+17,self_attn.q_proj,1.98045,0.01000,2.086
+17,self_attn.o_proj,0.01775,0.01000,1.794
+17,mlp.up_proj,5.85325,0.01000,2.815
+17,mlp.gate_proj,5.96039,0.01000,2.630
+17,mlp.down_proj,0.02586,0.01000,21.502
+18,self_attn.k_proj,0.69702,0.01000,2.279
+18,self_attn.v_proj,0.43813,0.01000,2.027
+18,self_attn.q_proj,2.08248,0.01000,2.103
+18,self_attn.o_proj,0.02093,0.01000,1.783
+18,mlp.up_proj,6.47200,0.01000,2.818
+18,mlp.gate_proj,6.62978,0.01000,2.612
+18,mlp.down_proj,0.02928,0.01000,21.351
+19,self_attn.k_proj,0.66530,0.01000,2.270
+19,self_attn.v_proj,0.37858,0.01000,1.998
+19,self_attn.q_proj,1.88443,0.01000,2.063
+19,self_attn.o_proj,0.01306,0.01000,1.777
+19,mlp.up_proj,6.62988,0.01000,2.805
+19,mlp.gate_proj,6.94350,0.01000,2.606
+19,mlp.down_proj,0.03099,0.01000,21.314
+20,self_attn.k_proj,0.81135,0.01000,2.260
+20,self_attn.v_proj,0.38350,0.01000,2.001
+20,self_attn.q_proj,2.06830,0.01000,2.080
+20,self_attn.o_proj,0.02000,0.01000,1.792
+20,mlp.up_proj,7.43201,0.01000,2.814
+20,mlp.gate_proj,7.91840,0.01000,2.591
+20,mlp.down_proj,0.03627,0.01000,21.376
+21,self_attn.k_proj,0.70096,0.01000,2.265
+21,self_attn.v_proj,0.36705,0.01000,1.992
+21,self_attn.q_proj,1.92954,0.01000,2.078
+21,self_attn.o_proj,0.01325,0.01000,1.790
+21,mlp.up_proj,8.11715,0.01000,2.814
+21,mlp.gate_proj,8.93193,0.01000,2.603
+21,mlp.down_proj,0.04128,0.01000,21.374
+22,self_attn.k_proj,0.70791,0.01000,2.271
+22,self_attn.v_proj,0.39611,0.01000,1.998
+22,self_attn.q_proj,1.96275,0.01000,2.077
+22,self_attn.o_proj,0.01037,0.01000,1.797
+22,mlp.up_proj,8.33616,0.01000,2.806
+22,mlp.gate_proj,9.31193,0.01000,2.634
+22,mlp.down_proj,0.04284,0.01000,21.328
+23,self_attn.k_proj,0.79493,0.01000,2.246
+23,self_attn.v_proj,0.43445,0.01000,1.993
+23,self_attn.q_proj,2.07691,0.01000,2.072
+23,self_attn.o_proj,0.01359,0.01000,1.772
+23,mlp.up_proj,8.70170,0.01000,2.778
+23,mlp.gate_proj,9.77240,0.01000,2.599
+23,mlp.down_proj,0.04640,0.01000,21.282
+24,self_attn.k_proj,0.69773,0.01000,2.253
+24,self_attn.v_proj,0.41813,0.01000,1.981
+24,self_attn.q_proj,2.03928,0.01000,2.075
+24,self_attn.o_proj,0.01088,0.01000,1.778
+24,mlp.up_proj,8.80652,0.01000,2.797
+24,mlp.gate_proj,9.70903,0.01000,2.615
+24,mlp.down_proj,0.04913,0.01000,21.288
+25,self_attn.k_proj,0.79937,0.01000,2.258
+25,self_attn.v_proj,0.45575,0.01000,1.995
+25,self_attn.q_proj,2.14765,0.01000,2.068
+25,self_attn.o_proj,0.01823,0.01000,1.784
+25,mlp.up_proj,9.37267,0.01000,2.808
+25,mlp.gate_proj,10.64839,0.01000,2.595
+25,mlp.down_proj,0.05317,0.01000,21.295
+26,self_attn.k_proj,0.74382,0.01000,2.251
+26,self_attn.v_proj,0.50377,0.01000,1.997
+26,self_attn.q_proj,2.20458,0.01000,2.073
+26,self_attn.o_proj,0.00984,0.01000,1.790
+26,mlp.up_proj,9.93985,0.01000,2.800
+26,mlp.gate_proj,11.58556,0.01000,2.593
+26,mlp.down_proj,0.05753,0.01000,21.315
+27,self_attn.k_proj,0.55674,0.01000,2.261
+27,self_attn.v_proj,0.41296,0.01000,2.002
+27,self_attn.q_proj,1.76307,0.01000,2.085
+27,self_attn.o_proj,0.01223,0.01000,1.787
+27,mlp.up_proj,10.23073,0.01000,2.807
+27,mlp.gate_proj,11.83200,0.01000,2.604
+27,mlp.down_proj,0.06342,0.01000,21.314
+28,self_attn.k_proj,0.87544,0.01000,2.264
+28,self_attn.v_proj,0.58248,0.01000,1.997
+28,self_attn.q_proj,2.46918,0.01000,2.072
+28,self_attn.o_proj,0.01549,0.01000,1.791
+28,mlp.up_proj,11.14356,0.01000,2.812
+28,mlp.gate_proj,13.50384,0.01000,2.606
+28,mlp.down_proj,0.06041,0.01000,21.327
+29,self_attn.k_proj,0.74402,0.01000,2.266
+29,self_attn.v_proj,0.44873,0.01000,1.998
+29,self_attn.q_proj,2.05879,0.01000,2.067
+29,self_attn.o_proj,0.01401,0.01000,1.782
+29,mlp.up_proj,11.79072,0.01000,2.802
+29,mlp.gate_proj,14.35310,0.01000,2.613
+29,mlp.down_proj,0.06547,0.01000,21.298
+30,self_attn.k_proj,0.89739,0.01000,2.268
+30,self_attn.v_proj,0.65209,0.01000,2.000
+30,self_attn.q_proj,2.55776,0.01000,2.077
+30,self_attn.o_proj,0.01919,0.01000,1.784
+30,mlp.up_proj,12.68720,0.01000,2.822
+30,mlp.gate_proj,15.47283,0.01000,2.600
+30,mlp.down_proj,0.07124,0.01000,21.326
+31,self_attn.k_proj,0.74295,0.01000,2.263
+31,self_attn.v_proj,0.69481,0.01000,2.001
+31,self_attn.q_proj,2.30010,0.01000,2.080
+31,self_attn.o_proj,0.01393,0.01000,1.787
+31,mlp.up_proj,13.45879,0.01000,2.797
+31,mlp.gate_proj,16.16864,0.01000,2.591
+31,mlp.down_proj,0.07880,0.01000,21.472
+32,self_attn.k_proj,0.79344,0.01000,2.272
+32,self_attn.v_proj,0.70892,0.01000,2.017
+32,self_attn.q_proj,2.28913,0.01000,2.078
+32,self_attn.o_proj,0.01805,0.01000,1.796
+32,mlp.up_proj,14.49875,0.01000,2.820
+32,mlp.gate_proj,17.25286,0.01000,2.608
+32,mlp.down_proj,0.08879,0.01000,21.407
+33,self_attn.k_proj,0.73419,0.01000,2.271
+33,self_attn.v_proj,0.87160,0.01000,2.003
+33,self_attn.q_proj,2.29943,0.01000,2.085
+33,self_attn.o_proj,0.02166,0.01000,1.799
+33,mlp.up_proj,15.58575,0.01000,2.814
+33,mlp.gate_proj,17.85829,0.01000,2.610
+33,mlp.down_proj,0.10513,0.01000,21.379
+34,self_attn.k_proj,0.77376,0.01000,2.267
+34,self_attn.v_proj,0.95059,0.01000,1.988
+34,self_attn.q_proj,2.26492,0.01000,2.069
+34,self_attn.o_proj,0.04073,0.01000,1.795
+34,mlp.up_proj,17.55798,0.01000,2.807
+34,mlp.gate_proj,18.92542,0.01000,2.629
+34,mlp.down_proj,0.14563,0.01000,21.290
+35,self_attn.k_proj,0.71895,0.01000,2.254
+35,self_attn.v_proj,1.02711,0.01000,1.992
+35,self_attn.q_proj,2.11974,0.01000,2.074
+35,self_attn.o_proj,0.04285,0.01000,1.791
+35,mlp.up_proj,18.38759,0.01000,2.813
+35,mlp.gate_proj,19.09245,0.01000,2.626
+35,mlp.down_proj,0.17871,0.01000,21.360
+36,self_attn.k_proj,0.63797,0.01000,2.267
+36,self_attn.v_proj,1.15012,0.01000,1.992
+36,self_attn.q_proj,2.14942,0.01000,2.078
+36,self_attn.o_proj,0.07055,0.01000,1.793
+36,mlp.up_proj,20.40460,0.01000,2.806
+36,mlp.gate_proj,20.68090,0.01000,2.613
+36,mlp.down_proj,0.23435,0.01000,21.459
+37,self_attn.k_proj,0.61815,0.01000,2.286
+37,self_attn.v_proj,1.67784,0.01000,1.999
+37,self_attn.q_proj,2.23314,0.01000,2.078
+37,self_attn.o_proj,0.11842,0.01000,1.801
+37,mlp.up_proj,22.80294,0.01000,2.817
+37,mlp.gate_proj,22.93331,0.01000,2.646
+37,mlp.down_proj,0.33252,0.01000,21.297
+38,self_attn.k_proj,0.64086,0.01000,2.265
+38,self_attn.v_proj,1.42819,0.01000,1.996
+38,self_attn.q_proj,2.15125,0.01000,2.063
+38,self_attn.o_proj,0.12921,0.01000,1.790
+38,mlp.up_proj,21.23742,0.01000,2.812
+38,mlp.gate_proj,20.96081,0.01000,2.591
+38,mlp.down_proj,0.45870,0.01000,21.335
+39,self_attn.k_proj,0.54457,0.01000,2.252
+39,self_attn.v_proj,0.75971,0.01000,1.982
+39,self_attn.q_proj,1.85362,0.01000,2.080
+39,self_attn.o_proj,0.10673,0.01000,1.793
+39,mlp.up_proj,16.02508,0.01000,2.812
+39,mlp.gate_proj,16.86120,0.01000,2.596
+39,mlp.down_proj,0.53701,0.01000,21.575

quantize_config.json ADDED Viewed

	@@ -0,0 +1,21 @@

+{
+  "bits": 4,
+  "group_size": 32,
+  "desc_act": true,
+  "sym": true,
+  "lm_head": false,
+  "quant_method": "gptq",
+  "checkpoint_format": "gptq",
+  "pack_dtype": "int32",
+  "meta": {
+    "quantizer": [
+      "gptqmodel:1.9.0"
+    ],
+    "uri": "https://github.com/modelcloud/gptqmodel",
+    "damp_percent": 0.01,
+    "damp_auto_increment": 0.0025,
+    "static_groups": false,
+    "true_sequential": true,
+    "mse": 0.0
+  }
+}

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,1032 @@

+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "[INST]",
+    "[/INST]",
+    "[AVAILABLE_TOOLS]",
+    "[/AVAILABLE_TOOLS]",
+    "[TOOL_RESULTS]",
+    "[/TOOL_RESULTS]",
+    "[TOOL_CALLS]",
+    "[IMG]",
+    "<pad>",
+    "[IMG_BREAK]",
+    "[IMG_END]",
+    "[PREFIX]",
+    "[MIDDLE]",
+    "[SUFFIX]",
+    "[SYSTEM_PROMPT]",
+    "[/SYSTEM_PROMPT]",
+    "[TOOL_CONTENT]",
+    "<SPECIAL_20>",
+    "<SPECIAL_21>",
+    "<SPECIAL_22>",
+    "<SPECIAL_23>",
+    "<SPECIAL_24>",
+    "<SPECIAL_25>",
+    "<SPECIAL_26>",
+    "<SPECIAL_27>",
+    "<SPECIAL_28>",
+    "<SPECIAL_29>",
+    "<SPECIAL_30>",
+    "<SPECIAL_31>",
+    "<SPECIAL_32>",
+    "<SPECIAL_33>",
+    "<SPECIAL_34>",
+    "<SPECIAL_35>",
+    "<SPECIAL_36>",
+    "<SPECIAL_37>",
+    "<SPECIAL_38>",
+    "<SPECIAL_39>",
+    "<SPECIAL_40>",
+    "<SPECIAL_41>",
+    "<SPECIAL_42>",
+    "<SPECIAL_43>",
+    "<SPECIAL_44>",
+    "<SPECIAL_45>",
+    "<SPECIAL_46>",
+    "<SPECIAL_47>",
+    "<SPECIAL_48>",
+    "<SPECIAL_49>",
+    "<SPECIAL_50>",
+    "<SPECIAL_51>",
+    "<SPECIAL_52>",
+    "<SPECIAL_53>",
+    "<SPECIAL_54>",
+    "<SPECIAL_55>",
+    "<SPECIAL_56>",
+    "<SPECIAL_57>",
+    "<SPECIAL_58>",
+    "<SPECIAL_59>",
+    "<SPECIAL_60>",
+    "<SPECIAL_61>",
+    "<SPECIAL_62>",
+    "<SPECIAL_63>",
+    "<SPECIAL_64>",
+    "<SPECIAL_65>",
+    "<SPECIAL_66>",
+    "<SPECIAL_67>",
+    "<SPECIAL_68>",
+    "<SPECIAL_69>",
+    "<SPECIAL_70>",
+    "<SPECIAL_71>",
+    "<SPECIAL_72>",
+    "<SPECIAL_73>",
+    "<SPECIAL_74>",
+    "<SPECIAL_75>",
+    "<SPECIAL_76>",
+    "<SPECIAL_77>",
+    "<SPECIAL_78>",
+    "<SPECIAL_79>",
+    "<SPECIAL_80>",
+    "<SPECIAL_81>",
+    "<SPECIAL_82>",
+    "<SPECIAL_83>",
+    "<SPECIAL_84>",
+    "<SPECIAL_85>",
+    "<SPECIAL_86>",
+    "<SPECIAL_87>",
+    "<SPECIAL_88>",
+    "<SPECIAL_89>",
+    "<SPECIAL_90>",
+    "<SPECIAL_91>",
+    "<SPECIAL_92>",
+    "<SPECIAL_93>",
+    "<SPECIAL_94>",
+    "<SPECIAL_95>",
+    "<SPECIAL_96>",
+    "<SPECIAL_97>",
+    "<SPECIAL_98>",
+    "<SPECIAL_99>",
+    "<SPECIAL_100>",
+    "<SPECIAL_101>",
+    "<SPECIAL_102>",
+    "<SPECIAL_103>",
+    "<SPECIAL_104>",
+    "<SPECIAL_105>",
+    "<SPECIAL_106>",
+    "<SPECIAL_107>",
+    "<SPECIAL_108>",
+    "<SPECIAL_109>",
+    "<SPECIAL_110>",
+    "<SPECIAL_111>",
+    "<SPECIAL_112>",
+    "<SPECIAL_113>",
+    "<SPECIAL_114>",
+    "<SPECIAL_115>",
+    "<SPECIAL_116>",
+    "<SPECIAL_117>",
+    "<SPECIAL_118>",
+    "<SPECIAL_119>",
+    "<SPECIAL_120>",
+    "<SPECIAL_121>",
+    "<SPECIAL_122>",
+    "<SPECIAL_123>",
+    "<SPECIAL_124>",
+    "<SPECIAL_125>",
+    "<SPECIAL_126>",
+    "<SPECIAL_127>",
+    "<SPECIAL_128>",
+    "<SPECIAL_129>",
+    "<SPECIAL_130>",
+    "<SPECIAL_131>",
+    "<SPECIAL_132>",
+    "<SPECIAL_133>",
+    "<SPECIAL_134>",
+    "<SPECIAL_135>",
+    "<SPECIAL_136>",
+    "<SPECIAL_137>",
+    "<SPECIAL_138>",
+    "<SPECIAL_139>",
+    "<SPECIAL_140>",
+    "<SPECIAL_141>",
+    "<SPECIAL_142>",
+    "<SPECIAL_143>",
+    "<SPECIAL_144>",
+    "<SPECIAL_145>",
+    "<SPECIAL_146>",
+    "<SPECIAL_147>",
+    "<SPECIAL_148>",
+    "<SPECIAL_149>",
+    "<SPECIAL_150>",
+    "<SPECIAL_151>",
+    "<SPECIAL_152>",
+    "<SPECIAL_153>",
+    "<SPECIAL_154>",
+    "<SPECIAL_155>",
+    "<SPECIAL_156>",
+    "<SPECIAL_157>",
+    "<SPECIAL_158>",
+    "<SPECIAL_159>",
+    "<SPECIAL_160>",
+    "<SPECIAL_161>",
+    "<SPECIAL_162>",
+    "<SPECIAL_163>",
+    "<SPECIAL_164>",
+    "<SPECIAL_165>",
+    "<SPECIAL_166>",
+    "<SPECIAL_167>",
+    "<SPECIAL_168>",
+    "<SPECIAL_169>",
+    "<SPECIAL_170>",
+    "<SPECIAL_171>",
+    "<SPECIAL_172>",
+    "<SPECIAL_173>",
+    "<SPECIAL_174>",
+    "<SPECIAL_175>",
+    "<SPECIAL_176>",
+    "<SPECIAL_177>",
+    "<SPECIAL_178>",
+    "<SPECIAL_179>",
+    "<SPECIAL_180>",
+    "<SPECIAL_181>",
+    "<SPECIAL_182>",
+    "<SPECIAL_183>",
+    "<SPECIAL_184>",
+    "<SPECIAL_185>",
+    "<SPECIAL_186>",
+    "<SPECIAL_187>",
+    "<SPECIAL_188>",
+    "<SPECIAL_189>",
+    "<SPECIAL_190>",
+    "<SPECIAL_191>",
+    "<SPECIAL_192>",
+    "<SPECIAL_193>",
+    "<SPECIAL_194>",
+    "<SPECIAL_195>",
+    "<SPECIAL_196>",
+    "<SPECIAL_197>",
+    "<SPECIAL_198>",
+    "<SPECIAL_199>",
+    "<SPECIAL_200>",
+    "<SPECIAL_201>",
+    "<SPECIAL_202>",
+    "<SPECIAL_203>",
+    "<SPECIAL_204>",
+    "<SPECIAL_205>",
+    "<SPECIAL_206>",
+    "<SPECIAL_207>",
+    "<SPECIAL_208>",
+    "<SPECIAL_209>",
+    "<SPECIAL_210>",
+    "<SPECIAL_211>",
+    "<SPECIAL_212>",
+    "<SPECIAL_213>",
+    "<SPECIAL_214>",
+    "<SPECIAL_215>",
+    "<SPECIAL_216>",
+    "<SPECIAL_217>",
+    "<SPECIAL_218>",
+    "<SPECIAL_219>",
+    "<SPECIAL_220>",
+    "<SPECIAL_221>",
+    "<SPECIAL_222>",
+    "<SPECIAL_223>",
+    "<SPECIAL_224>",
+    "<SPECIAL_225>",
+    "<SPECIAL_226>",
+    "<SPECIAL_227>",
+    "<SPECIAL_228>",
+    "<SPECIAL_229>",
+    "<SPECIAL_230>",
+    "<SPECIAL_231>",
+    "<SPECIAL_232>",
+    "<SPECIAL_233>",
+    "<SPECIAL_234>",
+    "<SPECIAL_235>",
+    "<SPECIAL_236>",
+    "<SPECIAL_237>",
+    "<SPECIAL_238>",
+    "<SPECIAL_239>",
+    "<SPECIAL_240>",
+    "<SPECIAL_241>",
+    "<SPECIAL_242>",
+    "<SPECIAL_243>",
+    "<SPECIAL_244>",
+    "<SPECIAL_245>",
+    "<SPECIAL_246>",
+    "<SPECIAL_247>",
+    "<SPECIAL_248>",
+    "<SPECIAL_249>",
+    "<SPECIAL_250>",
+    "<SPECIAL_251>",
+    "<SPECIAL_252>",
+    "<SPECIAL_253>",
+    "<SPECIAL_254>",
+    "<SPECIAL_255>",
+    "<SPECIAL_256>",
+    "<SPECIAL_257>",
+    "<SPECIAL_258>",
+    "<SPECIAL_259>",
+    "<SPECIAL_260>",
+    "<SPECIAL_261>",
+    "<SPECIAL_262>",
+    "<SPECIAL_263>",
+    "<SPECIAL_264>",
+    "<SPECIAL_265>",
+    "<SPECIAL_266>",
+    "<SPECIAL_267>",
+    "<SPECIAL_268>",
+    "<SPECIAL_269>",
+    "<SPECIAL_270>",
+    "<SPECIAL_271>",
+    "<SPECIAL_272>",
+    "<SPECIAL_273>",
+    "<SPECIAL_274>",
+    "<SPECIAL_275>",
+    "<SPECIAL_276>",
+    "<SPECIAL_277>",
+    "<SPECIAL_278>",
+    "<SPECIAL_279>",
+    "<SPECIAL_280>",
+    "<SPECIAL_281>",
+    "<SPECIAL_282>",
+    "<SPECIAL_283>",
+    "<SPECIAL_284>",
+    "<SPECIAL_285>",
+    "<SPECIAL_286>",
+    "<SPECIAL_287>",
+    "<SPECIAL_288>",
+    "<SPECIAL_289>",
+    "<SPECIAL_290>",
+    "<SPECIAL_291>",
+    "<SPECIAL_292>",
+    "<SPECIAL_293>",
+    "<SPECIAL_294>",
+    "<SPECIAL_295>",
+    "<SPECIAL_296>",
+    "<SPECIAL_297>",
+    "<SPECIAL_298>",
+    "<SPECIAL_299>",
+    "<SPECIAL_300>",
+    "<SPECIAL_301>",
+    "<SPECIAL_302>",
+    "<SPECIAL_303>",
+    "<SPECIAL_304>",
+    "<SPECIAL_305>",
+    "<SPECIAL_306>",
+    "<SPECIAL_307>",
+    "<SPECIAL_308>",
+    "<SPECIAL_309>",
+    "<SPECIAL_310>",
+    "<SPECIAL_311>",
+    "<SPECIAL_312>",
+    "<SPECIAL_313>",
+    "<SPECIAL_314>",
+    "<SPECIAL_315>",
+    "<SPECIAL_316>",
+    "<SPECIAL_317>",
+    "<SPECIAL_318>",
+    "<SPECIAL_319>",
+    "<SPECIAL_320>",
+    "<SPECIAL_321>",
+    "<SPECIAL_322>",
+    "<SPECIAL_323>",
+    "<SPECIAL_324>",
+    "<SPECIAL_325>",
+    "<SPECIAL_326>",
+    "<SPECIAL_327>",
+    "<SPECIAL_328>",
+    "<SPECIAL_329>",
+    "<SPECIAL_330>",
+    "<SPECIAL_331>",
+    "<SPECIAL_332>",
+    "<SPECIAL_333>",
+    "<SPECIAL_334>",
+    "<SPECIAL_335>",
+    "<SPECIAL_336>",
+    "<SPECIAL_337>",
+    "<SPECIAL_338>",
+    "<SPECIAL_339>",
+    "<SPECIAL_340>",
+    "<SPECIAL_341>",
+    "<SPECIAL_342>",
+    "<SPECIAL_343>",
+    "<SPECIAL_344>",
+    "<SPECIAL_345>",
+    "<SPECIAL_346>",
+    "<SPECIAL_347>",
+    "<SPECIAL_348>",
+    "<SPECIAL_349>",
+    "<SPECIAL_350>",
+    "<SPECIAL_351>",
+    "<SPECIAL_352>",
+    "<SPECIAL_353>",
+    "<SPECIAL_354>",
+    "<SPECIAL_355>",
+    "<SPECIAL_356>",
+    "<SPECIAL_357>",
+    "<SPECIAL_358>",
+    "<SPECIAL_359>",
+    "<SPECIAL_360>",
+    "<SPECIAL_361>",
+    "<SPECIAL_362>",
+    "<SPECIAL_363>",
+    "<SPECIAL_364>",
+    "<SPECIAL_365>",
+    "<SPECIAL_366>",
+    "<SPECIAL_367>",
+    "<SPECIAL_368>",
+    "<SPECIAL_369>",
+    "<SPECIAL_370>",
+    "<SPECIAL_371>",
+    "<SPECIAL_372>",
+    "<SPECIAL_373>",
+    "<SPECIAL_374>",
+    "<SPECIAL_375>",
+    "<SPECIAL_376>",
+    "<SPECIAL_377>",
+    "<SPECIAL_378>",
+    "<SPECIAL_379>",
+    "<SPECIAL_380>",
+    "<SPECIAL_381>",
+    "<SPECIAL_382>",
+    "<SPECIAL_383>",
+    "<SPECIAL_384>",
+    "<SPECIAL_385>",
+    "<SPECIAL_386>",
+    "<SPECIAL_387>",
+    "<SPECIAL_388>",
+    "<SPECIAL_389>",
+    "<SPECIAL_390>",
+    "<SPECIAL_391>",
+    "<SPECIAL_392>",
+    "<SPECIAL_393>",
+    "<SPECIAL_394>",
+    "<SPECIAL_395>",
+    "<SPECIAL_396>",
+    "<SPECIAL_397>",
+    "<SPECIAL_398>",
+    "<SPECIAL_399>",
+    "<SPECIAL_400>",
+    "<SPECIAL_401>",
+    "<SPECIAL_402>",
+    "<SPECIAL_403>",
+    "<SPECIAL_404>",
+    "<SPECIAL_405>",
+    "<SPECIAL_406>",
+    "<SPECIAL_407>",
+    "<SPECIAL_408>",
+    "<SPECIAL_409>",
+    "<SPECIAL_410>",
+    "<SPECIAL_411>",
+    "<SPECIAL_412>",
+    "<SPECIAL_413>",
+    "<SPECIAL_414>",
+    "<SPECIAL_415>",
+    "<SPECIAL_416>",
+    "<SPECIAL_417>",
+    "<SPECIAL_418>",
+    "<SPECIAL_419>",
+    "<SPECIAL_420>",
+    "<SPECIAL_421>",
+    "<SPECIAL_422>",
+    "<SPECIAL_423>",
+    "<SPECIAL_424>",
+    "<SPECIAL_425>",
+    "<SPECIAL_426>",
+    "<SPECIAL_427>",
+    "<SPECIAL_428>",
+    "<SPECIAL_429>",
+    "<SPECIAL_430>",
+    "<SPECIAL_431>",
+    "<SPECIAL_432>",
+    "<SPECIAL_433>",
+    "<SPECIAL_434>",
+    "<SPECIAL_435>",
+    "<SPECIAL_436>",
+    "<SPECIAL_437>",
+    "<SPECIAL_438>",
+    "<SPECIAL_439>",
+    "<SPECIAL_440>",
+    "<SPECIAL_441>",
+    "<SPECIAL_442>",
+    "<SPECIAL_443>",
+    "<SPECIAL_444>",
+    "<SPECIAL_445>",
+    "<SPECIAL_446>",
+    "<SPECIAL_447>",
+    "<SPECIAL_448>",
+    "<SPECIAL_449>",
+    "<SPECIAL_450>",
+    "<SPECIAL_451>",
+    "<SPECIAL_452>",
+    "<SPECIAL_453>",
+    "<SPECIAL_454>",
+    "<SPECIAL_455>",
+    "<SPECIAL_456>",
+    "<SPECIAL_457>",
+    "<SPECIAL_458>",
+    "<SPECIAL_459>",
+    "<SPECIAL_460>",
+    "<SPECIAL_461>",
+    "<SPECIAL_462>",
+    "<SPECIAL_463>",
+    "<SPECIAL_464>",
+    "<SPECIAL_465>",
+    "<SPECIAL_466>",
+    "<SPECIAL_467>",
+    "<SPECIAL_468>",
+    "<SPECIAL_469>",
+    "<SPECIAL_470>",
+    "<SPECIAL_471>",
+    "<SPECIAL_472>",
+    "<SPECIAL_473>",
+    "<SPECIAL_474>",
+    "<SPECIAL_475>",
+    "<SPECIAL_476>",
+    "<SPECIAL_477>",
+    "<SPECIAL_478>",
+    "<SPECIAL_479>",
+    "<SPECIAL_480>",
+    "<SPECIAL_481>",
+    "<SPECIAL_482>",
+    "<SPECIAL_483>",
+    "<SPECIAL_484>",
+    "<SPECIAL_485>",
+    "<SPECIAL_486>",
+    "<SPECIAL_487>",
+    "<SPECIAL_488>",
+    "<SPECIAL_489>",
+    "<SPECIAL_490>",
+    "<SPECIAL_491>",
+    "<SPECIAL_492>",
+    "<SPECIAL_493>",
+    "<SPECIAL_494>",
+    "<SPECIAL_495>",
+    "<SPECIAL_496>",
+    "<SPECIAL_497>",
+    "<SPECIAL_498>",
+    "<SPECIAL_499>",
+    "<SPECIAL_500>",
+    "<SPECIAL_501>",
+    "<SPECIAL_502>",
+    "<SPECIAL_503>",
+    "<SPECIAL_504>",
+    "<SPECIAL_505>",
+    "<SPECIAL_506>",
+    "<SPECIAL_507>",
+    "<SPECIAL_508>",
+    "<SPECIAL_509>",
+    "<SPECIAL_510>",
+    "<SPECIAL_511>",
+    "<SPECIAL_512>",
+    "<SPECIAL_513>",
+    "<SPECIAL_514>",
+    "<SPECIAL_515>",
+    "<SPECIAL_516>",
+    "<SPECIAL_517>",
+    "<SPECIAL_518>",
+    "<SPECIAL_519>",
+    "<SPECIAL_520>",
+    "<SPECIAL_521>",
+    "<SPECIAL_522>",
+    "<SPECIAL_523>",
+    "<SPECIAL_524>",
+    "<SPECIAL_525>",
+    "<SPECIAL_526>",
+    "<SPECIAL_527>",
+    "<SPECIAL_528>",
+    "<SPECIAL_529>",
+    "<SPECIAL_530>",
+    "<SPECIAL_531>",
+    "<SPECIAL_532>",
+    "<SPECIAL_533>",
+    "<SPECIAL_534>",
+    "<SPECIAL_535>",
+    "<SPECIAL_536>",
+    "<SPECIAL_537>",
+    "<SPECIAL_538>",
+    "<SPECIAL_539>",
+    "<SPECIAL_540>",
+    "<SPECIAL_541>",
+    "<SPECIAL_542>",
+    "<SPECIAL_543>",
+    "<SPECIAL_544>",
+    "<SPECIAL_545>",
+    "<SPECIAL_546>",
+    "<SPECIAL_547>",
+    "<SPECIAL_548>",
+    "<SPECIAL_549>",
+    "<SPECIAL_550>",
+    "<SPECIAL_551>",
+    "<SPECIAL_552>",
+    "<SPECIAL_553>",
+    "<SPECIAL_554>",
+    "<SPECIAL_555>",
+    "<SPECIAL_556>",
+    "<SPECIAL_557>",
+    "<SPECIAL_558>",
+    "<SPECIAL_559>",
+    "<SPECIAL_560>",
+    "<SPECIAL_561>",
+    "<SPECIAL_562>",
+    "<SPECIAL_563>",
+    "<SPECIAL_564>",
+    "<SPECIAL_565>",
+    "<SPECIAL_566>",
+    "<SPECIAL_567>",
+    "<SPECIAL_568>",
+    "<SPECIAL_569>",
+    "<SPECIAL_570>",
+    "<SPECIAL_571>",
+    "<SPECIAL_572>",
+    "<SPECIAL_573>",
+    "<SPECIAL_574>",
+    "<SPECIAL_575>",
+    "<SPECIAL_576>",
+    "<SPECIAL_577>",
+    "<SPECIAL_578>",
+    "<SPECIAL_579>",
+    "<SPECIAL_580>",
+    "<SPECIAL_581>",
+    "<SPECIAL_582>",
+    "<SPECIAL_583>",
+    "<SPECIAL_584>",
+    "<SPECIAL_585>",
+    "<SPECIAL_586>",
+    "<SPECIAL_587>",
+    "<SPECIAL_588>",
+    "<SPECIAL_589>",
+    "<SPECIAL_590>",
+    "<SPECIAL_591>",
+    "<SPECIAL_592>",
+    "<SPECIAL_593>",
+    "<SPECIAL_594>",
+    "<SPECIAL_595>",
+    "<SPECIAL_596>",
+    "<SPECIAL_597>",
+    "<SPECIAL_598>",
+    "<SPECIAL_599>",
+    "<SPECIAL_600>",
+    "<SPECIAL_601>",
+    "<SPECIAL_602>",
+    "<SPECIAL_603>",
+    "<SPECIAL_604>",
+    "<SPECIAL_605>",
+    "<SPECIAL_606>",
+    "<SPECIAL_607>",
+    "<SPECIAL_608>",
+    "<SPECIAL_609>",
+    "<SPECIAL_610>",
+    "<SPECIAL_611>",
+    "<SPECIAL_612>",
+    "<SPECIAL_613>",
+    "<SPECIAL_614>",
+    "<SPECIAL_615>",
+    "<SPECIAL_616>",
+    "<SPECIAL_617>",
+    "<SPECIAL_618>",
+    "<SPECIAL_619>",
+    "<SPECIAL_620>",
+    "<SPECIAL_621>",
+    "<SPECIAL_622>",
+    "<SPECIAL_623>",
+    "<SPECIAL_624>",
+    "<SPECIAL_625>",
+    "<SPECIAL_626>",
+    "<SPECIAL_627>",
+    "<SPECIAL_628>",
+    "<SPECIAL_629>",
+    "<SPECIAL_630>",
+    "<SPECIAL_631>",
+    "<SPECIAL_632>",
+    "<SPECIAL_633>",
+    "<SPECIAL_634>",
+    "<SPECIAL_635>",
+    "<SPECIAL_636>",
+    "<SPECIAL_637>",
+    "<SPECIAL_638>",
+    "<SPECIAL_639>",
+    "<SPECIAL_640>",
+    "<SPECIAL_641>",
+    "<SPECIAL_642>",
+    "<SPECIAL_643>",
+    "<SPECIAL_644>",
+    "<SPECIAL_645>",
+    "<SPECIAL_646>",
+    "<SPECIAL_647>",
+    "<SPECIAL_648>",
+    "<SPECIAL_649>",
+    "<SPECIAL_650>",
+    "<SPECIAL_651>",
+    "<SPECIAL_652>",
+    "<SPECIAL_653>",
+    "<SPECIAL_654>",
+    "<SPECIAL_655>",
+    "<SPECIAL_656>",
+    "<SPECIAL_657>",
+    "<SPECIAL_658>",
+    "<SPECIAL_659>",
+    "<SPECIAL_660>",
+    "<SPECIAL_661>",
+    "<SPECIAL_662>",
+    "<SPECIAL_663>",
+    "<SPECIAL_664>",
+    "<SPECIAL_665>",
+    "<SPECIAL_666>",
+    "<SPECIAL_667>",
+    "<SPECIAL_668>",
+    "<SPECIAL_669>",
+    "<SPECIAL_670>",
+    "<SPECIAL_671>",
+    "<SPECIAL_672>",
+    "<SPECIAL_673>",
+    "<SPECIAL_674>",
+    "<SPECIAL_675>",
+    "<SPECIAL_676>",
+    "<SPECIAL_677>",
+    "<SPECIAL_678>",
+    "<SPECIAL_679>",
+    "<SPECIAL_680>",
+    "<SPECIAL_681>",
+    "<SPECIAL_682>",
+    "<SPECIAL_683>",
+    "<SPECIAL_684>",
+    "<SPECIAL_685>",
+    "<SPECIAL_686>",
+    "<SPECIAL_687>",
+    "<SPECIAL_688>",
+    "<SPECIAL_689>",
+    "<SPECIAL_690>",
+    "<SPECIAL_691>",
+    "<SPECIAL_692>",
+    "<SPECIAL_693>",
+    "<SPECIAL_694>",
+    "<SPECIAL_695>",
+    "<SPECIAL_696>",
+    "<SPECIAL_697>",
+    "<SPECIAL_698>",
+    "<SPECIAL_699>",
+    "<SPECIAL_700>",
+    "<SPECIAL_701>",
+    "<SPECIAL_702>",
+    "<SPECIAL_703>",
+    "<SPECIAL_704>",
+    "<SPECIAL_705>",
+    "<SPECIAL_706>",
+    "<SPECIAL_707>",
+    "<SPECIAL_708>",
+    "<SPECIAL_709>",
+    "<SPECIAL_710>",
+    "<SPECIAL_711>",
+    "<SPECIAL_712>",
+    "<SPECIAL_713>",
+    "<SPECIAL_714>",
+    "<SPECIAL_715>",
+    "<SPECIAL_716>",
+    "<SPECIAL_717>",
+    "<SPECIAL_718>",
+    "<SPECIAL_719>",
+    "<SPECIAL_720>",
+    "<SPECIAL_721>",
+    "<SPECIAL_722>",
+    "<SPECIAL_723>",
+    "<SPECIAL_724>",
+    "<SPECIAL_725>",
+    "<SPECIAL_726>",
+    "<SPECIAL_727>",
+    "<SPECIAL_728>",
+    "<SPECIAL_729>",
+    "<SPECIAL_730>",
+    "<SPECIAL_731>",
+    "<SPECIAL_732>",
+    "<SPECIAL_733>",
+    "<SPECIAL_734>",
+    "<SPECIAL_735>",
+    "<SPECIAL_736>",
+    "<SPECIAL_737>",
+    "<SPECIAL_738>",
+    "<SPECIAL_739>",
+    "<SPECIAL_740>",
+    "<SPECIAL_741>",
+    "<SPECIAL_742>",
+    "<SPECIAL_743>",
+    "<SPECIAL_744>",
+    "<SPECIAL_745>",
+    "<SPECIAL_746>",
+    "<SPECIAL_747>",
+    "<SPECIAL_748>",
+    "<SPECIAL_749>",
+    "<SPECIAL_750>",
+    "<SPECIAL_751>",
+    "<SPECIAL_752>",
+    "<SPECIAL_753>",
+    "<SPECIAL_754>",
+    "<SPECIAL_755>",
+    "<SPECIAL_756>",
+    "<SPECIAL_757>",
+    "<SPECIAL_758>",
+    "<SPECIAL_759>",
+    "<SPECIAL_760>",
+    "<SPECIAL_761>",
+    "<SPECIAL_762>",
+    "<SPECIAL_763>",
+    "<SPECIAL_764>",
+    "<SPECIAL_765>",
+    "<SPECIAL_766>",
+    "<SPECIAL_767>",
+    "<SPECIAL_768>",
+    "<SPECIAL_769>",
+    "<SPECIAL_770>",
+    "<SPECIAL_771>",
+    "<SPECIAL_772>",
+    "<SPECIAL_773>",
+    "<SPECIAL_774>",
+    "<SPECIAL_775>",
+    "<SPECIAL_776>",
+    "<SPECIAL_777>",
+    "<SPECIAL_778>",
+    "<SPECIAL_779>",
+    "<SPECIAL_780>",
+    "<SPECIAL_781>",
+    "<SPECIAL_782>",
+    "<SPECIAL_783>",
+    "<SPECIAL_784>",
+    "<SPECIAL_785>",
+    "<SPECIAL_786>",
+    "<SPECIAL_787>",
+    "<SPECIAL_788>",
+    "<SPECIAL_789>",
+    "<SPECIAL_790>",
+    "<SPECIAL_791>",
+    "<SPECIAL_792>",
+    "<SPECIAL_793>",
+    "<SPECIAL_794>",
+    "<SPECIAL_795>",
+    "<SPECIAL_796>",
+    "<SPECIAL_797>",
+    "<SPECIAL_798>",
+    "<SPECIAL_799>",
+    "<SPECIAL_800>",
+    "<SPECIAL_801>",
+    "<SPECIAL_802>",
+    "<SPECIAL_803>",
+    "<SPECIAL_804>",
+    "<SPECIAL_805>",
+    "<SPECIAL_806>",
+    "<SPECIAL_807>",
+    "<SPECIAL_808>",
+    "<SPECIAL_809>",
+    "<SPECIAL_810>",
+    "<SPECIAL_811>",
+    "<SPECIAL_812>",
+    "<SPECIAL_813>",
+    "<SPECIAL_814>",
+    "<SPECIAL_815>",
+    "<SPECIAL_816>",
+    "<SPECIAL_817>",
+    "<SPECIAL_818>",
+    "<SPECIAL_819>",
+    "<SPECIAL_820>",
+    "<SPECIAL_821>",
+    "<SPECIAL_822>",
+    "<SPECIAL_823>",
+    "<SPECIAL_824>",
+    "<SPECIAL_825>",
+    "<SPECIAL_826>",
+    "<SPECIAL_827>",
+    "<SPECIAL_828>",
+    "<SPECIAL_829>",
+    "<SPECIAL_830>",
+    "<SPECIAL_831>",
+    "<SPECIAL_832>",
+    "<SPECIAL_833>",
+    "<SPECIAL_834>",
+    "<SPECIAL_835>",
+    "<SPECIAL_836>",
+    "<SPECIAL_837>",
+    "<SPECIAL_838>",
+    "<SPECIAL_839>",
+    "<SPECIAL_840>",
+    "<SPECIAL_841>",
+    "<SPECIAL_842>",
+    "<SPECIAL_843>",
+    "<SPECIAL_844>",
+    "<SPECIAL_845>",
+    "<SPECIAL_846>",
+    "<SPECIAL_847>",
+    "<SPECIAL_848>",
+    "<SPECIAL_849>",
+    "<SPECIAL_850>",
+    "<SPECIAL_851>",
+    "<SPECIAL_852>",
+    "<SPECIAL_853>",
+    "<SPECIAL_854>",
+    "<SPECIAL_855>",
+    "<SPECIAL_856>",
+    "<SPECIAL_857>",
+    "<SPECIAL_858>",
+    "<SPECIAL_859>",
+    "<SPECIAL_860>",
+    "<SPECIAL_861>",
+    "<SPECIAL_862>",
+    "<SPECIAL_863>",
+    "<SPECIAL_864>",
+    "<SPECIAL_865>",
+    "<SPECIAL_866>",
+    "<SPECIAL_867>",
+    "<SPECIAL_868>",
+    "<SPECIAL_869>",
+    "<SPECIAL_870>",
+    "<SPECIAL_871>",
+    "<SPECIAL_872>",
+    "<SPECIAL_873>",
+    "<SPECIAL_874>",
+    "<SPECIAL_875>",
+    "<SPECIAL_876>",
+    "<SPECIAL_877>",
+    "<SPECIAL_878>",
+    "<SPECIAL_879>",
+    "<SPECIAL_880>",
+    "<SPECIAL_881>",
+    "<SPECIAL_882>",
+    "<SPECIAL_883>",
+    "<SPECIAL_884>",
+    "<SPECIAL_885>",
+    "<SPECIAL_886>",
+    "<SPECIAL_887>",
+    "<SPECIAL_888>",
+    "<SPECIAL_889>",
+    "<SPECIAL_890>",
+    "<SPECIAL_891>",
+    "<SPECIAL_892>",
+    "<SPECIAL_893>",
+    "<SPECIAL_894>",
+    "<SPECIAL_895>",
+    "<SPECIAL_896>",
+    "<SPECIAL_897>",
+    "<SPECIAL_898>",
+    "<SPECIAL_899>",
+    "<SPECIAL_900>",
+    "<SPECIAL_901>",
+    "<SPECIAL_902>",
+    "<SPECIAL_903>",
+    "<SPECIAL_904>",
+    "<SPECIAL_905>",
+    "<SPECIAL_906>",
+    "<SPECIAL_907>",
+    "<SPECIAL_908>",
+    "<SPECIAL_909>",
+    "<SPECIAL_910>",
+    "<SPECIAL_911>",
+    "<SPECIAL_912>",
+    "<SPECIAL_913>",
+    "<SPECIAL_914>",
+    "<SPECIAL_915>",
+    "<SPECIAL_916>",
+    "<SPECIAL_917>",
+    "<SPECIAL_918>",
+    "<SPECIAL_919>",
+    "<SPECIAL_920>",
+    "<SPECIAL_921>",
+    "<SPECIAL_922>",
+    "<SPECIAL_923>",
+    "<SPECIAL_924>",
+    "<SPECIAL_925>",
+    "<SPECIAL_926>",
+    "<SPECIAL_927>",
+    "<SPECIAL_928>",
+    "<SPECIAL_929>",
+    "<SPECIAL_930>",
+    "<SPECIAL_931>",
+    "<SPECIAL_932>",
+    "<SPECIAL_933>",
+    "<SPECIAL_934>",
+    "<SPECIAL_935>",
+    "<SPECIAL_936>",
+    "<SPECIAL_937>",
+    "<SPECIAL_938>",
+    "<SPECIAL_939>",
+    "<SPECIAL_940>",
+    "<SPECIAL_941>",
+    "<SPECIAL_942>",
+    "<SPECIAL_943>",
+    "<SPECIAL_944>",
+    "<SPECIAL_945>",
+    "<SPECIAL_946>",
+    "<SPECIAL_947>",
+    "<SPECIAL_948>",
+    "<SPECIAL_949>",
+    "<SPECIAL_950>",
+    "<SPECIAL_951>",
+    "<SPECIAL_952>",
+    "<SPECIAL_953>",
+    "<SPECIAL_954>",
+    "<SPECIAL_955>",
+    "<SPECIAL_956>",
+    "<SPECIAL_957>",
+    "<SPECIAL_958>",
+    "<SPECIAL_959>",
+    "<SPECIAL_960>",
+    "<SPECIAL_961>",
+    "<SPECIAL_962>",
+    "<SPECIAL_963>",
+    "<SPECIAL_964>",
+    "<SPECIAL_965>",
+    "<SPECIAL_966>",
+    "<SPECIAL_967>",
+    "<SPECIAL_968>",
+    "<SPECIAL_969>",
+    "<SPECIAL_970>",
+    "<SPECIAL_971>",
+    "<SPECIAL_972>",
+    "<SPECIAL_973>",
+    "<SPECIAL_974>",
+    "<SPECIAL_975>",
+    "<SPECIAL_976>",
+    "<SPECIAL_977>",
+    "<SPECIAL_978>",
+    "<SPECIAL_979>",
+    "<SPECIAL_980>",
+    "<SPECIAL_981>",
+    "<SPECIAL_982>",
+    "<SPECIAL_983>",
+    "<SPECIAL_984>",
+    "<SPECIAL_985>",
+    "<SPECIAL_986>",
+    "<SPECIAL_987>",
+    "<SPECIAL_988>",
+    "<SPECIAL_989>",
+    "<SPECIAL_990>",
+    "<SPECIAL_991>",
+    "<SPECIAL_992>",
+    "<SPECIAL_993>",
+    "<SPECIAL_994>",
+    "<SPECIAL_995>",
+    "<SPECIAL_996>",
+    "<SPECIAL_997>",
+    "<SPECIAL_998>",
+    "<SPECIAL_999>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1c3ccea3ae921ba5c2694edccb7263901c00d4896972743a4a53cfd6df4c4475
+size 17078136

tokenizer_config.json ADDED Viewed

The diff for this file is too large to render. See raw diff