Upload folder using huggingface_hub

README.md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+tags:
+- finetuned
+- quantized
+- 4-bit
+- gptq
+- transformers
+- pytorch
+- safetensors
+- mistral
+- text-generation
+- generated_from_trainer
+- en
+- dataset:HuggingFaceH4/ultrachat_200k
+- dataset:HuggingFaceH4/ultrafeedback_binarized
+- arxiv:2305.18290
+- arxiv:2310.16944
+- base_model:mistralai/Mistral-7B-v0.1
+- license:mit
+- model-index
+- autotrain_compatible
+- endpoints_compatible
+- has_space
+- text-generation-inference
+- region:us
+model_name: zephyr-7b-beta-GPTQ
+base_model: HuggingFaceH4/zephyr-7b-beta
+inference: false
+model_creator: HuggingFaceH4
+pipeline_tag: text-generation
+quantized_by: MaziyarPanahi
+---
+# Description
+[MaziyarPanahi/zephyr-7b-beta-GPTQ](https://huggingface.co/MaziyarPanahi/zephyr-7b-beta-GPTQ) is a quantized (GPTQ) version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta)
+
+## How to use
+### Install the necessary packages
+
+```
+pip install --upgrade accelerate auto-gptq transformers
+```
+
+### Example Python code
+
+
+```python
+from transformers import AutoTokenizer, pipeline
+from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
+import torch
+
+model_id = "MaziyarPanahi/zephyr-7b-beta-GPTQ"
+
+quantize_config = BaseQuantizeConfig(
+        bits=4,
+        group_size=128,
+        desc_act=False
+    )
+
+model = AutoGPTQForCausalLM.from_quantized(
+        model_id,
+        use_safetensors=True,
+        device="cuda:0",
+        quantize_config=quantize_config)
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    max_new_tokens=512,
+    temperature=0.7,
+    top_p=0.95,
+    repetition_penalty=1.1
+)
+
+outputs = pipe("What is a large language model?")
+print(outputs[0]["generated_text"])
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26455200e6a104af5afe82c93d20fabdc9de2ec294008f09c6c133821ad30439
+size 4158662208

quantize_config.json

@@ -0,0 +1,11 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "damp_percent": 0.1,
+  "desc_act": false,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": null
+}

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}