init

README.md

@@ -1,3 +1,175 @@
----
-license: mit
----
+---
+license: mit
+tags:
+- decompile
+- binary
+---
+
+### 1. Introduction of LLM4Decompile
+
+LLM4Decompile aims to decompile x86 assembly instructions into C. The newly released V2 series are trained with a larger dataset (2B tokens) and a maximum token length of 4,096, with remarkable performance (up to 100% improvement) compared to the previous model.
+
+- **Github Repository:** [LLM4Decompile](https://github.com/albertan017/LLM4Decompile)
+
+
+### 2. Evaluation Results
+
+| Metrics | Re-executability Rate | | | | | Edit Similarity | | | | |
+|:-----------------------:|:---------------------:|:-------:|:-------:|:-------:|:-------:|:---------------:|:-------:|:-------:|:-------:|:-------:|
+| Optimization Level | O0 | O1 | O2 | O3 | AVG | O0 | O1 | O2 | O3 | AVG |
+| LLM4Decompile-End-6.7B | 0.6805 | 0.3951 | 0.3671 | 0.3720 | 0.4537 | 0.1557 | 0.1292 | 0.1293 | 0.1269 | 0.1353 |
+| Ghidra | 0.3476 | 0.1646 | 0.1524 | 0.1402 | 0.2012 | 0.0699 | 0.0613 | 0.0619 | 0.0547 | 0.0620 |
+| +GPT-4o | 0.4695 | 0.3415 | 0.2866 | 0.3110 | 0.3522 | 0.0660 | 0.0563 | 0.0567 | 0.0499 | 0.0572 |
+| +LLM4Decompile-Ref-1.3B | 0.6890 | 0.3720 | 0.4085 | 0.3720 | 0.4604 | 0.1517 | 0.1325 | 0.1292 | 0.1267 | 0.1350 |
+| +LLM4Decompile-Ref-6.7B | 0.7439 | 0.4695 | 0.4756 | 0.4207 | 0.5274 | 0.1559 | 0.1353 | 0.1342 | 0.1273 | 0.1382 |
+| +LLM4Decompile-Ref-33B | 0.7073 | 0.4756 | 0.4390 | 0.4146 | 0.5091 | 0.1540 | 0.1379 | 0.1363 | 0.1307 | 0.1397 |
+
+### 3. How to Use
+Here is an example of how to use our model (Only for V2. For previous models, please check the corresponding model page at HF).
+
+1. Install Ghidra
+Download [Ghidra](https://github.com/NationalSecurityAgency/ghidra/releases/download/Ghidra_11.0.3_build/ghidra_11.0.3_PUBLIC_20240410.zip) to the current folder. You can also check the [page](https://github.com/NationalSecurityAgency/ghidra/releases) for other versions. Unzip the package to the current folder.
+In bash, you can use the following:
+```bash
+cd LLM4Decompile/ghidra
+wget https://github.com/NationalSecurityAgency/ghidra/releases/download/Ghidra_11.0.3_build/ghidra_11.0.3_PUBLIC_20240410.zip
+unzip ghidra_11.0.3_PUBLIC_20240410.zip
+```
+2. Install Java-SDK-17
+Ghidra 11 is dependent on Java-SDK-17, a simple way to install the SDK on Ubuntu:
+```bash
+apt-get update
+apt-get upgrade
+apt install openjdk-17-jdk openjdk-17-jre
+```
+Please check [Ghidra install guide](https://htmlpreview.github.io/?https://github.com/NationalSecurityAgency/ghidra/blob/Ghidra_11.1.1_build/GhidraDocs/InstallationGuide.html) for other platforms. 
+
+3. Use Ghidra Headless to decompile binary (demo.py)
+
+Note: **Replace** func0 with the function name you want to decompile.
+
+**Preprocessing:** Compile the C code into binary, and disassemble the binary into assembly instructions.
+```python
+import os
+import subprocess
+from tqdm import tqdm,trange
+
+OPT = ["O0", "O1", "O2", "O3"]
+timeout_duration = 10
+
+ghidra_path = "./ghidra_11.0.3_PUBLIC/support/analyzeHeadless"#path to the headless analyzer, change the path accordingly
+postscript = "./decompile.py"#path to the decompiler helper function, change the path accordingly
+project_path = "."#path to temp folder for analysis, change the path accordingly
+project_name = "tmp_ghidra_proj"
+func_path = "../samples/sample.c"#path to c code for compiling and decompiling, change the path accordingly
+fileName = "sample"
+
+with tempfile.TemporaryDirectory() as temp_dir:
+ pid = os.getpid()
+ asm_all = {}
+ for opt in [OPT[0]]:
+ executable_path = os.path.join(temp_dir, f"{pid}_{opt}.o")
+ cmd = f'gcc -{opt} -o {executable_path} {func_path} -lm'
+ subprocess.run(
+ cmd.split(' '),
+ check=True,
+ stdout=subprocess.DEVNULL, # Suppress stdout
+ stderr=subprocess.DEVNULL, # Suppress stderr
+ timeout=timeout_duration,
+ )
+
+ output_path = os.path.join(temp_dir, f"{pid}_{opt}.c")
+ command = [
+ ghidra_path,
+ temp_dir,
+ project_name,
+ "-import", executable_path,
+ "-postScript", postscript, output_path,
+ "-deleteProject", # WARNING: This will delete the project after analysis
+ ]
+ result = subprocess.run(command, text=True, capture_output=True, check=True)
+ with open(output_path,'r') as f:
+ c_decompile = f.read()
+ c_func = []
+ flag = 0
+ for line in c_decompile.split('\n'):
+ if "Function: func0" in line:#**Replace** func0 with the function name you want to decompile.
+ flag = 1
+ c_func.append(line)
+ continue
+ if flag:
+ if '// Function:' in line:
+ if len(c_func) > 1:
+ break
+ c_func.append(line)
+ if flag == 0:
+ raise ValueError('bad case no function found')
+ for idx_tmp in range(1,len(c_func)):##########remove the comments
+ if 'func0' in c_func[idx_tmp]:
+ break
+ c_func = c_func[idx_tmp:]
+ input_asm = '\n'.join(c_func).strip()
+
+ before = f"# This is the assembly code:\n"#prompt
+ after = "\n# What is the source code?\n"#prompt
+ input_asm_prompt = before+input_asm.strip()+after
+ with open(fileName +'_' + opt +'.pseudo','w',encoding='utf-8') as f:
+ f.write(input_asm_prompt)
+```
+
+Ghidra pseudo-code may look like this:
+```c
+undefined4 func0(float param_1,long param_2,int param_3)
+{
+ int local_28;
+ int local_24;
+ 
+ local_24 = 0;
+ do {
+ local_28 = local_24;
+ if (param_3 <= local_24) {
+ return 0;
+ }
+ while (local_28 = local_28 + 1, local_28 < param_3) {
+ if ((double)((ulong)(double)(*(float *)(param_2 + (long)local_24 * 4) -
+ *(float *)(param_2 + (long)local_28 * 4)) &
+ SUB168(_DAT_00402010,0)) < (double)param_1) {
+ return 1;
+ }
+ }
+ local_24 = local_24 + 1;
+ } while( true );
+}
+```
+4. Refine pseudo-code using LLM4Decompile (demo.py)
+
+**Decompilation:** Use LLM4Decompile-Ref to refine the Ghidra pseudo-code into C:
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model_path = 'LLM4Binary/llm4decompile-6.7b-v2' # V2 Model
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype=torch.bfloat16).cuda()
+
+with open(fileName +'_' + OPT[0] +'.pseudo','r') as f:#optimization level O0
+ asm_func = f.read()
+inputs = tokenizer(asm_func, return_tensors="pt").to(model.device)
+with torch.no_grad():
+ outputs = model.generate(**inputs, max_new_tokens=2048)### max length to 4096, max new tokens should be below the range
+c_func_decompile = tokenizer.decode(outputs[0][len(inputs[0]):-1])
+
+with open(fileName +'_' + OPT[0] +'.pseudo','r') as f:#original file
+ func = f.read()
+
+print(f'pseudo function:\n{func}')# Note we only decompile one function, where the original file may contain multiple functions
+print(f'refined function:\n{c_func_decompile}')
+
+```
+
+### 4. License
+This code repository is licensed under the MIT License.
+
+### 5. Contact
+
+If you have any questions, please raise an issue.

all_results.json

@@ -0,0 +1,8 @@
+{
+ "epoch": 0.9994671476001148,
+ "total_flos": 6671683451092992.0,
+ "train_loss": 0.22089350833667545,
+ "train_runtime": 224810.7302,
+ "train_samples_per_second": 6.945,
+ "train_steps_per_second": 0.003
+}

config.json

@@ -0,0 +1,30 @@
+{
+ "_name_or_path": "01-ai/Yi-Coder-9B",
+ "architectures": [
+ "LlamaForCausalLM"
+ ],
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "hidden_act": "silu",
+ "hidden_size": 4096,
+ "initializer_range": 0.02,
+ "intermediate_size": 11008,
+ "max_position_embeddings": 131072,
+ "mlp_bias": false,
+ "model_type": "llama",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 48,
+ "num_key_value_heads": 4,
+ "pad_token_id": 0,
+ "pretraining_tp": 1,
+ "rms_norm_eps": 1e-05,
+ "rope_scaling": null,
+ "rope_theta": 10000000,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.44.2",
+ "use_cache": false,
+ "vocab_size": 64000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "pad_token_id": 0,
+ "transformers_version": "4.44.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3475727ee2a9aa10327dde53d215001cac4e39a8a6b6a3c971d4f54eedf3d715
+size 4932711424

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66c75fe14424f2aa276d86efcc6c8fb1c222ae8315118a4fc1a5f7e10d849ac5
+size 4976802816

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:165fd0b57b30bb8db95d20edc1769a59c6ee59295e82d3b0d8f89d8945da28b0
+size 4968397360

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fba922ca6e558f0296304b51f5154ab42f2f241fe21065e08dd9270242c1c81b
+size 2780953384

model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+ "metadata": {
+ "total_size": 17658814464
+ },
+ "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.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.41.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.42.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.42.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.42.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.43.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.43.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.43.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.44.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.44.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.44.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.44.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.45.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.45.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.45.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.45.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.46.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.46.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.46.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.46.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.46.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.46.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.46.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.46.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.46.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.47.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.47.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.47.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.47.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.47.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.47.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.47.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.47.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.47.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.norm.weight": "model-00004-of-00004.safetensors"
+ }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+ "bos_token": {
+ "content": "<|startoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<unk>",
+ "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 sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+ "add_bos_token": false,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "<|startoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<|startoftext|>",
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content }}{% endif %}{% endfor %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|endoftext|>",
+ "legacy": true,
+ "model_max_length": 200000,
+ "pad_token": "<unk>",
+ "padding_side": "right",
+ "sp_model_kwargs": {},
+ "spaces_between_special_tokens": false,
+ "split_special_tokens": false,
+ "tokenizer_class": "LlamaTokenizer",
+ "unk_token": "<unk>",
+ "use_default_system_prompt": false
+}