pankajmathur/orca_mini_phi-4
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: pankajmathur/orca_mini_phi-4
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-21 20:36:51 +08:00
commit 3de0f4329a
25 changed files with 609167 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View File

@@ -0,0 +1,35 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz 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

5899
Orca_Mini_Chat_4bit_Phi_4.ipynb Normal file
View File

File diff suppressed because it is too large Load Diff

203
Orca_Mini_Chat_8bit_Phi_4.ipynb Normal file
View File

@@ -0,0 +1,203 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "TFu_ibC1eYrz"
},
"outputs": [],
"source": [
"!pip install torch transformers bitsandbytes -q"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "Zs7QNs0Tet6r"
},
"outputs": [],
"source": [
"import torch\n",
"from transformers import pipeline, BitsAndBytesConfig\n",
"from IPython.display import clear_output\n",
"from google.colab import output"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "lOhAjLdI2oFt"
},
"outputs": [],
"source": [
"quantization_config = BitsAndBytesConfig(\n",
" load_in_8bit=True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "v4uIN6uIeyl3"
},
"outputs": [],
"source": [
"class ChatBot:\n",
" _instance = None\n",
" _current_model = None\n",
"\n",
" def __init__(self, model_slug=None):\n",
" if model_slug and model_slug != ChatBot._current_model:\n",
" self.load_model(model_slug)\n",
" ChatBot._current_model = model_slug\n",
"\n",
" self.messages = []\n",
" self.max_tokens = 2048\n",
" self.temperature = 0.5\n",
" self.top_k = 100\n",
" self.top_p = 0.95\n",
"\n",
" @classmethod\n",
" def get_instance(cls, model_slug=None):\n",
" if not cls._instance or (model_slug and model_slug != cls._current_model):\n",
" cls._instance = cls(model_slug)\n",
" return cls._instance\n",
"\n",
" def load_model(self, model_slug):\n",
" print(f\"Loading model {model_slug}...\")\n",
" self.pipeline = pipeline(\n",
" \"text-generation\",\n",
" model=model_slug,\n",
" model_kwargs={\"quantization_config\": quantization_config},\n",
" device_map=\"auto\",\n",
" )\n",
" clear_output()\n",
" print(\"Model loaded successfully!\")\n",
"\n",
" def reset_conversation(self, system_message):\n",
" \"\"\"Reset the conversation with a new system message\"\"\"\n",
" self.messages = [{\"role\": \"system\", \"content\": system_message}]\n",
"\n",
" def get_response(self, user_input):\n",
" \"\"\"Get response with current parameters\"\"\"\n",
" self.messages.append({\"role\": \"user\", \"content\": user_input})\n",
" outputs = self.pipeline(\n",
" self.messages,\n",
" max_new_tokens=self.max_tokens,\n",
" do_sample=True,\n",
" temperature=self.temperature,\n",
" top_k=self.top_k,\n",
" top_p=self.top_p\n",
" )\n",
" response = outputs[0][\"generated_text\"][-1]\n",
" content = response.get('content', 'No content available')\n",
" self.messages.append({\"role\": \"assistant\", \"content\": content})\n",
" return content\n",
"\n",
" def update_params(self, max_tokens=None, temperature=None, top_k=None, top_p=None):\n",
" \"\"\"Update generation parameters\"\"\"\n",
" if max_tokens is not None:\n",
" self.max_tokens = max_tokens\n",
" if temperature is not None:\n",
" self.temperature = temperature\n",
" if top_k is not None:\n",
" self.top_k = top_k\n",
" if top_p is not None:\n",
" self.top_p = top_p"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "H2n_6Xcue3Vn"
},
"outputs": [],
"source": [
"def run_chatbot(\n",
" model=None,\n",
" system_message=\"You are Orca Mini, You are expert in following given instructions, Think step by step before coming up with final answer\",\n",
" max_tokens=None,\n",
" temperature=None,\n",
" top_k=None,\n",
" top_p=None,\n",
"):\n",
" try:\n",
" # Get or create chatbot instance\n",
" chatbot = ChatBot.get_instance(model)\n",
"\n",
" # Update parameters if provided\n",
" chatbot.update_params(max_tokens, temperature, top_k, top_p)\n",
"\n",
" # Reset conversation with new system message\n",
" chatbot.reset_conversation(system_message)\n",
"\n",
" print(\"Chatbot: Hi! Type 'quit' to exit.\")\n",
"\n",
" while True:\n",
" user_input = input(\"You: \").strip()\n",
" if user_input.lower() == 'quit':\n",
" break\n",
" try:\n",
" response = chatbot.get_response(user_input)\n",
" print(\"Chatbot:\", response)\n",
" except Exception as e:\n",
" print(f\"Chatbot: An error occurred: {str(e)}\")\n",
" print(\"Please try again.\")\n",
"\n",
" except Exception as e:\n",
" print(f\"Error in chatbot: {str(e)}\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "JEqgoAH2fC6h"
},
"outputs": [],
"source": [
"run_chatbot(model=\"pankajmathur/orca_mini_phi-4\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "tGW8wsfAfHDf"
},
"outputs": [],
"source": [
"# # change system message\n",
"# run_chatbot(\n",
"# system_message=\"You are Orca Mini, You are expert in logic, Think step by step before coming up with final answer\",\n",
"# max_tokens=1024,\n",
"# temperature=0.3\n",
"# )"
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"gpuType": "T4",
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
}

119
README.md Normal file
View File

@@ -0,0 +1,119 @@
---
license: mit
datasets:
- pankajmathur/orca_mini_v1_dataset
- pankajmathur/orca_mini_v8_sharegpt_format
language:
- en
base_model:
- microsoft/phi-4
library_name: transformers
---
# Model Name: orca_mini_phi-4
**orca_mini_phi-4 is trained with various SFT Datasets on [microsoft/phi-4](https://huggingface.co/microsoft/phi-4) using Llama's architecture.**
<img src="https://huggingface.co/pankajmathur/orca_mini_v5_8b/resolve/main/orca_minis_small.jpeg" width="auto" />
<strong>
"Obsessed with Open Source GenAI's potential? So am I ! Let's Contribute together 🚀 <a href="https://www.linkedin.com/in/pankajam" target="_blank">https://www.linkedin.com/in/pankajam</a>"
</strong>
<br>
### NOTICE
By providing proper credit and attribution, you are granted permission to use this model as a foundational base for further Full fine tuning, DPO, PPO or ORPO tuning and any kind of Merges.
I actively encourage users to customize and enhance the model according to their specific needs, as this version is designed to be a comprehensive general model.
Dive in and innovate!
### Example Usage
**Use this model for Free on Google Colab with T4 GPU :)**
<a target="_blank" href="https://colab.research.google.com/#fileId=https://huggingface.co/pankajmathur/orca_mini_phi-4/blob/main/Orca_Mini_Chat_4bit_Phi_4.ipynb">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a>
### Example Usage on Your Personal Computer
Download GGUF version here and Follow Ollama instructions:
[https://huggingface.co/pankajmathur/orca_mini_phi-4-GGUF](https://huggingface.co/pankajmathur/orca_mini_phi-4-GGUF)
Below shows a code example on how to use this model in default half precision (bfloat16) format
```python
import torch
from transformers import pipeline
model_slug = "pankajmathur/orca_mini_phi-4"
pipeline = pipeline(
"text-generation",
model=model_slug,
device_map="auto",
)
messages = [
{"role": "system", "content": "You are Orca Mini, a helpful AI assistant."},
{"role": "user", "content": "Hello Orca Mini, what can you do for me?"}
]
outputs = pipeline(messages, max_new_tokens=128, do_sample=True, temperature=0.01, top_k=100, top_p=0.95)
print(outputs[0]["generated_text"][-1])
```
Below shows a code example on how to use this model in 4-bit format via bitsandbytes library
```python
import torch
from transformers import BitsAndBytesConfig, pipeline
model_slug = "pankajmathur/orca_mini_phi-4"
quantization_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype="float16",
bnb_4bit_use_double_quant=True,
)
pipeline = pipeline(
"text-generation",
model=model_slug,
model_kwargs={"quantization_config": quantization_config},
device_map="auto",
)
messages = [
{"role": "system", "content": "You are Orca Mini, a helpful AI assistant."},
{"role": "user", "content": "Hello Orca Mini, what can you do for me?"}
]
outputs = pipeline(messages, max_new_tokens=128, do_sample=True, temperature=0.01, top_k=100, top_p=0.95)
print(outputs[0]["generated_text"][-1])
```
Below shows a code example on how to use this model in 8-bit format via bitsandbytes library
```python
import torch
from transformers import BitsAndBytesConfig, pipeline
model_slug = "pankajmathur/orca_mini_phi-4"
quantization_config = BitsAndBytesConfig(
load_in_8bit=True
)
pipeline = pipeline(
"text-generation",
model=model_slug,
model_kwargs={"quantization_config": quantization_config},
device_map="auto",
)
messages = [
{"role": "system", "content": "You are Orca Mini, a helpful AI assistant."},
{"role": "user", "content": "Hello Orca Mini, what can you do for me?"}
]
outputs = pipeline(messages, max_new_tokens=128, do_sample=True, temperature=0.01, top_k=100, top_p=0.95)
print(outputs[0]["generated_text"][-1])
```
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)

31
config.json Normal file
View File

@@ -0,0 +1,31 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 100257,
"eos_token_id": 100265,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 17920,
"max_position_embeddings": 16384,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 10,
"original_max_position_embeddings": 16384,
"pad_token_id": 100351,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 250000,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.47.1",
"use_cache": false,
"vocab_size": 100352
}

8
generation_config.json Normal file
View File

@@ -0,0 +1,8 @@
{
"_from_model_config": true,
"bos_token_id": 100257,
"do_sample": true,
"eos_token_id": 100265,
"pad_token_id": 100351,
"transformers_version": "4.47.1"
}

100001
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model-00001-of-00006.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2c599023f83da6f5db90fe9687eb82c8df62be3cc1e27b9b0a19e6cfbd122c68
size 4933658528

3
model-00002-of-00006.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:87f31bb31962afc991936a9d0d47ae7d4771bbb609e0573d518279a3203b7c64
size 4954693112

3
model-00003-of-00006.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:619fd659d7cde5de9dbfa514a5e470e68c622acdb35b5991c96f424f9fa685bd
size 4902243992

3
model-00004-of-00006.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6f0c31c15d63c9b291bcec22cdbeba9515f05f8879e66bd5270d1d9c0815829f
size 4954672440

3
model-00005-of-00006.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:064f3a6e96f6fb2a6f1128377f2639c89be8b7a7b5458f2ceba4d19c5aa3ec5c
size 4954672432

3
model-00006-of-00006.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e722b00068c02cd2968baf9c36f9c29d188a7f10254b9b3b40a72b67a1a4d23d
size 4619116224

370
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,370 @@
{
"metadata": {
"total_size": 29319014400
},
"weight_map": {
"lm_head.weight": "model-00006-of-00006.safetensors",
"model.embed_tokens.weight": "model-00001-of-00006.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.34.input_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.34.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.34.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.35.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.35.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.35.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.35.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.35.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.35.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.35.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.36.input_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.36.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.36.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.36.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.36.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.36.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.36.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.36.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.36.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.37.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.37.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.37.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.37.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.37.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
"model.norm.weight": "model-00006-of-00006.safetensors"
}
}

3
pytorch_model-00001-of-00006.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b33fc11afc8d0a9759ff383ecc479b1bf37b6a6316e0a01a5b372ca672bb469b
size 4933671150

3
pytorch_model-00002-of-00006.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dbe76c7462dce8d8964fcf8d988b47ede58e6627d630d681ea60a93395fb944c
size 4954709034

3
pytorch_model-00003-of-00006.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:62f6ff5330f45f397fdcd8522fb285cc96fa39c67610bbfe581be0a3ca0ae2ab
size 4902260228

3
pytorch_model-00004-of-00006.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8e8bf54d34903f8024ba8824e9ff2cd006a40e7880535eec73d63170b5ef9ac1
size 4954687950

3
pytorch_model-00005-of-00006.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:905876bebeafc53f2dcac2667d97eaaa1b00ba53aaf87a231f85b49a373b0a72
size 4954687866

3
pytorch_model-00006-of-00006.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:10aaf7e42d7b4a8d17c546722741027d68e5bbe0ab773cacb92d5a78f031c6e1
size 4619128282

370
pytorch_model.bin.index.json Normal file
View File

@@ -0,0 +1,370 @@
{
"metadata": {
"total_size": 29319014400
},
"weight_map": {
"lm_head.weight": "pytorch_model-00006-of-00006.bin",
"model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.29.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.36.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.37.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.norm.weight": "pytorch_model-00006-of-00006.bin"
}
}

30
special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<|endoftext|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false
},
"eos_token": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|dummy_87|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "�",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

501273
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

791
tokenizer_config.json Normal file
View File

@@ -0,0 +1,791 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"5809": {
"content": "�",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100256": {
"content": "<|dummy_0|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100257": {
"content": "<|endoftext|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100258": {
"content": "<|fim_prefix|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100259": {
"content": "<|fim_middle|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100260": {
"content": "<|fim_suffix|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100261": {
"content": "<|dummy_1|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100262": {
"content": "<|dummy_2|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100263": {
"content": "<|dummy_3|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100264": {
"content": "<|im_start|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100265": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100266": {
"content": "<|im_sep|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100267": {
"content": "<|dummy_4|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100268": {
"content": "<|dummy_5|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100269": {
"content": "<|dummy_6|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100270": {
"content": "<|dummy_7|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100271": {
"content": "<|dummy_8|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100272": {
"content": "<|dummy_9|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100273": {
"content": "<|dummy_10|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100274": {
"content": "<|dummy_11|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100275": {
"content": "<|dummy_12|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100276": {
"content": "<|endofprompt|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100277": {
"content": "<|dummy_13|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100278": {
"content": "<|dummy_14|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100279": {
"content": "<|dummy_15|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100280": {
"content": "<|dummy_16|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100281": {
"content": "<|dummy_17|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100282": {
"content": "<|dummy_18|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100283": {
"content": "<|dummy_19|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100284": {
"content": "<|dummy_20|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100285": {
"content": "<|dummy_21|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100286": {
"content": "<|dummy_22|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100287": {
"content": "<|dummy_23|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100288": {
"content": "<|dummy_24|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100289": {
"content": "<|dummy_25|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100290": {
"content": "<|dummy_26|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100291": {
"content": "<|dummy_27|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100292": {
"content": "<|dummy_28|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100293": {
"content": "<|dummy_29|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100294": {
"content": "<|dummy_30|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100295": {
"content": "<|dummy_31|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100296": {
"content": "<|dummy_32|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100297": {
"content": "<|dummy_33|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100298": {
"content": "<|dummy_34|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100299": {
"content": "<|dummy_35|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100300": {
"content": "<|dummy_36|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100301": {
"content": "<|dummy_37|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100302": {
"content": "<|dummy_38|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100303": {
"content": "<|dummy_39|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100304": {
"content": "<|dummy_40|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100305": {
"content": "<|dummy_41|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100306": {
"content": "<|dummy_42|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100307": {
"content": "<|dummy_43|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100308": {
"content": "<|dummy_44|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100309": {
"content": "<|dummy_45|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100310": {
"content": "<|dummy_46|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100311": {
"content": "<|dummy_47|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100312": {
"content": "<|dummy_48|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100313": {
"content": "<|dummy_49|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100314": {
"content": "<|dummy_50|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100315": {
"content": "<|dummy_51|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100316": {
"content": "<|dummy_52|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100317": {
"content": "<|dummy_53|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100318": {
"content": "<|dummy_54|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100319": {
"content": "<|dummy_55|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100320": {
"content": "<|dummy_56|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100321": {
"content": "<|dummy_57|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100322": {
"content": "<|dummy_58|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100323": {
"content": "<|dummy_59|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100324": {
"content": "<|dummy_60|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100325": {
"content": "<|dummy_61|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100326": {
"content": "<|dummy_62|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100327": {
"content": "<|dummy_63|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100328": {
"content": "<|dummy_64|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100329": {
"content": "<|dummy_65|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100330": {
"content": "<|dummy_66|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100331": {
"content": "<|dummy_67|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100332": {
"content": "<|dummy_68|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100333": {
"content": "<|dummy_69|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100334": {
"content": "<|dummy_70|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100335": {
"content": "<|dummy_71|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100336": {
"content": "<|dummy_72|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100337": {
"content": "<|dummy_73|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100338": {
"content": "<|dummy_74|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100339": {
"content": "<|dummy_75|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100340": {
"content": "<|dummy_76|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100341": {
"content": "<|dummy_77|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100342": {
"content": "<|dummy_78|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100343": {
"content": "<|dummy_79|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100344": {
"content": "<|dummy_80|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100345": {
"content": "<|dummy_81|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100346": {
"content": "<|dummy_82|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100347": {
"content": "<|dummy_83|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100348": {
"content": "<|dummy_84|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100349": {
"content": "<|dummy_85|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100350": {
"content": "<|dummy_86|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100351": {
"content": "<|dummy_87|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"extra_special_tokens": {},
"model_max_length": 16384,
"pad_token": "<|dummy_87|>",
"padding_side": "left",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "�"
}

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long