CultriX/MistralTrix-v1
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: CultriX/MistralTrix-v1
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-29 23:28:59 +08:00
commit 7d7942f00d
14 changed files with 92510 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

751
MistralTrix.ipynb Normal file
View File

@@ -0,0 +1,751 @@
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"machine_shape": "hm",
"gpuType": "A100"
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
},
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"22773c721a7c4221a9c14cd388461d4c": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_6b54841f5de1482694c360095dae3039",
"IPY_MODEL_448ccbc85e624ec3b3e71931a7ee4ff6",
"IPY_MODEL_173769f6f465485f8848a11bf269850b"
],
"layout": "IPY_MODEL_60978b9b4e8348f0a71ce3e35c73bcff"
}
},
"6b54841f5de1482694c360095dae3039": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_6a38dcbaf4674b448329ac0a16587d2a",
"placeholder": "​",
"style": "IPY_MODEL_7eaeada2158e493189449af91f643553",
"value": "Loading checkpoint shards: 100%"
}
},
"448ccbc85e624ec3b3e71931a7ee4ff6": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_6e32854952b340008edca0139d3471d6",
"max": 3,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_db6d7cfcdade4b4baa213a5d0abc07d7",
"value": 3
}
},
"173769f6f465485f8848a11bf269850b": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_9083029642744c43b7705532cbe0cf79",
"placeholder": "​",
"style": "IPY_MODEL_d028a98caa13425b907ceb513119006e",
"value": " 3/3 [00:11<00:00, 2.89s/it]"
}
},
"60978b9b4e8348f0a71ce3e35c73bcff": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"6a38dcbaf4674b448329ac0a16587d2a": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"7eaeada2158e493189449af91f643553": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"6e32854952b340008edca0139d3471d6": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"db6d7cfcdade4b4baa213a5d0abc07d7": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"9083029642744c43b7705532cbe0cf79": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"d028a98caa13425b907ceb513119006e": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
}
}
},
"accelerator": "GPU"
},
"cells": [
{
"cell_type": "markdown",
"source": [
"# MistralTrix\n",
"\n",
"❤️ Created by [@maximelabonne](https://twitter.com/maximelabonne)."
],
"metadata": {
"id": "Pa8905-YsHAn"
}
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "_zIBL8IssExG"
},
"outputs": [],
"source": [
"!pip install -q datasets trl peft bitsandbytes sentencepiece wandb"
]
},
{
"cell_type": "code",
"source": [
"import os\n",
"import gc\n",
"import torch\n",
"\n",
"import transformers\n",
"from transformers import AutoModelForCausalLM, AutoTokenizer, TrainingArguments, BitsAndBytesConfig\n",
"from datasets import load_dataset\n",
"from peft import LoraConfig, PeftModel, get_peft_model, prepare_model_for_kbit_training\n",
"from trl import DPOTrainer\n",
"import bitsandbytes as bnb\n",
"from google.colab import userdata\n",
"import wandb\n",
"\n",
"# Defined in the secrets tab in Google Colab\n",
"hf_token = userdata.get('huggingface')\n",
"wb_token = userdata.get('wandb')\n",
"wandb.login(key=wb_token)\n",
"\n",
"model_name = \"zyh3826/GML-Mistral-merged-v1\"\n",
"new_model = \"MistralTrix-v1\""
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "YpdkZsMNylvp",
"outputId": "6c2df234-1ce7-4cd2-a7e3-567e7536319f"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.10/dist-packages/trl/trainer/ppo_config.py:141: UserWarning: The `optimize_cuda_cache` arguement will be deprecated soon, please use `optimize_device_cache` instead.\n",
" warnings.warn(\n",
"\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33mmlabonne\u001b[0m. Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\n",
"\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m If you're specifying your api key in code, ensure this code is not shared publicly.\n",
"\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Consider setting the WANDB_API_KEY environment variable, or running `wandb login` from the command line.\n",
"\u001b[34m\u001b[1mwandb\u001b[0m: Appending key for api.wandb.ai to your netrc file: /root/.netrc\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"## Format dataset"
],
"metadata": {
"id": "d8CvUgROUDw-"
}
},
{
"cell_type": "code",
"source": [
"def chatml_format(example):\n",
" # Format system\n",
" if len(example['system']) > 0:\n",
" message = {\"role\": \"system\", \"content\": example['system']}\n",
" system = tokenizer.apply_chat_template([message], tokenize=False)\n",
" else:\n",
" system = \"\"\n",
"\n",
" # Format instruction\n",
" message = {\"role\": \"user\", \"content\": example['question']}\n",
" prompt = tokenizer.apply_chat_template([message], tokenize=False, add_generation_prompt=True)\n",
"\n",
" # Format chosen answer\n",
" chosen = example['chosen'] + \"<|im_end|>\\n\"\n",
"\n",
" # Format rejected answer\n",
" rejected = example['rejected'] + \"<|im_end|>\\n\"\n",
"\n",
" return {\n",
" \"prompt\": system + prompt,\n",
" \"chosen\": chosen,\n",
" \"rejected\": rejected,\n",
" }\n",
"\n",
"# Load dataset\n",
"dataset = load_dataset(\"Intel/orca_dpo_pairs\")['train']\n",
"\n",
"# Save columns\n",
"original_columns = dataset.column_names\n",
"\n",
"# Tokenizer\n",
"tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
"tokenizer.pad_token = tokenizer.eos_token\n",
"tokenizer.padding_side = \"left\"\n",
"\n",
"# Format dataset\n",
"dataset = dataset.map(\n",
" chatml_format,\n",
" remove_columns=original_columns\n",
")\n",
"\n",
"# Print sample\n",
"dataset[1]"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "MCD77GZ60DOT",
"outputId": "c7c6773c-5545-4fee-bfa3-6fa6d69c0f3f"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n",
"Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"{'prompt': '<|im_start|>system\\nYou are an AI assistant. You will be given a task. You must generate a detailed and long answer.<|im_end|>\\n<|im_start|>user\\nGenerate an approximately fifteen-word sentence that describes all this data: Midsummer House eatType restaurant; Midsummer House food Chinese; Midsummer House priceRange moderate; Midsummer House customer rating 3 out of 5; Midsummer House near All Bar One<|im_end|>\\n<|im_start|>assistant\\n',\n",
" 'chosen': 'Midsummer House is a moderately priced Chinese restaurant with a 3/5 customer rating, located near All Bar One.<|im_end|>\\n',\n",
" 'rejected': ' Sure! Here\\'s a sentence that describes all the data you provided:\\n\\n\"Midsummer House is a moderately priced Chinese restaurant with a customer rating of 3 out of 5, located near All Bar One, offering a variety of delicious dishes.\"<|im_end|>\\n'}"
]
},
"metadata": {},
"execution_count": 3
}
]
},
{
"cell_type": "markdown",
"source": [
"## Train model with DPO"
],
"metadata": {
"id": "DeT5eUK_UJgK"
}
},
{
"cell_type": "code",
"source": [
"# LoRA configuration\n",
"peft_config = LoraConfig(\n",
" r=16,\n",
" lora_alpha=16,\n",
" lora_dropout=0.05,\n",
" bias=\"none\",\n",
" task_type=\"CAUSAL_LM\",\n",
" target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj']\n",
")\n",
"\n",
"# Model to fine-tune\n",
"model = AutoModelForCausalLM.from_pretrained(\n",
" model_name,\n",
" torch_dtype=torch.float16,\n",
" load_in_4bit=True\n",
")\n",
"model.config.use_cache = False\n",
"\n",
"# Reference model\n",
"ref_model = AutoModelForCausalLM.from_pretrained(\n",
" model_name,\n",
" torch_dtype=torch.float16,\n",
" load_in_4bit=True\n",
")\n",
"\n",
"# Training arguments\n",
"training_args = TrainingArguments(\n",
" per_device_train_batch_size=4,\n",
" gradient_accumulation_steps=4,\n",
" gradient_checkpointing=True,\n",
" learning_rate=5e-5,\n",
" lr_scheduler_type=\"cosine\",\n",
" max_steps=200,\n",
" save_strategy=\"no\",\n",
" logging_steps=1,\n",
" output_dir=new_model,\n",
" optim=\"paged_adamw_32bit\",\n",
" warmup_steps=100,\n",
" bf16=True,\n",
" report_to=\"wandb\",\n",
")\n",
"\n",
"# Create DPO trainer\n",
"dpo_trainer = DPOTrainer(\n",
" model,\n",
" ref_model,\n",
" args=training_args,\n",
" train_dataset=dataset,\n",
" tokenizer=tokenizer,\n",
" peft_config=peft_config,\n",
" beta=0.1,\n",
" max_prompt_length=1024,\n",
" max_length=1536,\n",
")\n",
"\n",
"# Fine-tune model with DPO\n",
"dpo_trainer.train()"
],
"metadata": {
"id": "rKPILNOLR-aK"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"## Upload model"
],
"metadata": {
"id": "3LdhPpcrUM3H"
}
},
{
"cell_type": "code",
"source": [
"# Save artifacts\n",
"dpo_trainer.model.save_pretrained(\"final_checkpoint\")\n",
"tokenizer.save_pretrained(\"final_checkpoint\")\n",
"\n",
"# Flush memory\n",
"del dpo_trainer, model, ref_model\n",
"gc.collect()\n",
"torch.cuda.empty_cache()\n",
"\n",
"# Reload model in FP16 (instead of NF4)\n",
"base_model = AutoModelForCausalLM.from_pretrained(\n",
" model_name,\n",
" return_dict=True,\n",
" torch_dtype=torch.float16,\n",
")\n",
"tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
"\n",
"# Merge base model with the adapter\n",
"model = PeftModel.from_pretrained(base_model, \"final_checkpoint\")\n",
"model = model.merge_and_unload()\n",
"\n",
"# Save model and tokenizer\n",
"model.save_pretrained(new_model)\n",
"tokenizer.save_pretrained(new_model)\n",
"\n",
"# Push them to the HF Hub\n",
"model.push_to_hub(new_model, use_temp_dir=False, token=hf_token)\n",
"tokenizer.push_to_hub(new_model, use_temp_dir=False, token=hf_token)"
],
"metadata": {
"id": "h7cIvxcTfBC4"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"## Inference"
],
"metadata": {
"id": "G6EFsmS4UOgV"
}
},
{
"cell_type": "code",
"source": [
"# Format prompt\n",
"message = [\n",
" {\"role\": \"system\", \"content\": \"You are a helpful assistant chatbot.\"},\n",
" {\"role\": \"user\", \"content\": \"What is a Large Language Model?\"}\n",
"]\n",
"tokenizer = AutoTokenizer.from_pretrained(new_model)\n",
"prompt = tokenizer.apply_chat_template(message, add_generation_prompt=True, tokenize=False)\n",
"\n",
"# Create pipeline\n",
"pipeline = transformers.pipeline(\n",
" \"text-generation\",\n",
" model=new_model,\n",
" tokenizer=tokenizer\n",
")\n",
"\n",
"# Generate text\n",
"sequences = pipeline(\n",
" prompt,\n",
" do_sample=True,\n",
" temperature=0.7,\n",
" top_p=0.9,\n",
" num_return_sequences=1,\n",
" max_length=200,\n",
")\n",
"print(sequences[0]['generated_text'])"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 251,
"referenced_widgets": [
"22773c721a7c4221a9c14cd388461d4c",
"6b54841f5de1482694c360095dae3039",
"448ccbc85e624ec3b3e71931a7ee4ff6",
"173769f6f465485f8848a11bf269850b",
"60978b9b4e8348f0a71ce3e35c73bcff",
"6a38dcbaf4674b448329ac0a16587d2a",
"7eaeada2158e493189449af91f643553",
"6e32854952b340008edca0139d3471d6",
"db6d7cfcdade4b4baa213a5d0abc07d7",
"9083029642744c43b7705532cbe0cf79",
"d028a98caa13425b907ceb513119006e"
]
},
"id": "LAEUZFjvlJOv",
"outputId": "9b5720c7-49ef-45c7-e5a7-f38d64899b1e"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s]"
],
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "22773c721a7c4221a9c14cd388461d4c"
}
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.10/dist-packages/transformers/generation/utils.py:1473: UserWarning: You have modified the pretrained model configuration to control generation. This is a deprecated strategy to control generation and will be removed soon, in a future version. Please use and modify the model generation configuration (see https://huggingface.co/docs/transformers/generation_strategies#default-text-generation-configuration )\n",
" warnings.warn(\n",
"Setting `pad_token_id` to `eos_token_id`:32000 for open-end generation.\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"<|im_start|>system\n",
"You are a helpful assistant chatbot.<|im_end|>\n",
"<|im_start|>user\n",
"What is a Large Language Model?<|im_end|>\n",
"<|im_start|>assistant\n",
"A large language model is a type of artificial intelligence (AI) system that has been trained on vast amounts of text data. These models are designed to understand and generate human language, allowing them to perform various natural language processing tasks, such as text generation, language translation, and question answering. Large language models typically use deep learning techniques, like recurrent neural networks (RNNs) or transformers, to learn patterns and relationships in the data, enabling them to generate coherent and contextually relevant responses. The size of these models, in terms of the number of parameters and the volume of data they are trained on, plays a significant role in their ability to comprehend and produce complex language structures.\n"
]
}
]
}
]
}

111
README.md Normal file
View File

@@ -0,0 +1,111 @@
---
license: apache-2.0
language:
- en
pipeline_tag: text-generation
dtype: bfloat16
tags:
- merge
---
# EDIT:
Always check my space for the latest benchmark results for my models!
* https://huggingface.co/spaces/CultriX/Yet_Another_LLM_Leaderboard
# Results:
T: 🟦
Model: CultriX/MistralTrix-v1 📑
Average: 73.39
ARC: 72.27
HellaSwag: 88.33
MMLU: 65.24
TruthfulQA: 70.73
Winogrande: 80.98
GSM8K: 62.77
# Edit/Disclaimer:
Currently the #1 ranked 7B LLM on the LLM Leaderboards, woah!
I did not expect that result at all and am in no way a professional when it comes to LLM's or computer science in general,
just a guy that likes to nerd about and tinker around.
For those wondering how I achieved this, the answer is that I simply attempted to apply the techniques outlined in this amazing article myself: https://towardsdatascience.com/fine-tune-a-mistral-7b-model-with-direct-preference-optimization-708042745aac
Therefore, all credit basically goes to the guy who wrote that.
He offers the exact Colab notebook I used to train this model for free, as well as a really nice GitHub page I hope he doesn't mind me sharing: https://github.com/mlabonne/llm-course/
So huge thank you to him for sharing his knowledge and learning me a thing or two in the process!
# GGUF
I attempted to quantisize the model myself, which again I pretty much have no clue about, but it seems to run fine for me when I test them:
https://huggingface.co/CultriX/MistralTrix-v1-GGUF
I'll say it one more time though:
"I am a complete beginner to all of this, so if these do end up sucking don't be surprised."
You have been warned :)
# Description:
(trained on a single Colab GPU in less than a few hours)
MistralTrix-v1 is an zyh3826/GML-Mistral-merged-v1 model that has been further fine-tuned with Direct Preference Optimization (DPO) using Intel's dataset for neural-chat-7b-v3-1.
It surpasses the original model on several benchmarks (see results).
It is directly inspired by the RLHF process described by Intel/neural-chat-7b-v3-1's authors to improve performance.
I used the same dataset and reformatted it to apply the ChatML template.
The code to train this model is available on Google Colab and GitHub.
Fine-tuning took about an hour on Google Colab A-1000 GPU with 40GB VRAM.
# TRAINING SPECIFICATIONS
> LoRA configuration
peft_config = LoraConfig(
r=16,
lora_alpha=16,
lora_dropout=0.05,
bias="none",
task_type="CAUSAL_LM",
target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj']
)
> Model to fine-tune
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.float16,
load_in_4bit=True
)
model.config.use_cache = False
> Reference model
ref_model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.float16,
load_in_4bit=True
)
> Training arguments
training_args = TrainingArguments(
per_device_train_batch_size=4,
gradient_accumulation_steps=4,
gradient_checkpointing=True,
learning_rate=5e-5,
lr_scheduler_type="cosine",
max_steps=200,
save_strategy="no",
logging_steps=1,
output_dir=new_model,
optim="paged_adamw_32bit",
warmup_steps=100,
bf16=True,
report_to="wandb",
)
> Create DPO trainer
dpo_trainer = DPOTrainer(
model,
ref_model,
args=training_args,
train_dataset=dataset,
tokenizer=tokenizer,
peft_config=peft_config,
beta=0.1,
max_prompt_length=1024,
max_length=1536,
)

26
config.json Normal file
View File

@@ -0,0 +1,26 @@
{
"_name_or_path": "zyh3826/GML-Mistral-merged-v1",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 40,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.35.2",
"use_cache": true,
"vocab_size": 32000
}

6
generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"transformers_version": "4.35.2"
}

3
model-00001-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bbeee2819e4689ba08b2e3003e2fb4fc8641f1cbfaf29b2417f1ff272a5a89e7
size 4943162240

3
model-00002-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:91f4a6f841456249d24331d001d5d949cf7fbd95d38fb7f12128d507a17d2f17
size 4999819232

3
model-00003-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fc953409846ac5f4f5055d6e5a1d6c6a45c9ea905bcda9499b625a317bf3c6a1
size 4915916080

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8f036303d4abd2ed53858c59ed47ca1385420b3b8cd7728b8da4cbac927435e8
size 3114400496

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

@@ -0,0 +1,370 @@
{
"metadata": {
"total_size": 17973256192
},
"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-00002-of-00004.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00002-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-00002-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-00002-of-00004.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00002-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-00002-of-00004.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00002-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-00003-of-00004.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00003-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-00003-of-00004.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00003-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-00003-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-00003-of-00004.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00003-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-00004-of-00004.safetensors",
"model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.33.post_attention_layernorm.weight": "model-00004-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-00004-of-00004.safetensors",
"model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.36.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.36.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.36.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.36.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.36.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.36.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.36.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.37.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.37.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.37.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.37.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.37.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.37.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.38.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.38.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.38.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.39.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.39.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.39.self_attn.v_proj.weight": "model-00004-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.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"
}
}

28
special_tokens_map.json Normal file
View File

@@ -0,0 +1,28 @@
{
"additional_special_tokens": [
"<unk>",
"<s>",
"</s>"
],
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

91122
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
tokenizer.model (Stored with Git LFS) Normal file
View File

Binary file not shown.

46
tokenizer_config.json Normal file
View File

@@ -0,0 +1,46 @@
{
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<unk>",
"<s>",
"</s>"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": null,
"padding_side": "left",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"split_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": true
}