初始化项目，由ModelHub XC社区提供模型
Model: adityakum667388/lumichats-v1.1 Source: Original Platform
This commit is contained in:
ModelHub XC
40
.gitattributes
vendored
Normal file
40
.gitattributes
vendored
Normal file
@@ -0,0 +1,40 @@
|
||||
*.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
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lumichats-v1.1-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lumichats-v1.1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lumichats-v1.1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lumichats-v1.1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
83
LICENSE.txt
Normal file
83
LICENSE.txt
Normal file
@@ -0,0 +1,83 @@
|
||||
LLAMA 3.2 COMMUNITY LICENSE AGREEMENT
|
||||
|
||||
Llama 3.2 Version Release Date: September 25, 2024
|
||||
|
||||
“Agreement” means the terms and conditions for use, reproduction, distribution
|
||||
and modification of the Llama Materials set forth herein.
|
||||
|
||||
“Documentation” means the specifications, manuals and documentation accompanying
|
||||
Llama 3.2 distributed by Meta at https://llama.meta.com/doc/overview.
|
||||
|
||||
“Licensee” or “you” means you, or your employer or any other person or entity
|
||||
(if you are entering into this Agreement on such person or entity’s behalf),
|
||||
of the age required under applicable laws, rules or regulations to provide
|
||||
legal consent and that has legal authority to bind your employer or such other
|
||||
person or entity if you are entering into this Agreement on their behalf.
|
||||
|
||||
“Llama 3.2” means the foundational large language models and software and
|
||||
algorithms, including machine-learning model code, trained model weights,
|
||||
inference-enabling code, training-enabling code, fine-tuning enabling code and
|
||||
other elements of the foregoing distributed by Meta at
|
||||
https://www.llama.com/llama-downloads.
|
||||
|
||||
“Llama Materials” means, collectively, Meta’s proprietary Llama 3.2 and
|
||||
Documentation (and any portion thereof) made available under this Agreement.
|
||||
|
||||
“Meta” or “we” means Meta Platforms Ireland Limited (if you are located in or,
|
||||
if you are an entity, your principal place of business is in the EEA or
|
||||
Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or
|
||||
Switzerland).
|
||||
|
||||
By using, reproducing, modifying, distributing, or making available any
|
||||
portion or element of the Llama Materials, you agree to be bound by this
|
||||
Agreement.
|
||||
|
||||
1. License Rights and Redistribution.
|
||||
|
||||
a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable
|
||||
and royalty-free limited license under Meta’s intellectual property or other
|
||||
rights owned by Meta embodied in the Llama Materials to use, reproduce,
|
||||
distribute, copy, create derivative works of, and make modifications to the
|
||||
Llama Materials.
|
||||
|
||||
b. Redistribution and Use.
|
||||
|
||||
i. If you distribute or make available the Llama Materials (or any derivative
|
||||
works thereof), or a product or service (including another AI model) that
|
||||
contains any of them, you shall (A) provide a copy of this Agreement with any
|
||||
such Llama Materials; and (B) prominently display “Built with Llama” on a related
|
||||
website, user interface, blogpost, about page, or product documentation. If you
|
||||
use the Llama Materials or any outputs or results of the Llama Materials to
|
||||
create, train, fine tune, or otherwise improve an AI model, which is distributed
|
||||
or made available, you shall also include “Llama” at the beginning of any such
|
||||
AI model name.
|
||||
|
||||
ii. You must retain the following attribution notice within a “Notice” text file
|
||||
distributed as part of such copies:
|
||||
“Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta
|
||||
Platforms, Inc. All Rights Reserved.”
|
||||
|
||||
iii. Your use of the Llama Materials must comply with applicable laws and
|
||||
regulations and adhere to the Acceptable Use Policy for the Llama Materials
|
||||
available at https://www.llama.com/llama3_2/use-policy.
|
||||
|
||||
2. Additional Commercial Terms.
|
||||
|
||||
If, on the Llama 3.2 version release date, the monthly active users of the
|
||||
products or services made available by or for Licensee, or Licensee’s
|
||||
affiliates, exceeds 700 million monthly active users in the preceding calendar
|
||||
month, you must request a license from Meta.
|
||||
|
||||
3. Disclaimer of Warranty.
|
||||
|
||||
THE LLAMA MATERIALS AND ANY OUTPUTS ARE PROVIDED “AS IS” WITHOUT WARRANTIES OF ANY
|
||||
KIND.
|
||||
|
||||
4. Limitation of Liability.
|
||||
|
||||
IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE FOR ANY DAMAGES ARISING OUT OF
|
||||
THIS AGREEMENT.
|
||||
|
||||
5. Governing Law.
|
||||
|
||||
This Agreement is governed by the laws of the State of California.
|
||||
481
README.md
Normal file
481
README.md
Normal file
@@ -0,0 +1,481 @@
|
||||
---
|
||||
license: other
|
||||
license_name: llama-3.2-community
|
||||
license_link: https://www.llama.com/llama-downloads
|
||||
base_model: meta-llama/Llama-3.2-1B
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
tags:
|
||||
- llama
|
||||
- llama-3
|
||||
- meta
|
||||
- causal-lm
|
||||
- text-generation
|
||||
---
|
||||
|
||||
<div align="center">
|
||||
|
||||
# LumiChats v1.1
|
||||
|
||||
**A Fine-tuned Conversational AI Model Based on Llama 3.2 3B**
|
||||
|
||||
[](https://llama.meta.com/llama3_2/license/)
|
||||
[]()
|
||||
[](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)
|
||||
|
||||
</div>
|
||||
|
||||
---
|
||||
|
||||
## 📖 Overview
|
||||
|
||||
LumiChats v1.1 is a specialized conversational AI model built on top of **Meta's Llama 3.2 3B Instruct** foundation. This model has been fine-tuned using **LoRA (Low-Rank Adaptation)** with the **Unsloth** framework to deliver enhanced conversational capabilities while maintaining exceptional efficiency and performance.
|
||||
|
||||
**Base Model:** [unsloth/Llama-3.2-3B-Instruct](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct)
|
||||
**Model Type:** Conversational AI / Instruction-tuned Language Model
|
||||
**Parameters:** 3.21 Billion (3,237,063,680 total)
|
||||
**Trainable Parameters:** 24,313,856 (~0.75% via LoRA)
|
||||
**Architecture:** Optimized Transformer with Auto-regressive Language Modeling
|
||||
|
||||
---
|
||||
|
||||
## ✨ Key Features
|
||||
|
||||
- **💬 Enhanced Conversational Abilities**: Fine-tuned on FineTome-100k for natural, engaging dialogue
|
||||
- **🚀 Efficient & Fast**:
|
||||
- 2x faster training and inference with Unsloth optimizations
|
||||
- 4-bit quantization for reduced memory footprint
|
||||
- Only 0.75% of parameters trained via LoRA
|
||||
- **🌍 Multilingual Support**: Supports 8+ languages (English, German, French, Italian, Portuguese, Hindi, Spanish, Thai)
|
||||
- **📱 Edge-Ready**: Optimized for deployment on edge devices and mobile platforms
|
||||
- **🎯 Superior Instruction Following**: Specialized training on response-only objectives
|
||||
- **🔒 Privacy-Focused**: Can run entirely on-device without cloud dependencies
|
||||
- **⚡ Memory Efficient**: Trained with just 2.35 GB peak memory using gradient checkpointing
|
||||
|
||||
---
|
||||
|
||||
## 🏗️ Architecture Details
|
||||
|
||||
LumiChats v1.1 inherits the robust architecture of Llama 3.2 3B:
|
||||
|
||||
- **Model Type**: Auto-regressive transformer language model (LlamaForCausalLM)
|
||||
- **Training Approach**:
|
||||
- Base: Supervised Fine-Tuning (SFT) + Reinforcement Learning with Human Feedback (RLHF)
|
||||
- Fine-tuning: LoRA adapters with response-only training
|
||||
- **Context Length**: Up to 128,000 tokens (trained with max_seq_length: 2048)
|
||||
- **Vocabulary Size**: Extended multilingual tokenizer
|
||||
- **Optimization**: 4-bit quantization, structured pruning, and knowledge distillation
|
||||
|
||||
### LoRA Configuration Details
|
||||
|
||||
- **LoRA Rank (r)**: 16
|
||||
- **LoRA Alpha**: 16
|
||||
- **Target Modules**: `q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj`
|
||||
- **LoRA Dropout**: 0
|
||||
- **Trainable Parameters**: 24,313,856 (0.75% of total 3.2B parameters)
|
||||
|
||||
---
|
||||
|
||||
## 🎯 Intended Use Cases
|
||||
|
||||
LumiChats v1.1 excels at:
|
||||
|
||||
- **Conversational AI**: Natural dialogue and chat applications
|
||||
- **Personal Assistants**: Task management and information retrieval
|
||||
- **Content Generation**: Writing assistance and creative text generation
|
||||
- **Summarization**: Document and conversation summarization
|
||||
- **Question Answering**: Knowledge retrieval and Q&A systems
|
||||
- **Code Assistance**: Basic coding help and explanations
|
||||
- **On-Device Applications**: Mobile AI assistants and offline chatbots
|
||||
|
||||
---
|
||||
|
||||
## 🚀 Quick Start
|
||||
|
||||
### Using Transformers
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
import torch
|
||||
|
||||
# Load model and tokenizer
|
||||
model_name = "adityakum667388/lumichats-v1.1"
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name,
|
||||
torch_dtype=torch.float16,
|
||||
device_map="auto"
|
||||
)
|
||||
|
||||
# Prepare conversation
|
||||
messages = [
|
||||
{"role": "system", "content": "You are a helpful AI assistant."},
|
||||
{"role": "user", "content": "What is the capital of France?"}
|
||||
]
|
||||
|
||||
# Generate response
|
||||
input_ids = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
add_generation_prompt=True,
|
||||
return_tensors="pt"
|
||||
).to(model.device)
|
||||
|
||||
outputs = model.generate(
|
||||
input_ids,
|
||||
max_new_tokens=512,
|
||||
temperature=0.7,
|
||||
top_p=0.9,
|
||||
do_sample=True,
|
||||
eos_token_id=tokenizer.eos_token_id
|
||||
)
|
||||
|
||||
response = tokenizer.decode(outputs[0][input_ids.shape[-1]:], skip_special_tokens=True)
|
||||
print(response)
|
||||
```
|
||||
|
||||
### Using Unsloth for Inference (Fastest)
|
||||
|
||||
```python
|
||||
from unsloth import FastLanguageModel
|
||||
|
||||
# Load model with Unsloth (2x faster inference)
|
||||
model, tokenizer = FastLanguageModel.from_pretrained(
|
||||
model_name="adityakum667388/lumichats-v1.1",
|
||||
max_seq_length=2048,
|
||||
dtype=None, # Auto-detect
|
||||
load_in_4bit=True, # Memory efficient
|
||||
)
|
||||
|
||||
# Enable native 2x faster inference
|
||||
FastLanguageModel.for_inference(model)
|
||||
|
||||
# Chat template
|
||||
messages = [
|
||||
{"role": "system", "content": "You are a helpful AI assistant."},
|
||||
{"role": "user", "content": "Explain quantum computing"}
|
||||
]
|
||||
|
||||
inputs = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=True,
|
||||
add_generation_prompt=True,
|
||||
return_tensors="pt"
|
||||
).to("cuda")
|
||||
|
||||
outputs = model.generate(
|
||||
input_ids=inputs,
|
||||
max_new_tokens=128,
|
||||
temperature=1.5,
|
||||
min_p=0.1
|
||||
)
|
||||
print(tokenizer.batch_decode(outputs))
|
||||
```
|
||||
|
||||
### Chat Template Format
|
||||
|
||||
LumiChats v1.1 uses the Llama 3.1 chat template format:
|
||||
|
||||
```
|
||||
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
||||
|
||||
You are a helpful AI assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>
|
||||
|
||||
Hello!<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
||||
```
|
||||
|
||||
**Special Tokens:**
|
||||
- `<|begin_of_text|>` - Beginning of sequence
|
||||
- `<|start_header_id|>` - Start of role header
|
||||
- `<|end_header_id|>` - End of role header
|
||||
- `<|eot_id|>` - End of turn
|
||||
- `<|finetune_right_pad_id|>` - Padding token
|
||||
|
||||
### Using GGUF Format (llama.cpp)
|
||||
|
||||
```python
|
||||
from llama_cpp import Llama
|
||||
|
||||
# Load GGUF model
|
||||
llm = Llama(
|
||||
model_path="lumichats-v1.1-Q4_K_M.gguf",
|
||||
n_ctx=4096,
|
||||
n_gpu_layers=-1 # Use GPU acceleration
|
||||
)
|
||||
|
||||
# Format prompt with chat template
|
||||
prompt = """<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
||||
|
||||
You are a helpful AI assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>
|
||||
|
||||
What is machine learning?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
||||
|
||||
"""
|
||||
|
||||
# Generate response
|
||||
output = llm(
|
||||
prompt,
|
||||
max_tokens=512,
|
||||
temperature=0.7,
|
||||
top_p=0.9,
|
||||
stop=["<|eot_id|>", "<|end_of_text|>", "<|im_end|>", "<|endoftext|>"]
|
||||
)
|
||||
|
||||
print(output['choices'][0]['text'])
|
||||
```
|
||||
|
||||
### Using Ollama
|
||||
|
||||
```bash
|
||||
# Pull the model (if available on Ollama)
|
||||
ollama pull lumichats-v1.1
|
||||
|
||||
# Run inference
|
||||
ollama run lumichats-v1.1 "Explain quantum computing in simple terms"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 📦 Available Model Formats
|
||||
|
||||
| Format | Size | Precision | Use Case |
|
||||
|--------|------|-----------|----------|
|
||||
| **SafeTensors (FP16)** | ~6.5 GB | Full precision | Training, fine-tuning, highest quality |
|
||||
| **GGUF (Q4_K_M)** | ~2.0 GB | 4-bit quantized | **Recommended** - Best balance of size/quality |
|
||||
| **GGUF (Q5_K_M)** | ~2.3 GB | 5-bit quantized | Higher quality, slightly larger |
|
||||
| **GGUF (Q8_0)** | ~3.5 GB | 8-bit quantized | Near-full quality |
|
||||
| **GGUF (F16)** | ~6.4 GB | Full precision GGUF | Maximum compatibility |
|
||||
| **LoRA Adapters** | ~100 MB | Adapter weights only | For merging with base model |
|
||||
|
||||
**Recommendation**: For most users, **Q4_K_M** offers the best tradeoff between model size and output quality.
|
||||
|
||||
---
|
||||
|
||||
## 💻 Hardware Requirements
|
||||
|
||||
### Minimum Requirements
|
||||
- **RAM**: 4 GB (for Q4_K_M quantized version)
|
||||
- **GPU**: Optional, but recommended (4GB+ VRAM)
|
||||
- **Storage**: 2-7 GB depending on format
|
||||
|
||||
### Recommended Setup
|
||||
- **RAM**: 8 GB or more
|
||||
- **GPU**: NVIDIA GPU with 6GB+ VRAM (RTX 3060, T4, or better)
|
||||
- **CPU**: Modern multi-core processor (for CPU inference)
|
||||
|
||||
### Performance Estimates
|
||||
- **GPU (T4)**: 20-40 tokens/second
|
||||
- **GPU (T4 with Unsloth)**: 40-80 tokens/second (2x faster)
|
||||
- **GPU (RTX 4090)**: 60-100+ tokens/second
|
||||
- **CPU (High-end)**: 5-15 tokens/second
|
||||
|
||||
---
|
||||
|
||||
## 🎨 Training Details
|
||||
|
||||
### Training Configuration
|
||||
|
||||
LumiChats v1.1 was fine-tuned with the following setup:
|
||||
|
||||
**Framework & Optimization:**
|
||||
- **Base Model**: unsloth/Llama-3.2-3B-Instruct
|
||||
- **Training Framework**: Unsloth 2026.1.4 (optimized fine-tuning)
|
||||
- **Fine-tuning Method**: LoRA (Low-Rank Adaptation)
|
||||
- **Quantization**: 4-bit during training (`load_in_4bit=True`)
|
||||
- **Gradient Checkpointing**: Unsloth-optimized for memory efficiency
|
||||
|
||||
**Dataset & Preprocessing:**
|
||||
- **Dataset**: mlabonne/FineTome-100k
|
||||
- **Format**: ShareGPT → HuggingFace chat format
|
||||
- **Chat Template**: Llama 3.1 template
|
||||
- **Training Objective**: Response-only training (masks user inputs)
|
||||
|
||||
**Hardware & Performance:**
|
||||
- **GPU**: Tesla T4 (Max memory: 14.741 GB)
|
||||
- **Peak Memory Usage**: 2.35 GB additional for training
|
||||
- **Training Time**: 8.54 minutes (512 seconds) for 60 steps
|
||||
- **Speed**: 2x faster than standard PyTorch training
|
||||
|
||||
### Training Hyperparameters
|
||||
|
||||
```python
|
||||
training_config = {
|
||||
"per_device_train_batch_size": 2,
|
||||
"gradient_accumulation_steps": 4,
|
||||
"effective_batch_size": 8,
|
||||
"warmup_steps": 5,
|
||||
"max_steps": 60,
|
||||
"learning_rate": 2e-4,
|
||||
"optimizer": "adamw_8bit",
|
||||
"weight_decay": 0.001,
|
||||
"lr_scheduler_type": "linear",
|
||||
"max_seq_length": 2048,
|
||||
"dtype": "float16",
|
||||
"seed": 3407
|
||||
}
|
||||
```
|
||||
|
||||
### Why This Approach is Superior
|
||||
|
||||
1. **Efficiency**: Only 0.75% of parameters trained, reducing computational cost by 99%+
|
||||
2. **Speed**: Unsloth optimizations provide 2x faster training and inference
|
||||
3. **Memory**: 4-bit quantization + gradient checkpointing enables training on consumer GPUs
|
||||
4. **Quality**: Response-only training focuses learning on generating high-quality outputs
|
||||
5. **Versatility**: Multiple export formats (HuggingFace, GGUF) for diverse deployment scenarios
|
||||
|
||||
The model builds upon Llama 3.2's foundation, which was pretrained on up to **9 trillion tokens** from publicly available sources and further refined through supervised fine-tuning and RLHF alignment.
|
||||
|
||||
---
|
||||
|
||||
## 📊 Performance & Benchmarks
|
||||
|
||||
LumiChats v1.1 inherits the strong performance characteristics of Llama 3.2 3B, with enhanced conversational abilities:
|
||||
|
||||
- **MMLU** (Massive Multitask Language Understanding): Competitive performance
|
||||
- **AGIEval** (General AI evaluation): Strong reasoning capabilities
|
||||
- **ARC-Challenge** (Abstract reasoning): Improved over base model
|
||||
- **Instruction Following**: Superior response quality on FineTome-100k
|
||||
- **Multilingual** dialogue tasks: Consistent across 8+ languages
|
||||
- **Conversational Quality**: Enhanced coherence and context awareness
|
||||
|
||||
The model outperforms similar-sized models like Gemma 2 2.6B and Phi 3.5-mini on instruction following, summarization, and conversational tasks, while maintaining efficiency advantages through LoRA and quantization.
|
||||
|
||||
---
|
||||
|
||||
## 🌐 Supported Languages
|
||||
|
||||
Official support for 8 languages:
|
||||
- 🇬🇧 English
|
||||
- 🇩🇪 German
|
||||
- 🇫🇷 French
|
||||
- 🇮🇹 Italian
|
||||
- 🇵🇹 Portuguese
|
||||
- 🇮🇳 Hindi
|
||||
- 🇪🇸 Spanish
|
||||
- 🇹🇭 Thai
|
||||
|
||||
*Note: The model has been trained on additional languages and can be fine-tuned for other languages as needed.*
|
||||
|
||||
---
|
||||
|
||||
## ⚖️ Limitations & Considerations
|
||||
|
||||
- **Context Understanding**: May struggle with very long contexts despite 128k token capacity
|
||||
- **Factual Accuracy**: Can occasionally generate plausible but incorrect information
|
||||
- **Bias**: May reflect biases present in training data
|
||||
- **Specialized Knowledge**: Not optimized for highly technical or domain-specific tasks
|
||||
- **Real-time Information**: No access to current events (knowledge cutoff applies)
|
||||
- **Safety**: Should be deployed with appropriate content filtering and monitoring
|
||||
- **LoRA Constraints**: Trained parameters limited to attention and MLP layers
|
||||
|
||||
---
|
||||
|
||||
## 🔒 Responsible AI & Safety
|
||||
|
||||
LumiChats v1.1 is built on Llama 3.2's safety foundations:
|
||||
|
||||
- Trained with safety alignment through RLHF (base model)
|
||||
- Designed to decline harmful requests
|
||||
- Tested for bias and fairness across languages
|
||||
- Implements content filtering guidelines
|
||||
- Response-only training reduces risk of prompt injection
|
||||
|
||||
**Developers should**:
|
||||
- Implement additional safety layers for production use
|
||||
- Test thoroughly for their specific use case
|
||||
- Monitor outputs for quality and appropriateness
|
||||
- Follow the Llama 3.2 Acceptable Use Policy
|
||||
- Be aware that fine-tuning may affect safety properties
|
||||
|
||||
---
|
||||
|
||||
## 📜 License
|
||||
|
||||
This model is released under the **Llama 3.2 Community License**.
|
||||
|
||||
- ✅ Commercial use permitted
|
||||
- ✅ Modification and derivative works allowed
|
||||
- ✅ Distribution allowed with attribution
|
||||
- ⚠️ Subject to Llama 3.2 Acceptable Use Policy
|
||||
|
||||
Please review the full license at: [Llama 3.2 License](https://llama.meta.com/llama3_2/license/)
|
||||
|
||||
---
|
||||
|
||||
## 🙏 Acknowledgments
|
||||
|
||||
- **Meta AI** for developing and releasing Llama 3.2
|
||||
- **Unsloth AI** for the efficient fine-tuning framework and optimizations
|
||||
- **Maxime Labonne** for the FineTome-100k dataset
|
||||
- **Hugging Face** for model hosting and transformers library
|
||||
- The open-source AI community for tools and support
|
||||
|
||||
---
|
||||
|
||||
## 📞 Contact & Support
|
||||
|
||||
- **Model Page**: [huggingface.co/adityakum667388/lumichats-v1.1](https://huggingface.co/adityakum667388/lumichats-v1.1)
|
||||
- **LoRA Adapters**: [huggingface.co/adityakum667388/lumichats-lora](https://huggingface.co/adityakum667388/lumichats-lora)
|
||||
- **Issues**: Report bugs or request features via the Community tab
|
||||
- **Creator**: [@adityakum667388](https://huggingface.co/adityakum667388)
|
||||
|
||||
---
|
||||
|
||||
## 🔄 Version History
|
||||
|
||||
**v1.1** (Current)
|
||||
- Initial release
|
||||
- Fine-tuned on Llama 3.2 3B Instruct with LoRA
|
||||
- Trained on FineTome-100k dataset
|
||||
- Optimized for conversational tasks
|
||||
- Multiple export formats available (SafeTensors, GGUF, LoRA adapters)
|
||||
- 2x faster inference with Unsloth
|
||||
- Peak training memory: 2.35 GB on Tesla T4
|
||||
|
||||
---
|
||||
|
||||
## 📚 Citation
|
||||
|
||||
If you use LumiChats v1.1 in your research or applications, please cite:
|
||||
|
||||
```bibtex
|
||||
@misc{lumichats2025,
|
||||
author = {Aditya Kumar},
|
||||
title = {LumiChats v1.1: A Fine-tuned Conversational AI Model},
|
||||
year = {2025},
|
||||
publisher = {HuggingFace},
|
||||
howpublished = {\url{https://huggingface.co/adityakum667388/lumichats-v1.1}},
|
||||
note = {Fine-tuned using Unsloth and LoRA on FineTome-100k}
|
||||
}
|
||||
```
|
||||
|
||||
And the base model:
|
||||
|
||||
```bibtex
|
||||
@article{llama32,
|
||||
title={Llama 3.2: Advancing Efficient and Accessible AI},
|
||||
author={Meta AI},
|
||||
year={2024},
|
||||
url={https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/}
|
||||
}
|
||||
```
|
||||
|
||||
And Unsloth:
|
||||
|
||||
```bibtex
|
||||
@software{unsloth2024,
|
||||
author = {Unsloth AI},
|
||||
title = {Unsloth: Fast and Memory-Efficient Finetuning},
|
||||
year = {2024},
|
||||
url = {https://github.com/unslothai/unsloth}
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
<div align="center">
|
||||
|
||||
**Built with ❤️ using Llama 3.2 3B | Powered by Unsloth | Trained on FineTome-100k**
|
||||
|
||||
⭐ If you find this model useful, please consider giving it a star!
|
||||
|
||||
</div>
|
||||
139
chat_template.jinja
Normal file
139
chat_template.jinja
Normal file
@@ -0,0 +1,139 @@
|
||||
{{- bos_token }}
|
||||
{%- if custom_tools is defined %}
|
||||
{%- set tools = custom_tools %}
|
||||
{%- endif %}
|
||||
{%- if not tools_in_user_message is defined %}
|
||||
{%- set tools_in_user_message = true %}
|
||||
{%- endif %}
|
||||
{%- if not date_string is defined %}
|
||||
{%- set date_string = "26 July 2024" %}
|
||||
{%- endif %}
|
||||
{%- if not tools is defined %}
|
||||
{%- set tools = none %}
|
||||
{%- endif %}
|
||||
|
||||
{#- This block extracts the system message, so we can slot it into the right place. #}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{%- set system_message = messages[0]['content'] %}
|
||||
{%- set messages = messages[1:] %}
|
||||
{%- else %}
|
||||
{%- set system_message = "" %}
|
||||
{%- endif %}
|
||||
|
||||
{#- System message + builtin tools #}
|
||||
{{- "<|start_header_id|>system<|end_header_id|>
|
||||
|
||||
" }}
|
||||
{%- if builtin_tools is defined or tools is not none %}
|
||||
{{- "Environment: ipython
|
||||
" }}
|
||||
{%- endif %}
|
||||
{%- if builtin_tools is defined %}
|
||||
{{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "
|
||||
|
||||
"}}
|
||||
{%- endif %}
|
||||
{{- "Cutting Knowledge Date: December 2023
|
||||
" }}
|
||||
{{- "Today Date: " + date_string + "
|
||||
|
||||
" }}
|
||||
{%- if tools is not none and not tools_in_user_message %}
|
||||
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
|
||||
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
||||
{{- "Do not use variables.
|
||||
|
||||
" }}
|
||||
{%- for t in tools %}
|
||||
{{- t | tojson(indent=4) }}
|
||||
{{- "
|
||||
|
||||
" }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- system_message }}
|
||||
{{- "<|eot_id|>" }}
|
||||
|
||||
{#- Custom tools are passed in a user message with some extra guidance #}
|
||||
{%- if tools_in_user_message and not tools is none %}
|
||||
{#- Extract the first user message so we can plug it in here #}
|
||||
{%- if messages | length != 0 %}
|
||||
{%- set first_user_message = messages[0]['content'] %}
|
||||
{%- set messages = messages[1:] %}
|
||||
{%- else %}
|
||||
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
|
||||
{%- endif %}
|
||||
{{- '<|start_header_id|>user<|end_header_id|>
|
||||
|
||||
' -}}
|
||||
{{- "Given the following functions, please respond with a JSON for a function call " }}
|
||||
{{- "with its proper arguments that best answers the given prompt.
|
||||
|
||||
" }}
|
||||
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
||||
{{- "Do not use variables.
|
||||
|
||||
" }}
|
||||
{%- for t in tools %}
|
||||
{{- t | tojson(indent=4) }}
|
||||
{{- "
|
||||
|
||||
" }}
|
||||
{%- endfor %}
|
||||
{{- first_user_message + "<|eot_id|>"}}
|
||||
{%- endif %}
|
||||
|
||||
{%- for message in messages %}
|
||||
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
|
||||
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>
|
||||
|
||||
'+ message['content'] + '<|eot_id|>' }}
|
||||
{%- elif 'tool_calls' in message %}
|
||||
{%- if not message.tool_calls|length == 1 %}
|
||||
{{- raise_exception("This model only supports single tool-calls at once!") }}
|
||||
{%- endif %}
|
||||
{%- set tool_call = message.tool_calls[0].function %}
|
||||
{%- if builtin_tools is defined and tool_call.name in builtin_tools %}
|
||||
{{- '<|start_header_id|>assistant<|end_header_id|>
|
||||
|
||||
' -}}
|
||||
{{- "<|python_tag|>" + tool_call.name + ".call(" }}
|
||||
{%- for arg_name, arg_val in tool_call.arguments | items %}
|
||||
{{- arg_name + '="' + arg_val + '"' }}
|
||||
{%- if not loop.last %}
|
||||
{{- ", " }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{{- ")" }}
|
||||
{%- else %}
|
||||
{{- '<|start_header_id|>assistant<|end_header_id|>
|
||||
|
||||
' -}}
|
||||
{{- '{"name": "' + tool_call.name + '", ' }}
|
||||
{{- '"parameters": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- "}" }}
|
||||
{%- endif %}
|
||||
{%- if builtin_tools is defined %}
|
||||
{#- This means we're in ipython mode #}
|
||||
{{- "<|eom_id|>" }}
|
||||
{%- else %}
|
||||
{{- "<|eot_id|>" }}
|
||||
{%- endif %}
|
||||
{%- elif message.role == "tool" or message.role == "ipython" %}
|
||||
{{- "<|start_header_id|>ipython<|end_header_id|>
|
||||
|
||||
" }}
|
||||
{%- if message.content is mapping or message.content is iterable %}
|
||||
{{- message.content | tojson }}
|
||||
{%- else %}
|
||||
{{- message.content }}
|
||||
{%- endif %}
|
||||
{{- "<|eot_id|>" }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|start_header_id|>assistant<|end_header_id|>
|
||||
|
||||
' }}
|
||||
{%- endif %}
|
||||
38
config.json
Normal file
38
config.json
Normal file
@@ -0,0 +1,38 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"torch_dtype": "float16",
|
||||
"eos_token_id": 128009,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3072,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8192,
|
||||
"max_position_embeddings": 131072,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 24,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 128004,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"factor": 32.0,
|
||||
"high_freq_factor": 4.0,
|
||||
"low_freq_factor": 1.0,
|
||||
"original_max_position_embeddings": 8192,
|
||||
"rope_type": "llama3"
|
||||
},
|
||||
"rope_theta": 500000.0,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "4.56.2",
|
||||
"unsloth_fixed": true,
|
||||
"unsloth_version": "2026.1.4",
|
||||
"use_cache": true,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
3
lumichats-v1.1-Q4_K_M.gguf
Normal file
3
lumichats-v1.1-Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2de98e8232149a3e3a838fe03666498b16009797304690b7b7ce6c7e822e56ec
|
||||
size 2019378432
|
||||
3
lumichats-v1.1-Q5_K_M.gguf
Normal file
3
lumichats-v1.1-Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ff147039247971a6f6e90495b63fe324b1e2030b9c23d650152e1226c3143802
|
||||
size 2322154752
|
||||
3
lumichats-v1.1-Q8_0.gguf
Normal file
3
lumichats-v1.1-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:385314ef834a2549f1d503dfe804815414b996f1e571a52c7a04cee3c075a769
|
||||
size 3421900032
|
||||
3
lumichats-v1.1-f16.gguf
Normal file
3
lumichats-v1.1-f16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4cfc5683ba13dac5146d632b8f9f29519137e389eec55b7daa105bf4ad41d882
|
||||
size 6433688832
|
||||
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cff56aeb8b828a5fcb6c6e1cd6af597e7e6065ed2a4f3e9d1d1b02fcb2c8ed67
|
||||
size 4965799096
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0f51f8ef91c6460bc22ed6c47608cd9c919c1d79372b6645502e99e880bf8ca0
|
||||
size 1459729952
|
||||
261
model.safetensors.index.json
Normal file
261
model.safetensors.index.json
Normal file
@@ -0,0 +1,261 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 6425499648
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00002-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|finetune_right_pad_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
2067
tokenizer_config.json
Normal file
2067
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user