初始化项目，由ModelHub XC社区提供模型
Model: OpenMedZoo/MedGo Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
|||||||
|
*.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
|
||||||
|
main_results.png filter=lfs diff=lfs merge=lfs -text
|
||||||
14
Modelfile
Normal file
14
Modelfile
Normal file
@@ -0,0 +1,14 @@
|
|||||||
|
# ollama modelfile auto-generated by llamafactory
|
||||||
|
|
||||||
|
FROM .
|
||||||
|
|
||||||
|
TEMPLATE """{{ if .System }}<|im_start|>system
|
||||||
|
{{ .System }}<|im_end|>
|
||||||
|
{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|im_start|>user
|
||||||
|
{{ .Content }}<|im_end|>
|
||||||
|
<|im_start|>assistant
|
||||||
|
{{ else if eq .Role "assistant" }}{{ .Content }}<|im_end|>
|
||||||
|
{{ end }}{{ end }}"""
|
||||||
|
|
||||||
|
PARAMETER stop "<|im_end|>"
|
||||||
|
PARAMETER num_ctx 4096
|
||||||
547
README.md
Normal file
547
README.md
Normal file
@@ -0,0 +1,547 @@
|
|||||||
|
---
|
||||||
|
license: apache-2.0
|
||||||
|
language:
|
||||||
|
- zh
|
||||||
|
- en
|
||||||
|
metrics:
|
||||||
|
- accuracy
|
||||||
|
base_model:
|
||||||
|
- Qwen/Qwen3-32B
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
library_name: transformers
|
||||||
|
tags:
|
||||||
|
- medical
|
||||||
|
model-index:
|
||||||
|
- name: Med-Go-32B
|
||||||
|
results:
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
dataset:
|
||||||
|
type: medical_eval_hle
|
||||||
|
name: Medical-Eval-HLE
|
||||||
|
metrics:
|
||||||
|
- name: accuracy
|
||||||
|
type: accuracy
|
||||||
|
value: 19.4
|
||||||
|
verified: false
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
dataset:
|
||||||
|
type: supergpqa
|
||||||
|
name: SuperGPQA
|
||||||
|
metrics:
|
||||||
|
- name: accuracy
|
||||||
|
type: accuracy
|
||||||
|
value: 37.2
|
||||||
|
verified: false
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
dataset:
|
||||||
|
type: medbullets
|
||||||
|
name: Medbullets
|
||||||
|
metrics:
|
||||||
|
- name: accuracy
|
||||||
|
type: accuracy
|
||||||
|
value: 57.8
|
||||||
|
verified: false
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
dataset:
|
||||||
|
type: mmlu_pro
|
||||||
|
name: MMLU-pro
|
||||||
|
metrics:
|
||||||
|
- name: accuracy
|
||||||
|
type: accuracy
|
||||||
|
value: 64.3
|
||||||
|
verified: false
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
dataset:
|
||||||
|
type: afrimedqa
|
||||||
|
name: AfrimedQA
|
||||||
|
metrics:
|
||||||
|
- name: accuracy
|
||||||
|
type: accuracy
|
||||||
|
value: 74.7
|
||||||
|
verified: false
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
dataset:
|
||||||
|
type: medmcqa
|
||||||
|
name: MedMCQA
|
||||||
|
metrics:
|
||||||
|
- name: accuracy
|
||||||
|
type: accuracy
|
||||||
|
value: 68.3
|
||||||
|
verified: false
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
dataset:
|
||||||
|
type: medqa_usmle
|
||||||
|
name: MedQA-USMLE
|
||||||
|
metrics:
|
||||||
|
- name: accuracy
|
||||||
|
type: accuracy
|
||||||
|
value: 76.8
|
||||||
|
verified: false
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
dataset:
|
||||||
|
type: cmb
|
||||||
|
name: CMB
|
||||||
|
metrics:
|
||||||
|
- name: accuracy
|
||||||
|
type: accuracy
|
||||||
|
value: 92.5
|
||||||
|
verified: false
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
dataset:
|
||||||
|
type: cmexam
|
||||||
|
name: CMExam
|
||||||
|
metrics:
|
||||||
|
- name: accuracy
|
||||||
|
type: accuracy
|
||||||
|
value: 87.4
|
||||||
|
verified: false
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
dataset:
|
||||||
|
type: pubmedqa
|
||||||
|
name: PubMedQA
|
||||||
|
metrics:
|
||||||
|
- name: accuracy
|
||||||
|
type: accuracy
|
||||||
|
value: 76.6
|
||||||
|
verified: false
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
dataset:
|
||||||
|
type: medexqa
|
||||||
|
name: MedExQA
|
||||||
|
metrics:
|
||||||
|
- name: accuracy
|
||||||
|
type: accuracy
|
||||||
|
value: 81.5
|
||||||
|
verified: false
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
dataset:
|
||||||
|
type: explaincpe
|
||||||
|
name: ExplainCPE
|
||||||
|
metrics:
|
||||||
|
- name: accuracy
|
||||||
|
type: accuracy
|
||||||
|
value: 89.5
|
||||||
|
verified: false
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
dataset:
|
||||||
|
type: mmlu_med
|
||||||
|
name: MMLU-Med
|
||||||
|
metrics:
|
||||||
|
- name: accuracy
|
||||||
|
type: accuracy
|
||||||
|
value: 87.4
|
||||||
|
verified: false
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
dataset:
|
||||||
|
type: medxperqa
|
||||||
|
name: MedXperQA
|
||||||
|
metrics:
|
||||||
|
- name: accuracy
|
||||||
|
type: accuracy
|
||||||
|
value: 20.7
|
||||||
|
verified: false
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
dataset:
|
||||||
|
type: anesbench
|
||||||
|
name: AnesBench
|
||||||
|
metrics:
|
||||||
|
- name: accuracy
|
||||||
|
type: accuracy
|
||||||
|
value: 53.1
|
||||||
|
verified: false
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
dataset:
|
||||||
|
type: diagnosisarena
|
||||||
|
name: DiagnosisArena
|
||||||
|
metrics:
|
||||||
|
- name: accuracy
|
||||||
|
type: accuracy
|
||||||
|
value: 64.4
|
||||||
|
verified: false
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
dataset:
|
||||||
|
type: clinbench_hbp
|
||||||
|
name: Clinbench-HBP
|
||||||
|
metrics:
|
||||||
|
- name: accuracy
|
||||||
|
type: accuracy
|
||||||
|
value: 80.6
|
||||||
|
verified: false
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
dataset:
|
||||||
|
type: medpair
|
||||||
|
name: MedPAIR
|
||||||
|
metrics:
|
||||||
|
- name: accuracy
|
||||||
|
type: accuracy
|
||||||
|
value: 32.3
|
||||||
|
verified: false
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
dataset:
|
||||||
|
type: amqa
|
||||||
|
name: AMQA
|
||||||
|
metrics:
|
||||||
|
- name: accuracy
|
||||||
|
type: accuracy
|
||||||
|
value: 72.7
|
||||||
|
verified: false
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
dataset:
|
||||||
|
type: medethicaleval
|
||||||
|
name: MedethicalEval
|
||||||
|
metrics:
|
||||||
|
- name: accuracy
|
||||||
|
type: accuracy
|
||||||
|
value: 92.2
|
||||||
|
verified: false
|
||||||
|
---
|
||||||
|
|
||||||
|
# MedGo: Medical Large Language Model Based on Qwen3-32B
|
||||||
|
|
||||||
|
<div align="center">
|
||||||
|
|
||||||
|
[](https://huggingface.co/OpenMedZoo/MedGo)
|
||||||
|
[](LICENSE)
|
||||||
|
[](https://www.python.org/)
|
||||||
|
|
||||||
|
|
||||||
|
English | [简体中文](./README_CN.md)
|
||||||
|
|
||||||
|
</div>
|
||||||
|
|
||||||
|
## 📋 Table of Contents
|
||||||
|
|
||||||
|
- [Introduction](#introduction)
|
||||||
|
- [Key Features](#key-features)
|
||||||
|
- [Performance](#performance)
|
||||||
|
- [Quick Start](#quick-start)
|
||||||
|
- [Training Details](#training-details)
|
||||||
|
- [Use Cases](#use-cases)
|
||||||
|
- [Limitations & Risks](#limitations--risks)
|
||||||
|
- [Citation](#citation)
|
||||||
|
- [License](#license)
|
||||||
|
- [Contributing](#contributing)
|
||||||
|
- [Contact](#contact)
|
||||||
|
|
||||||
|
## 🎯 Introduction
|
||||||
|
|
||||||
|
**MedGo** is a general-purpose medical large language model fine-tuned from **Qwen3-32B**, designed for clinical medicine and research scenarios. The model is trained on large-scale multi-source medical corpora and enhanced with complex case data, supporting various capabilities including medical Q&A, clinical summary, clinical reasoning, multi-turn dialogue, and scientific text generation.
|
||||||
|
|
||||||
|
### 🌟 Core Capabilities
|
||||||
|
|
||||||
|
- **📚 Medical Knowledge Q&A**: Professional responses based on authoritative medical literature and clinical guidelines
|
||||||
|
- **📝 Clinical Documentation**: Automated medical record summaries, diagnostic reports, and medical documentation
|
||||||
|
- **🔍 Clinical Reasoning**: Differential diagnosis, examination recommendations, and treatment suggestions
|
||||||
|
- **💬 Multi-turn Dialogue**: Patient-doctor interaction simulation and complex case discussions
|
||||||
|
- **🔬 Research Support**: Literature summarization, research idea generation, and quality control review
|
||||||
|
|
||||||
|
## ✨ Key Features
|
||||||
|
|
||||||
|
| Feature | Details |
|
||||||
|
|---------|---------|
|
||||||
|
| **Base Architecture** | Qwen3-32B |
|
||||||
|
| **Parameters** | 32B |
|
||||||
|
| **Domain** | Clinical Medicine, Research Support, Healthcare System Integration |
|
||||||
|
| **Fine-tuning Method** | SFT + Preference Alignment (DPO/KTO) |
|
||||||
|
| **Data Sources** | Authoritative medical literature, clinical guidelines, real cases (anonymized) |
|
||||||
|
| **Deployment** | Local deployment, HIS/EMR system integration |
|
||||||
|
| **License** | Apache 2.0 |
|
||||||
|
|
||||||
|
## 📊 Performance
|
||||||
|
|
||||||
|
MedGo demonstrates excellent performance across multiple medical and general evaluation benchmarks, showing competitive results among 32B-parameter models:
|
||||||
|
|
||||||
|
### Key Benchmark Results
|
||||||
|
|
||||||
|
- **AIMedQA**: Medical question answering comprehension
|
||||||
|
- **CME**: Clinical reasoning evaluation
|
||||||
|
- **DiagnosisArena**: Diagnostic capability assessment
|
||||||
|
- **MedQA / MedMCQA**: Medical multiple-choice questions
|
||||||
|
- **PubMedQA**: Biomedical literature Q&A
|
||||||
|
- **MMLU-Pro**: Comprehensive capability evaluation
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
**Performance Highlights**:
|
||||||
|
- ✅ **Average Score**: ~70 points (excellent performance in the 32B parameter class)
|
||||||
|
- ✅ **Strong Tasks**: Clinical reasoning (DiagnosisArena, CME) and multi-turn medical Q&A
|
||||||
|
- ✅ **Balanced Capability**: Good performance in medical semantic understanding and multi-task generalization
|
||||||
|
|
||||||
|
|
||||||
|
## 🚀 Quick Start
|
||||||
|
|
||||||
|
### Requirements
|
||||||
|
|
||||||
|
- Python >= 3.8
|
||||||
|
- PyTorch >= 2.0
|
||||||
|
- Transformers >= 4.35.0
|
||||||
|
- CUDA >= 11.8 (for GPU inference)
|
||||||
|
|
||||||
|
### Installation
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# Clone the repository
|
||||||
|
git clone https://github.com/OpenMedZoo/MedGo.git
|
||||||
|
cd MedGo
|
||||||
|
|
||||||
|
# Install dependencies
|
||||||
|
pip install -r requirements.txt
|
||||||
|
```
|
||||||
|
|
||||||
|
### Model Download
|
||||||
|
|
||||||
|
Download model weights from HuggingFace:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# Using huggingface-cli
|
||||||
|
huggingface-cli download OpenMedZoo/MedGo --local-dir ./models/MedGo
|
||||||
|
|
||||||
|
# Or using git-lfs
|
||||||
|
git lfs install
|
||||||
|
git clone https://huggingface.co/OpenMedZoo/MedGo
|
||||||
|
```
|
||||||
|
|
||||||
|
### Basic Inference
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||||
|
|
||||||
|
# Load model and tokenizer
|
||||||
|
model_path = "OpenMedZoo/MedGo"
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
model_path,
|
||||||
|
device_map="auto",
|
||||||
|
trust_remote_code=True,
|
||||||
|
torch_dtype="auto"
|
||||||
|
)
|
||||||
|
|
||||||
|
# Medical Q&A example
|
||||||
|
messages = [
|
||||||
|
{"role": "system", "content": "You are a professional medical assistant. Please answer questions based on medical knowledge."},
|
||||||
|
{"role": "user", "content": "What is hypertension and what are the common treatment methods?"}
|
||||||
|
]
|
||||||
|
|
||||||
|
# Generate response
|
||||||
|
inputs = tokenizer.apply_chat_template(
|
||||||
|
messages,
|
||||||
|
tokenize=True,
|
||||||
|
add_generation_prompt=True,
|
||||||
|
return_tensors="pt"
|
||||||
|
).to(model.device)
|
||||||
|
|
||||||
|
outputs = model.generate(
|
||||||
|
inputs,
|
||||||
|
max_new_tokens=512,
|
||||||
|
temperature=0.7,
|
||||||
|
top_p=0.9,
|
||||||
|
do_sample=True
|
||||||
|
)
|
||||||
|
|
||||||
|
response = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
|
||||||
|
print(response)
|
||||||
|
```
|
||||||
|
|
||||||
|
### Batch Inference
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# Use the provided inference script
|
||||||
|
python scripts/inference.py \
|
||||||
|
--model_path OpenMedZoo/MedGo \
|
||||||
|
--input_file examples/medical_qa.jsonl \
|
||||||
|
--output_file results/predictions.jsonl \
|
||||||
|
--batch_size 4
|
||||||
|
```
|
||||||
|
|
||||||
|
### Accelerated Inference with vLLM
|
||||||
|
|
||||||
|
```python
|
||||||
|
from vllm import LLM, SamplingParams
|
||||||
|
|
||||||
|
# Initialize vLLM
|
||||||
|
llm = LLM(model="OpenMedZoo/MedGo", trust_remote_code=True)
|
||||||
|
sampling_params = SamplingParams(temperature=0.7, top_p=0.9, max_tokens=512)
|
||||||
|
|
||||||
|
# Batch inference
|
||||||
|
prompts = [
|
||||||
|
"What are the symptoms and treatment methods for diabetes?",
|
||||||
|
"What dietary precautions should hypertensive patients take?"
|
||||||
|
]
|
||||||
|
|
||||||
|
outputs = llm.generate(prompts, sampling_params)
|
||||||
|
for output in outputs:
|
||||||
|
print(output.outputs[0].text)
|
||||||
|
```
|
||||||
|
|
||||||
|
## 🔧 Training Details
|
||||||
|
|
||||||
|
MedGo employs a **two-stage fine-tuning strategy** to balance general medical knowledge with clinical task adaptation.
|
||||||
|
|
||||||
|
### Stage I: General Medical Alignment
|
||||||
|
|
||||||
|
**Objective**: Establish a solid foundation of medical knowledge and improve Q&A standardization
|
||||||
|
|
||||||
|
- **Data Sources**:
|
||||||
|
- Authoritative medical literature (PubMed, medical textbooks)
|
||||||
|
- Clinical guidelines and diagnostic standards
|
||||||
|
- Medical encyclopedia entries and terminology databases
|
||||||
|
|
||||||
|
- **Training Methods**:
|
||||||
|
- Supervised Fine-Tuning (SFT)
|
||||||
|
- Chain-of-Thought (CoT) guided samples
|
||||||
|
- Medical terminology alignment and safety constraints
|
||||||
|
|
||||||
|
### Stage II: Clinical Task Enhancement
|
||||||
|
|
||||||
|
**Objective**: Enhance complex case reasoning and multi-task processing capabilities
|
||||||
|
|
||||||
|
- **Data Sources**:
|
||||||
|
- Real medical records (fully anonymized)
|
||||||
|
- Outpatient and emergency records with complex multi-diagnosis samples
|
||||||
|
- Research articles and quality control cases
|
||||||
|
|
||||||
|
- **Data Augmentation Techniques**:
|
||||||
|
- Semantic paraphrasing and multi-perspective expansion
|
||||||
|
- Complex case synthesis
|
||||||
|
- Doctor-patient interaction simulation
|
||||||
|
|
||||||
|
- **Training Methods**:
|
||||||
|
- Multi-Task Learning (medical record summary, differential diagnosis, examination suggestions, etc.)
|
||||||
|
- Preference Alignment (DPO/KTO)
|
||||||
|
- Expert feedback iterative optimization
|
||||||
|
|
||||||
|
### Training Optimization Focus
|
||||||
|
|
||||||
|
- ✅ Strengthen information extraction and cross-evidence reasoning for complex cases
|
||||||
|
- ✅ Improve medical consistency and interpretability of outputs
|
||||||
|
- ✅ Optimize expression compliance and safety
|
||||||
|
- ✅ Continuous iteration through expert samples and automated evaluation
|
||||||
|
|
||||||
|
## 💡 Use Cases
|
||||||
|
|
||||||
|
### ✅ Suitable Scenarios
|
||||||
|
|
||||||
|
| Scenario | Description |
|
||||||
|
|----------|-------------|
|
||||||
|
| **Clinical Assistance** | Preliminary diagnosis suggestions, medical record writing, formatted report generation |
|
||||||
|
| **Research Support** | Literature summarization, research idea generation, data analysis assistance |
|
||||||
|
| **Quality Control** | Medical document compliance checking, clinical process quality control |
|
||||||
|
| **System Integration** | Embedded in HIS/EMR systems to provide intelligent decision support |
|
||||||
|
| **Medical Education** | Case discussions, medical knowledge Q&A, clinical reasoning training |
|
||||||
|
|
||||||
|
### 🚫 Unsuitable Scenarios
|
||||||
|
|
||||||
|
- ❌ **Cannot Replace Doctors**: Only an auxiliary tool, not a standalone diagnostic basis
|
||||||
|
- ❌ **High-Risk Operations**: Not recommended for surgical decisions or other high-risk medical operations
|
||||||
|
- ❌ **Rare Disease Limitations**: May perform poorly on rare diseases outside training data
|
||||||
|
- ❌ **Emergency Care**: Not suitable for scenarios requiring immediate decisions
|
||||||
|
|
||||||
|
## ⚠️ Limitations & Risks
|
||||||
|
|
||||||
|
### Model Limitations
|
||||||
|
|
||||||
|
1. **Understanding Bias**: Despite covering extensive medical knowledge, may still produce understanding biases or incorrect recommendations
|
||||||
|
2. **Complex Cases**: Higher risk for cases with complex conditions, severe complications, or missing information
|
||||||
|
3. **Knowledge Currency**: Medical knowledge continuously updates; training data may lag
|
||||||
|
4. **Language Limitation**: Primarily designed for Chinese medical scenarios; performance in other languages may vary
|
||||||
|
|
||||||
|
### Usage Recommendations
|
||||||
|
|
||||||
|
- ⚠️ Use in controlled environments with clinical expert review of generated results
|
||||||
|
- ⚠️ Treat model outputs as auxiliary references, not final diagnostic conclusions
|
||||||
|
- ⚠️ For sensitive cases or high-risk scenarios, expert consultation is mandatory
|
||||||
|
- ⚠️ Deployment requires internal validation, security review, and clinical testing
|
||||||
|
|
||||||
|
### Data Privacy & Compliance
|
||||||
|
|
||||||
|
- 🔒 Training data fully anonymized
|
||||||
|
- 🔒 Attention to patient privacy protection during use
|
||||||
|
- 🔒 Production deployment must comply with healthcare data security regulations (e.g., HIPAA, GDPR)
|
||||||
|
- 🔒 Local deployment recommended to avoid sensitive data transmission
|
||||||
|
|
||||||
|
## 📚 Citation
|
||||||
|
|
||||||
|
If MedGo is helpful for your research or project, please cite our work:
|
||||||
|
|
||||||
|
```bibtex
|
||||||
|
@misc{openmedzoo_2025,
|
||||||
|
author = { OpenMedZoo },
|
||||||
|
title = { MedGo (Revision 640a2e2) },
|
||||||
|
year = 2025,
|
||||||
|
url = { https://huggingface.co/OpenMedZoo/MedGo },
|
||||||
|
doi = { 10.57967/hf/7024 },
|
||||||
|
publisher = { Hugging Face }
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
## 📄 License
|
||||||
|
|
||||||
|
This project is licensed under the [Apache License 2.0](LICENSE).
|
||||||
|
|
||||||
|
**Commercial Use Notice**:
|
||||||
|
- ✅ Commercial use and modification allowed
|
||||||
|
- ✅ Original license and copyright notice must be retained
|
||||||
|
- ✅ Contact us for technical support when integrating into healthcare systems
|
||||||
|
|
||||||
|
## 🤝 Contributing
|
||||||
|
|
||||||
|
We welcome community contributions! Here's how to participate:
|
||||||
|
|
||||||
|
### Contribution Types
|
||||||
|
|
||||||
|
- 🐛 Submit bug reports
|
||||||
|
- 💡 Propose new features
|
||||||
|
- 📝 Improve documentation
|
||||||
|
- 🔧 Submit code fixes or optimizations
|
||||||
|
- 📊 Share evaluation results and use cases
|
||||||
|
|
||||||
|
|
||||||
|
## 🙏 Acknowledgments
|
||||||
|
|
||||||
|
Thanks to all contributors to the MedGo project:
|
||||||
|
|
||||||
|
- Model development and fine-tuning algorithm team
|
||||||
|
- Data annotation and quality control team
|
||||||
|
- Clinical expert guidance and review team
|
||||||
|
- Open-source community support and feedback
|
||||||
|
|
||||||
|
Special thanks to:
|
||||||
|
- [Qwen Team](https://github.com/QwenLM/Qwen) for providing excellent foundation models
|
||||||
|
- All healthcare institutions that provided data and feedback
|
||||||
|
|
||||||
|
## 📧 Contact
|
||||||
|
|
||||||
|
- **HuggingFace**: [Model Homepage](https://huggingface.co/OpenMedZoo/MedGo)
|
||||||
|
|
||||||
|
## Copyright
|
||||||
|
- Publisher: Tongji University Affiliated East Hospital — Sole Corresponding Author
|
||||||
|
- Co-developer / Technical Support: Shanghai Shuole Technology Co., Ltd.
|
||||||
|
- Contact: dongfyy@pudong.gov.cn
|
||||||
|
- Version: v1.0
|
||||||
|
- Attribution (required):
|
||||||
|
“Powered by Med-Go 32B, released by Tongji University Affiliated East Hospital (v1.0).”
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
<div align="center">
|
||||||
|
</div>
|
||||||
332
README_CN.md
Normal file
332
README_CN.md
Normal file
@@ -0,0 +1,332 @@
|
|||||||
|
# MedGo: 基于 Qwen3-32B 的医疗大模型
|
||||||
|
|
||||||
|
<div align="center">
|
||||||
|
|
||||||
|
[](https://huggingface.co/OpenMedZoo/MedGo)
|
||||||
|
[](LICENSE)
|
||||||
|
[](https://www.python.org/)
|
||||||
|
|
||||||
|
[English](./README.md) | 简体中文
|
||||||
|
|
||||||
|
</div>
|
||||||
|
|
||||||
|
|
||||||
|
## 📋 目录
|
||||||
|
|
||||||
|
- [简介](#简介)
|
||||||
|
- [模型特点](#模型特点)
|
||||||
|
- [性能评估](#性能评估)
|
||||||
|
- [快速开始](#快速开始)
|
||||||
|
- [训练细节](#训练细节)
|
||||||
|
- [使用场景](#使用场景)
|
||||||
|
- [限制与风险](#限制与风险)
|
||||||
|
- [引用](#引用)
|
||||||
|
- [许可证](#许可证)
|
||||||
|
- [贡献](#贡献)
|
||||||
|
- [联系方式](#联系方式)
|
||||||
|
|
||||||
|
## 🎯 简介
|
||||||
|
|
||||||
|
**MedGo** 是一个基于 **Qwen3-32B** 微调的通用医疗大语言模型，专为临床医学与科研场景设计。模型通过大规模多源医学语料和复杂病例数据增强进行训练，支持医学问答、病历摘要、临床推理、多轮对话和科研文本生成等多任务能力。
|
||||||
|
|
||||||
|
### 🌟 核心能力
|
||||||
|
|
||||||
|
- **📚 医学知识问答**: 基于权威医学文献和临床指南的专业问答
|
||||||
|
- **📝 病历文书生成**: 自动化病历摘要、诊断报告和医疗文书
|
||||||
|
- **🔍 临床推理**: 鉴别诊断、检查建议和治疗方案推荐
|
||||||
|
- **💬 多轮对话**: 医患交互模拟和复杂病例讨论
|
||||||
|
- **🔬 科研辅助**: 文献摘要、研究思路生成和质控审查
|
||||||
|
|
||||||
|
## ✨ 模型特点
|
||||||
|
|
||||||
|
| 特性 | 详情 |
|
||||||
|
|------|------|
|
||||||
|
| **基础架构** | Qwen3-32B |
|
||||||
|
| **参数规模** | 32B |
|
||||||
|
| **应用领域** | 临床医学、科研辅助、医疗系统集成 |
|
||||||
|
| **微调方法** | SFT + Preference Alignment (DPO/KTO) |
|
||||||
|
| **数据来源** | 权威医学文献、临床指南、真实病例（脱敏） |
|
||||||
|
| **部署方式** | 本地部署、HIS/EMR 系统集成 |
|
||||||
|
| **开源许可** | Apache 2.0 |
|
||||||
|
|
||||||
|
## 📊 性能评估
|
||||||
|
|
||||||
|
MedGo 在多项医学与综合评测基准上表现优异，在 32B 参数级别模型中具有竞争力：
|
||||||
|
|
||||||
|
### 主要基准测试结果
|
||||||
|
|
||||||
|
- **AIMedQA**: 医学问答理解
|
||||||
|
- **CME**: 临床推理评估
|
||||||
|
- **DiagnosisArena**: 诊断能力测试
|
||||||
|
- **MedQA / MedMCQA**: 医学选择题
|
||||||
|
- **PubMedQA**: 生物医学文献问答
|
||||||
|
- **MMLU-Pro**: 综合能力评估
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
**性能亮点**：
|
||||||
|
- ✅ **平均得分**: 约 70 分（32B 级别模型中表现优异）
|
||||||
|
- ✅ **优势任务**: 临床推理（DiagnosisArena、CME）和多轮医学问答
|
||||||
|
- ✅ **平衡能力**: 在医疗语义理解和多任务泛化上表现良好
|
||||||
|
|
||||||
|
|
||||||
|
## 🚀 快速开始
|
||||||
|
|
||||||
|
### 环境要求
|
||||||
|
|
||||||
|
- Python >= 3.8
|
||||||
|
- PyTorch >= 2.0
|
||||||
|
- Transformers >= 4.35.0
|
||||||
|
- CUDA >= 11.8 (GPU 推理)
|
||||||
|
|
||||||
|
### 安装
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# 克隆仓库
|
||||||
|
git clone https://github.com/OpenMedZoo/MedGo.git
|
||||||
|
cd MedGo
|
||||||
|
|
||||||
|
# 安装依赖
|
||||||
|
pip install -r requirements.txt
|
||||||
|
```
|
||||||
|
|
||||||
|
### 模型下载
|
||||||
|
|
||||||
|
从 HuggingFace 下载模型权重：
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# 使用 huggingface-cli
|
||||||
|
huggingface-cli download OpenMedZoo/MedGo --local-dir ./models/MedGo
|
||||||
|
|
||||||
|
# 或使用 git-lfs
|
||||||
|
git lfs install
|
||||||
|
git clone https://huggingface.co/OpenMedZoo/MedGo
|
||||||
|
```
|
||||||
|
|
||||||
|
### 基础推理
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||||
|
|
||||||
|
# 加载模型和分词器
|
||||||
|
model_path = "OpenMedZoo/MedGo"
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
model_path,
|
||||||
|
device_map="auto",
|
||||||
|
trust_remote_code=True,
|
||||||
|
torch_dtype="auto"
|
||||||
|
)
|
||||||
|
|
||||||
|
# 医学问答示例
|
||||||
|
messages = [
|
||||||
|
{"role": "system", "content": "你是一个专业的医疗助手，请基于医学知识回答问题。"},
|
||||||
|
{"role": "user", "content": "请解释什么是高血压，以及常见的治疗方法。"}
|
||||||
|
]
|
||||||
|
|
||||||
|
# 生成回复
|
||||||
|
inputs = tokenizer.apply_chat_template(
|
||||||
|
messages,
|
||||||
|
tokenize=True,
|
||||||
|
add_generation_prompt=True,
|
||||||
|
return_tensors="pt"
|
||||||
|
).to(model.device)
|
||||||
|
|
||||||
|
outputs = model.generate(
|
||||||
|
inputs,
|
||||||
|
max_new_tokens=512,
|
||||||
|
temperature=0.7,
|
||||||
|
top_p=0.9,
|
||||||
|
do_sample=True
|
||||||
|
)
|
||||||
|
|
||||||
|
response = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
|
||||||
|
print(response)
|
||||||
|
```
|
||||||
|
|
||||||
|
### 批量推理
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# 使用提供的推理脚本
|
||||||
|
python scripts/inference.py \
|
||||||
|
--model_path OpenMedZoo/MedGo \
|
||||||
|
--input_file examples/medical_qa.jsonl \
|
||||||
|
--output_file results/predictions.jsonl \
|
||||||
|
--batch_size 4
|
||||||
|
```
|
||||||
|
|
||||||
|
### vLLM 加速推理
|
||||||
|
|
||||||
|
```python
|
||||||
|
from vllm import LLM, SamplingParams
|
||||||
|
|
||||||
|
# 初始化 vLLM
|
||||||
|
llm = LLM(model="OpenMedZoo/MedGo", trust_remote_code=True)
|
||||||
|
sampling_params = SamplingParams(temperature=0.7, top_p=0.9, max_tokens=512)
|
||||||
|
|
||||||
|
# 批量推理
|
||||||
|
prompts = [
|
||||||
|
"请解释糖尿病的症状和治疗方法。",
|
||||||
|
"高血压患者应该注意哪些饮食事项？"
|
||||||
|
]
|
||||||
|
|
||||||
|
outputs = llm.generate(prompts, sampling_params)
|
||||||
|
for output in outputs:
|
||||||
|
print(output.outputs[0].text)
|
||||||
|
```
|
||||||
|
|
||||||
|
## 🔧 训练细节
|
||||||
|
|
||||||
|
MedGo 采用**两阶段微调策略**，兼顾通用医学知识与临床任务适配。
|
||||||
|
|
||||||
|
### 阶段 I：通识医学对齐
|
||||||
|
|
||||||
|
**目标**: 建立扎实的医学知识基础，提高问答规范性
|
||||||
|
|
||||||
|
- **数据来源**:
|
||||||
|
- 权威医学文献（PubMed、医学教科书）
|
||||||
|
- 临床指南和诊疗规范
|
||||||
|
- 医学百科条目和术语库
|
||||||
|
|
||||||
|
- **训练方法**:
|
||||||
|
- Supervised Fine-Tuning (SFT)
|
||||||
|
- Chain-of-Thought (CoT) 引导样本
|
||||||
|
- 医学术语对齐和安全性约束
|
||||||
|
|
||||||
|
### 阶段 II：临床任务增强
|
||||||
|
|
||||||
|
**目标**: 增强复杂病例推理和多任务处理能力
|
||||||
|
|
||||||
|
- **数据来源**:
|
||||||
|
- 真实病历（完全脱敏处理）
|
||||||
|
- 门急诊记录和复杂多诊断样本
|
||||||
|
- 科研文章和质控案例
|
||||||
|
|
||||||
|
- **数据增强技术**:
|
||||||
|
- 语义改写和多视角扩写
|
||||||
|
- 复杂病例合成
|
||||||
|
- 医患交互模拟
|
||||||
|
|
||||||
|
- **训练方法**:
|
||||||
|
- Multi-Task Learning（病历摘要、鉴别诊断、检查建议等）
|
||||||
|
- Preference Alignment (DPO/KTO)
|
||||||
|
- 专家反馈迭代优化
|
||||||
|
|
||||||
|
### 训练优化重点
|
||||||
|
|
||||||
|
- ✅ 强化复杂病例的信息抽取与跨证据推理
|
||||||
|
- ✅ 提升输出的医学一致性和可解释性
|
||||||
|
- ✅ 优化表达的合规性和安全性
|
||||||
|
- ✅ 通过专家样本和自动评测持续迭代
|
||||||
|
|
||||||
|
## 💡 使用场景
|
||||||
|
|
||||||
|
### ✅ 适用场景
|
||||||
|
|
||||||
|
| 场景 | 说明 |
|
||||||
|
|------|------|
|
||||||
|
| **临床辅助** | 初步诊断建议、病历书写、格式化报告生成 |
|
||||||
|
| **科研支持** | 文献摘要、研究思路生成、数据分析辅助 |
|
||||||
|
| **质控审查** | 医疗文书规范性检查、诊疗流程质控 |
|
||||||
|
| **系统集成** | 嵌入 HIS/EMR 系统，提供智能辅助决策 |
|
||||||
|
| **医学教育** | 病例讨论、医学知识问答、临床推理训练 |
|
||||||
|
|
||||||
|
### 🚫 不适用场景
|
||||||
|
|
||||||
|
- ❌ **不能替代医生**: 仅为辅助工具，不能单独作为诊断依据
|
||||||
|
- ❌ **高风险操作**: 不建议用于手术决策等高风险医疗操作
|
||||||
|
- ❌ **罕见病局限**: 对训练数据外的罕见病表现可能欠佳
|
||||||
|
- ❌ **实时急救**: 不适用于需要即时决策的急救场景
|
||||||
|
|
||||||
|
## ⚠️ 限制与风险
|
||||||
|
|
||||||
|
### 模型局限性
|
||||||
|
|
||||||
|
1. **理解偏差**: 虽已覆盖大量医学知识，仍可能出现理解偏差或错误推荐
|
||||||
|
2. **复杂病例**: 对病情复杂、并发症严重、资料缺失的病例风险较高
|
||||||
|
3. **知识时效**: 医学知识持续更新，模型训练数据可能滞后
|
||||||
|
4. **语言限制**: 主要针对中文医学场景，其他语言表现可能不佳
|
||||||
|
|
||||||
|
### 使用建议
|
||||||
|
|
||||||
|
- ⚠️ 请在受控环境中使用，并由临床专家审核生成结果
|
||||||
|
- ⚠️ 将模型输出作为辅助参考，而非最终诊断依据
|
||||||
|
- ⚠️ 对敏感病案或高风险场景，必须结合专家意见
|
||||||
|
- ⚠️ 部署前需通过内部验证、安全审查和临床测试
|
||||||
|
|
||||||
|
### 数据隐私与合规
|
||||||
|
|
||||||
|
- 🔒 训练数据已完全脱敏处理
|
||||||
|
- 🔒 使用时注意患者隐私保护
|
||||||
|
- 🔒 生产环境部署需符合医疗数据安全法规（如 HIPAA、GDPR）
|
||||||
|
- 🔒 建议在本地部署，避免敏感数据外传
|
||||||
|
|
||||||
|
## 📚 引用
|
||||||
|
|
||||||
|
如果 MedGo 对您的研究或项目有帮助，请引用我们的工作：
|
||||||
|
|
||||||
|
```bibtex
|
||||||
|
@misc{openmedzoo_2025,
|
||||||
|
author = { OpenMedZoo },
|
||||||
|
title = { MedGo (Revision 640a2e2) },
|
||||||
|
year = 2025,
|
||||||
|
url = { https://huggingface.co/OpenMedZoo/MedGo },
|
||||||
|
doi = { 10.57967/hf/7024 },
|
||||||
|
publisher = { Hugging Face }
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
## 📄 许可证
|
||||||
|
|
||||||
|
本项目采用 [Apache License 2.0](LICENSE) 开源协议。
|
||||||
|
|
||||||
|
**商业使用须知**：
|
||||||
|
- ✅ 允许商业使用和修改
|
||||||
|
- ✅ 需保留原始许可证和版权声明
|
||||||
|
- ✅ 医疗系统集成建议联系我们获取技术支持
|
||||||
|
|
||||||
|
## 🤝 贡献
|
||||||
|
|
||||||
|
我们欢迎社区贡献！以下是参与方式：
|
||||||
|
|
||||||
|
### 贡献类型
|
||||||
|
|
||||||
|
- 🐛 提交 Bug 报告
|
||||||
|
- 💡 提出新功能建议
|
||||||
|
- 📝 改进文档
|
||||||
|
- 🔧 提交代码修复或优化
|
||||||
|
- 📊 分享评测结果和使用案例
|
||||||
|
|
||||||
|
## 🙏 致谢
|
||||||
|
|
||||||
|
感谢所有参与 MedGo 项目的人员：
|
||||||
|
|
||||||
|
- 模型研发与微调算法团队
|
||||||
|
- 数据标注与质量控制团队
|
||||||
|
- 临床专家指导与审核团队
|
||||||
|
- 开源社区的支持与反馈
|
||||||
|
|
||||||
|
特别感谢：
|
||||||
|
- [Qwen Team](https://github.com/QwenLM/Qwen) 提供优秀的基础模型
|
||||||
|
- 所有提供数据和反馈的医疗机构
|
||||||
|
|
||||||
|
## 📧 联系方式
|
||||||
|
|
||||||
|
- **HuggingFace**: [模型主页](https://huggingface.co/OpenMedZoo/MedGo)
|
||||||
|
|
||||||
|
## 版权声明
|
||||||
|
|
||||||
|
- 发布单位：同济大学附属东方医院｜唯一通信作者
|
||||||
|
- 联合研发单位：上海烁乐科技有限公司（提供技术支持）
|
||||||
|
- 联系方式：dongfyy@pudong.gov.cn
|
||||||
|
- 版本：v1.0
|
||||||
|
- 署名/引用：使用或再发布时请注明来源与版本号
|
||||||
|
“Powered by Med-Go 32B, released by Tongji University Affiliated East Hospital (v1.0).”
|
||||||
|
---
|
||||||
|
|
||||||
|
<div align="center">
|
||||||
|
|
||||||
|
|
||||||
|
[⬆ 回到顶部](#medgo-基于-qwen25-32b-的医疗大模型)
|
||||||
|
|
||||||
|
</div>
|
||||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
|||||||
|
{
|
||||||
|
"</think>": 151668,
|
||||||
|
"</tool_call>": 151658,
|
||||||
|
"</tool_response>": 151666,
|
||||||
|
"<think>": 151667,
|
||||||
|
"<tool_call>": 151657,
|
||||||
|
"<tool_response>": 151665,
|
||||||
|
"<|box_end|>": 151649,
|
||||||
|
"<|box_start|>": 151648,
|
||||||
|
"<|endoftext|>": 151643,
|
||||||
|
"<|file_sep|>": 151664,
|
||||||
|
"<|fim_middle|>": 151660,
|
||||||
|
"<|fim_pad|>": 151662,
|
||||||
|
"<|fim_prefix|>": 151659,
|
||||||
|
"<|fim_suffix|>": 151661,
|
||||||
|
"<|im_end|>": 151645,
|
||||||
|
"<|im_start|>": 151644,
|
||||||
|
"<|image_pad|>": 151655,
|
||||||
|
"<|object_ref_end|>": 151647,
|
||||||
|
"<|object_ref_start|>": 151646,
|
||||||
|
"<|quad_end|>": 151651,
|
||||||
|
"<|quad_start|>": 151650,
|
||||||
|
"<|repo_name|>": 151663,
|
||||||
|
"<|video_pad|>": 151656,
|
||||||
|
"<|vision_end|>": 151653,
|
||||||
|
"<|vision_pad|>": 151654,
|
||||||
|
"<|vision_start|>": 151652
|
||||||
|
}
|
||||||
85
chat_template.jinja
Normal file
85
chat_template.jinja
Normal file
@@ -0,0 +1,85 @@
|
|||||||
|
{%- if tools %}
|
||||||
|
{{- '<|im_start|>system\n' }}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- messages[0].content + '\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||||
|
{%- for tool in tools %}
|
||||||
|
{{- "\n" }}
|
||||||
|
{{- tool | tojson }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||||
|
{%- else %}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||||
|
{%- for message in messages[::-1] %}
|
||||||
|
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||||
|
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||||
|
{%- set ns.multi_step_tool = false %}
|
||||||
|
{%- set ns.last_query_index = index %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||||
|
{%- elif message.role == "assistant" %}
|
||||||
|
{%- set content = message.content %}
|
||||||
|
{%- set reasoning_content = '' %}
|
||||||
|
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
||||||
|
{%- set reasoning_content = message.reasoning_content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- if '</think>' in message.content %}
|
||||||
|
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
||||||
|
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if loop.index0 > ns.last_query_index %}
|
||||||
|
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if message.tool_calls %}
|
||||||
|
{%- for tool_call in message.tool_calls %}
|
||||||
|
{%- if (loop.first and content) or (not loop.first) %}
|
||||||
|
{{- '\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if tool_call.function %}
|
||||||
|
{%- set tool_call = tool_call.function %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<tool_call>\n{"name": "' }}
|
||||||
|
{{- tool_call.name }}
|
||||||
|
{{- '", "arguments": ' }}
|
||||||
|
{%- if tool_call.arguments is string %}
|
||||||
|
{{- tool_call.arguments }}
|
||||||
|
{%- else %}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '}\n</tool_call>' }}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- elif message.role == "tool" %}
|
||||||
|
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||||
|
{{- '<|im_start|>user' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_response>\n' }}
|
||||||
|
{{- message.content }}
|
||||||
|
{{- '\n</tool_response>' }}
|
||||||
|
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- if add_generation_prompt %}
|
||||||
|
{{- '<|im_start|>assistant\n' }}
|
||||||
|
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||||
|
{{- '<think>\n\n</think>\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen3ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 5120,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 25600,
|
||||||
|
"max_position_embeddings": 40960,
|
||||||
|
"max_window_layers": 64,
|
||||||
|
"model_type": "qwen3",
|
||||||
|
"num_attention_heads": 64,
|
||||||
|
"num_hidden_layers": 64,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 1000000,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.52.4",
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
151645,
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"temperature": 0.6,
|
||||||
|
"top_k": 20,
|
||||||
|
"top_p": 0.95,
|
||||||
|
"transformers_version": "4.52.4"
|
||||||
|
}
|
||||||
3
main_results.png
Normal file
3
main_results.png
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:87932bc2b934dc9992d8db349cb33a2cd21dba832d7ccbdcdd358848e4a005be
|
||||||
|
size 1614572
|
||||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00014.safetensors
Normal file
3
model-00001-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:bf7ef6eca9e6d70fb55b13d86b56102644d2ed14addfefcca38dbe63498d1215
|
||||||
|
size 4932307584
|
||||||
3
model-00002-of-00014.safetensors
Normal file
3
model-00002-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3046b5b1426a7c1c037c2948bf57f3476b5886e3d1f8d33966323b266609ff0d
|
||||||
|
size 4875989696
|
||||||
3
model-00003-of-00014.safetensors
Normal file
3
model-00003-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:70d2fd458c5d83932e72f3b0f021e8c228706d368c8dda979285ff7a6514a674
|
||||||
|
size 4875989720
|
||||||
3
model-00004-of-00014.safetensors
Normal file
3
model-00004-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:364adf71d9603489ccd1a8d24539255196bb13b9a6145cad37393904c28acbdc
|
||||||
|
size 4875989752
|
||||||
3
model-00005-of-00014.safetensors
Normal file
3
model-00005-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:403d6ca7e12b373db26cb464cd9473e074b08c141264af66c898ba49824904da
|
||||||
|
size 4875989752
|
||||||
3
model-00006-of-00014.safetensors
Normal file
3
model-00006-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:15097b2f7909a6173ff92a6821f47ab4c4754e9a2591cb6d406758b5ae80500a
|
||||||
|
size 4875989752
|
||||||
3
model-00007-of-00014.safetensors
Normal file
3
model-00007-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:6723f989dfe52eae611f85a694884bfb8f30e08767339ffc7d8e2c6fb00278c1
|
||||||
|
size 4875989752
|
||||||
3
model-00008-of-00014.safetensors
Normal file
3
model-00008-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:0b213dd751e03e45e7aa965ac993792438deb8d6983eec98b7c7ba6d491a25eb
|
||||||
|
size 4875989752
|
||||||
3
model-00009-of-00014.safetensors
Normal file
3
model-00009-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:8ecb205ea9f45f531f8e64617217cf71d328ca85647e9b705a69e4979368f60b
|
||||||
|
size 4875989752
|
||||||
3
model-00010-of-00014.safetensors
Normal file
3
model-00010-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:5240fa3fa561446386dac9c135b797631cb28b1c62bb298cc319190fbe983e68
|
||||||
|
size 4875989752
|
||||||
3
model-00011-of-00014.safetensors
Normal file
3
model-00011-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:690559b5d989dd14197be2a3fc180ba12acacda89736896789e3e8abe4ec7199
|
||||||
|
size 4875989752
|
||||||
3
model-00012-of-00014.safetensors
Normal file
3
model-00012-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b0f03b2b6d4529d70c1959cdc4e1aec2e1df74aab813121cce6c4f07034ae25d
|
||||||
|
size 4875989752
|
||||||
3
model-00013-of-00014.safetensors
Normal file
3
model-00013-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:388a0f84be28c61d9c050d9f4a7c79c3712274a8487dd2e4096dae96979861df
|
||||||
|
size 4875989752
|
||||||
3
model-00014-of-00014.safetensors
Normal file
3
model-00014-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:ca4abb1e86fb27e0a982020fa5c83c773d1eca4867f4fcca39fb9ef82e8d2c0e
|
||||||
|
size 2080144040
|
||||||
714
model.safetensors.index.json
Normal file
714
model.safetensors.index.json
Normal file
@@ -0,0 +1,714 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 65524246528
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00014-of-00014.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
||||||
|
"model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.36.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.36.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.37.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.37.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.38.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.38.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
||||||
|
"model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.39.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.39.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.40.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.40.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.41.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.41.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.42.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.42.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.43.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.43.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
||||||
|
"model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.44.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.44.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.45.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.45.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.46.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.46.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.47.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.47.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.48.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.48.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
||||||
|
"model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.49.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.49.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.50.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.50.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.51.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.51.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.52.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.52.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.53.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.53.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
||||||
|
"model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.54.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.54.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.55.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.55.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.56.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.56.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.57.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.57.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.58.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.58.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
||||||
|
"model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.59.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.59.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.60.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.60.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.61.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.61.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.62.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.62.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
|
||||||
|
"model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
|
||||||
|
"model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
|
||||||
|
"model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
|
||||||
|
"model.layers.63.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.63.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
||||||
|
"model.norm.weight": "model-00014-of-00014.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"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.
240
tokenizer_config.json
Normal file
240
tokenizer_config.json
Normal file
@@ -0,0 +1,240 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": false,
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"151643": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151644": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151645": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151646": {
|
||||||
|
"content": "<|object_ref_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151647": {
|
||||||
|
"content": "<|object_ref_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151648": {
|
||||||
|
"content": "<|box_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151649": {
|
||||||
|
"content": "<|box_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151650": {
|
||||||
|
"content": "<|quad_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151651": {
|
||||||
|
"content": "<|quad_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151652": {
|
||||||
|
"content": "<|vision_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151653": {
|
||||||
|
"content": "<|vision_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151654": {
|
||||||
|
"content": "<|vision_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151655": {
|
||||||
|
"content": "<|image_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151656": {
|
||||||
|
"content": "<|video_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151657": {
|
||||||
|
"content": "<tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151658": {
|
||||||
|
"content": "</tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151659": {
|
||||||
|
"content": "<|fim_prefix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151660": {
|
||||||
|
"content": "<|fim_middle|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151661": {
|
||||||
|
"content": "<|fim_suffix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151662": {
|
||||||
|
"content": "<|fim_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151663": {
|
||||||
|
"content": "<|repo_name|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151664": {
|
||||||
|
"content": "<|file_sep|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151665": {
|
||||||
|
"content": "<tool_response>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151666": {
|
||||||
|
"content": "</tool_response>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151667": {
|
||||||
|
"content": "<think>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151668": {
|
||||||
|
"content": "</think>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"bos_token": null,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"padding_side": "left",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user