初始化项目，由ModelHub XC社区提供模型
Model: hbx/JustRL-Nemotron-1.5B 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
|
||||||
|
assets/fig1_aime24_curves_added.png filter=lfs diff=lfs merge=lfs -text
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
184
README.md
Normal file
184
README.md
Normal file
@@ -0,0 +1,184 @@
|
|||||||
|
---
|
||||||
|
base_model:
|
||||||
|
- nvidia/OpenMath-Nemotron-1.5B
|
||||||
|
datasets:
|
||||||
|
- BytedTsinghua-SIA/DAPO-Math-17k
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
library_name: transformers
|
||||||
|
license: apache-2.0
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
---
|
||||||
|
|
||||||
|
<div align="center">
|
||||||
|
<span style="font-family: default; font-size: 1.5em;">JustRL: Simplicity at Scale</span>
|
||||||
|
<div>
|
||||||
|
🚀 Competitive RL Performance Without Complex Techniques 🌟
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
<div align="center" style="line-height: 1;">
|
||||||
|
<a href="https://github.com/thunlp/JustRL" style="margin: 2px;">
|
||||||
|
<img alt="Code" src="https://img.shields.io/badge/GitHub-100000?style=for-the-badge&logo=github&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
|
||||||
|
</a>
|
||||||
|
<a href="https://huggingface.co/collections/hbx/justrl" style="margin: 2px;">
|
||||||
|
<img alt="Hugging Face" src="https://img.shields.io/badge/JustRL-fcd022?style=for-the-badge&logo=huggingface&logoColor=000&labelColor" style="display: inline-block; vertical-align: middle;"/>
|
||||||
|
</a>
|
||||||
|
<a href="https://relieved-cafe-fe1.notion.site/JustRL-Scaling-a-1-5B-LLM-with-a-Simple-RL-Recipe-24f6198b0b6b80e48e74f519bfdaf0a8" target="_blank" style="margin: 2px;">
|
||||||
|
<img alt="Notion" src="https://img.shields.io/badge/Notion-%23000000.svg?style=for-the-badge&logo=notion&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
|
||||||
|
</a>
|
||||||
|
<a href="https://arxiv.org/abs/2512.16649" style="margin: 2px;">
|
||||||
|
<img alt="Paper" src="https://img.shields.io/badge/Paper-2512.16649-b31b1b.svg" style="display: inline-block; vertical-align: middle;"/>
|
||||||
|
</a>
|
||||||
|
<a href="https://x.com/HBX_hbx/status/1988474153436090776" style="margin: 2px;">
|
||||||
|
<img alt="Paper" src="https://img.shields.io/badge/X-000000?style=for-the-badge&logo=x&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
|
||||||
|
</a>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
## Overview
|
||||||
|
|
||||||
|
**JustRL** demonstrates that competitive reinforcement learning performance for small language models doesn't require complex multi-stage pipelines or dynamic schedules. Using a minimal recipe with single-stage training and fixed hyperparameters, we achieve state-of-the-art results on mathematical reasoning tasks.
|
||||||
|
|
||||||
|
We release two models:
|
||||||
|
- [**JustRL-DeepSeek-1.5B**](https://huggingface.co/hbx/JustRL-DeepSeek-1.5B): Trained from DeepSeek-R1-Distill-Qwen-1.5B
|
||||||
|
- [**JustRL-Nemotron-1.5B**](https://huggingface.co/hbx/JustRL-Nemotron-1.5B): Trained from OpenMath-Nemotron-1.5B
|
||||||
|
|
||||||
|
Both models use identical hyperparameters without per-model tuning, demonstrating the robustness of our approach.
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
## Key Highlights
|
||||||
|
|
||||||
|
✨ **Simplicity**: Single-stage training with fixed hyperparameters, without multi-stage pipelines or dynamic schedules
|
||||||
|
|
||||||
|
📈 **Stability**: Smooth, monotonic improvement over 4,000+ training steps without collapses or oscillations
|
||||||
|
|
||||||
|
🎯 **Performance**: State-of-the-art results at 1.5B scale, matching or exceeding more complex approaches
|
||||||
|
|
||||||
|
💰 **Efficiency**: Comparable or better performance with 2× less compute than multi-stage methods
|
||||||
|
|
||||||
|
🔓 **Open**: Complete evaluation scripts, and model weights released
|
||||||
|
|
||||||
|
## Performance
|
||||||
|
|
||||||
|
### JustRL-DeepSeek-1.5B (Based on DeepSeek-R1-Distill-Qwen-1.5B)
|
||||||
|
|
||||||
|
| Model | AIME24 (@32) | AIME25 (@32) | AMC23 (@32) | MATH-500 (@4) | Minerva (@4) | OlympiadBench (@4) | HMMT25 (@32) | BRUMO25 (@32) | CMIMC25 (@32) | Avg |
|
||||||
|
| ------------------------ | ------------ | ------------ | ----------- | ------------- | ------------ | ------------------ | ------------ | ------------- | ------------- | --------- |
|
||||||
|
| DeepSeek-R1-Distill-1.5B | 29.90 | 22.40 | 63.82 | 84.90 | 34.65 | 45.95 | 13.44 | 30.94 | 12.89 | 37.65 |
|
||||||
|
| DeepScaleR-1.5B-Preview | 40.21 | 28.65 | 73.83 | 89.30 | 39.34 | 52.79 | 18.96 | 40.00 | 21.00 | 44.88 |
|
||||||
|
| ProRL-V2 | 51.87 | 35.73 | 88.75 | 92.00 | 49.03 | 67.84 | 19.38 | 47.29 | **25.86** | 53.08 |
|
||||||
|
| BroRL | **57.50** | 36.88 | / | **92.14** | 49.08 | 61.54 | / | / | / | / |
|
||||||
|
| JustRL-DeepSeek-1.5B | 52.60 | **38.75** | **91.02** | 91.65 | **51.47** | **67.99** | **21.98** | **52.71** | 25.63 | **54.87** |
|
||||||
|
|
||||||
|
Besides, the real question is whether our simplicity comes at a computational cost. It doesn't. We match half of ProRL-V2's compute budget while using a single-stage recipe with fixed hyperparameters. BroRL requires 4.9× more compute by increasing rollouts to 512 per example, essentially exhaustively exploring the solution space. Our approach achieves competitive performance without this computational overhead.
|
||||||
|
|
||||||
|
### JustRL-Nemotron-1.5B (Based on OpenMath-Nemotron-1.5B)
|
||||||
|
|
||||||
|
| Model | AIME24 (@32) | AIME25 (@32) | AMC23 (@32) | MATH-500 (@4) | Minerva (@4) | OlympiadBench (@4) | HMMT25 (@32) | BRUMO25 (@32) | CMIMC25 (@32) | Avg |
|
||||||
|
| ---------------------- | ------------ | ------------ | ----------- | ------------- | ------------ | ------------------ | ------------ | ------------- | ------------- | --------- |
|
||||||
|
| OpenMath-Nemotron-1.5B | 58.75 | 48.44 | 90.55 | 92.40 | 26.93 | 71.70 | 30.10 | 61.67 | 30.08 | 56.74 |
|
||||||
|
| QUESTA-Nemotron-1.5B | **71.56** | 62.08 | 93.44 | 92.95 | **32.08** | 72.28 | **40.94** | **67.50** | 41.48 | 63.81 |
|
||||||
|
| JustRL-Nemotron-1.5B | 69.69 | **62.92** | **96.02** | **94.15** | 30.24 | **76.59** | 40.63 | 66.88 | **41.72** | **64.32** |
|
||||||
|
|
||||||
|
We achieve 64.32% average, slightly outperforming QuestA's 63.81% and leading on five of nine benchmarks. The gap is narrow, which makes sense—both approaches are pushing the boundaries of what's achievable at 1.5B scale. The key difference is in how we get there. We use 2× less compute while achieving slightly better average performance without designing a complex curriculum as used in QuestA.
|
||||||
|
|
||||||
|
## Training Recipe
|
||||||
|
|
||||||
|
Our approach is deliberately minimal:
|
||||||
|
|
||||||
|
**Core Algorithm**: Standard GRPO with binary outcome rewards
|
||||||
|
|
||||||
|
- **Reward**: Simple DAPO verifier (string-matching, no SymPy)
|
||||||
|
- **Training**: Single-stage, no curriculum or stage transitions
|
||||||
|
- **Hyperparameters**: Fixed throughout (no adaptive schedules)
|
||||||
|
- **Data**: DAPO-Math-17k without filtering or dynamic sampling
|
||||||
|
- **Length Control**: 16K context cap (no explicit penalties)
|
||||||
|
- **Stabilization**: Only "clip higher" for gradient stability
|
||||||
|
|
||||||
|
Detail hyperparameters and comparisons on training techniques with other methods can refer to our [paper](https://arxiv.org/abs/2512.16649).
|
||||||
|
|
||||||
|
## Training Data
|
||||||
|
|
||||||
|
We train on [DAPO-Math-17k](https://huggingface.co/datasets/BytedTsinghua-SIA/DAPO-Math-17k), a curated dataset of mathematical problems. **No offline difficulty filtering or online dynamic sampling is used.**
|
||||||
|
|
||||||
|
## Usage
|
||||||
|
|
||||||
|
### Basic Inference
|
||||||
|
```python
|
||||||
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||||
|
|
||||||
|
model_name = "hbx/JustRL-Nemotron-1.5B" # or JustRL-DeepSeek-1.5B
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
model_name,
|
||||||
|
torch_dtype="auto",
|
||||||
|
device_map="auto"
|
||||||
|
)
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||||
|
|
||||||
|
prompt = """<problem>
|
||||||
|
|
||||||
|
Please reason step by step, and put your final answer within \\boxed{}."""
|
||||||
|
|
||||||
|
messages = [{"role": "user", "content": prompt}]
|
||||||
|
text = tokenizer.apply_chat_template(
|
||||||
|
messages,
|
||||||
|
tokenize=False,
|
||||||
|
add_generation_prompt=True
|
||||||
|
)
|
||||||
|
|
||||||
|
inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
||||||
|
outputs = model.generate(
|
||||||
|
**inputs,
|
||||||
|
max_new_tokens=16384,
|
||||||
|
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 with vLLM
|
||||||
|
```python
|
||||||
|
from vllm import LLM, SamplingParams
|
||||||
|
|
||||||
|
llm = LLM(
|
||||||
|
model="hbx/JustRL-Nemotron-1.5B",
|
||||||
|
tensor_parallel_size=1,
|
||||||
|
max_model_len=32768
|
||||||
|
)
|
||||||
|
|
||||||
|
sampling_params = SamplingParams(
|
||||||
|
temperature=0.7,
|
||||||
|
top_p=0.9,
|
||||||
|
max_tokens=16384,
|
||||||
|
)
|
||||||
|
|
||||||
|
problems = [...] # Your list of problems
|
||||||
|
responses = llm.generate(problems, sampling_params)
|
||||||
|
```
|
||||||
|
|
||||||
|
## Reproduction
|
||||||
|
|
||||||
|
We provide evaluation scripts based on [POLARIS](https://github.com/ChenxinAn-fdu/POLARIS), the evaluation script is [here](https://github.com/thunlp/JustRL).
|
||||||
|
|
||||||
|
## Citation
|
||||||
|
|
||||||
|
```bibtex
|
||||||
|
@article{he2025justrl,
|
||||||
|
title={JustRL: Scaling a 1.5 B LLM with a Simple RL Recipe},
|
||||||
|
author={He, Bingxiang and Qu, Zekai and Liu, Zeyuan and Chen, Yinghao and Zuo, Yuxin and Qian, Cheng and Zhang, Kaiyan and Chen, Weize and Xiao, Chaojun and Cui, Ganqu and others},
|
||||||
|
journal={arXiv preprint arXiv:2512.16649},
|
||||||
|
year={2025}
|
||||||
|
}
|
||||||
|
```
|
||||||
3
assets/fig1_aime24_curves_added.png
Normal file
3
assets/fig1_aime24_curves_added.png
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:55e10fc37dbdee38f23dccfa144a6cf4fcadb6b87192927d4561e685ff15d482
|
||||||
|
size 395136
|
||||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 1536,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 8960,
|
||||||
|
"max_position_embeddings": 131072,
|
||||||
|
"max_window_layers": 21,
|
||||||
|
"model_type": "qwen2",
|
||||||
|
"num_attention_heads": 12,
|
||||||
|
"num_hidden_layers": 28,
|
||||||
|
"num_key_value_heads": 2,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 500000.0,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.51.3",
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"transformers_version": "4.47.1"
|
||||||
|
}
|
||||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b324dd08c79397c9c651511f75573d795716ecc0ea35f16fdc31b33dca0aa19c
|
||||||
|
size 3554214752
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||||
|
size 11421896
|
||||||
208
tokenizer_config.json
Normal file
208
tokenizer_config.json
Normal file
@@ -0,0 +1,208 @@
|
|||||||
|
{
|
||||||
|
"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
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"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,
|
||||||
|
"chat_template": "{%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}\n{%- else %}\n {{- '<|im_start|>system\n<|im_end|>\n' }}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == 'user') or (message.role == 'system' and not loop.first) or (message.role == 'assistant') %}\n {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' }}\n{%- endif %}",
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"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