初始化项目，由ModelHub XC社区提供模型
Model: NovatasticRoScript/Atomight-V2.1-0.5B-Inference Source: Original Platform
This commit is contained in:
ModelHub XC
41
.gitattributes
vendored
Normal file
41
.gitattributes
vendored
Normal file
@@ -0,0 +1,41 @@
|
|||||||
|
*.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
|
||||||
|
download[[:space:]](1).png filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OfficialBenchmarkAtomight2.1.png filter=lfs diff=lfs merge=lfs -text
|
||||||
|
1780283618807.png filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OfficialAtomight.png filter=lfs diff=lfs merge=lfs -text
|
||||||
|
1780289720666.png filter=lfs diff=lfs merge=lfs -text
|
||||||
3
OfficialAtomight.png
Normal file
3
OfficialAtomight.png
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:ad2192ff671525d5b5d1315ddaf911bffcf71574dca7e7e4cf0f469dd20f1462
|
||||||
|
size 520644
|
||||||
3
OfficialBenchmarkAtomight2.1.png
Normal file
3
OfficialBenchmarkAtomight2.1.png
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:cbfeebe890db2335a950149c0a785af6d6f84d5ce8aee0ceb7dafb2b46728e21
|
||||||
|
size 129717
|
||||||
235
README.md
Normal file
235
README.md
Normal file
@@ -0,0 +1,235 @@
|
|||||||
|
---
|
||||||
|
license: mit
|
||||||
|
tags:
|
||||||
|
- text-generation
|
||||||
|
- causal-lm
|
||||||
|
- grpo
|
||||||
|
- reasoning
|
||||||
|
- reinforcement-learning
|
||||||
|
- mini-llm
|
||||||
|
- text-generation-inference
|
||||||
|
- lm-evaluation-harness
|
||||||
|
- AtomightV2.1
|
||||||
|
datasets:
|
||||||
|
- openai/gsm8k
|
||||||
|
- openai/openai_humaneval
|
||||||
|
- cais/mmlu
|
||||||
|
- allenai/ai2_arc
|
||||||
|
- bespokelabs/Bespoke-Stratos-17k
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
metrics:
|
||||||
|
- accuracy
|
||||||
|
- exact_match
|
||||||
|
model-index:
|
||||||
|
- name: Atomight-V2.1-0.5B-Inference
|
||||||
|
results:
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: ARC-Challenge
|
||||||
|
dataset:
|
||||||
|
name: AI2 ARC-Challenge
|
||||||
|
type: allenai/ai2_arc
|
||||||
|
config: ARC-Challenge
|
||||||
|
split: test
|
||||||
|
metrics:
|
||||||
|
- name: Accuracy
|
||||||
|
type: acc
|
||||||
|
value: 0.30802
|
||||||
|
- name: Accuracy (Norm)
|
||||||
|
type: acc_norm
|
||||||
|
value: 0.33788
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: GSM8K
|
||||||
|
dataset:
|
||||||
|
name: GSM8K
|
||||||
|
type: openai/gsm8k
|
||||||
|
config: main
|
||||||
|
split: test
|
||||||
|
metrics:
|
||||||
|
- name: Exact Match (Strict)
|
||||||
|
type: exact_match
|
||||||
|
value: 0.19788
|
||||||
|
- name: Exact Match (Flexible)
|
||||||
|
type: exact_match
|
||||||
|
value: 0.32449
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: ARC-Easy
|
||||||
|
dataset:
|
||||||
|
name: AI2 ARC-Easy
|
||||||
|
type: allenai/ai2_arc
|
||||||
|
config: ARC-Easy
|
||||||
|
split: test
|
||||||
|
metrics:
|
||||||
|
- name: Accuracy
|
||||||
|
type: acc
|
||||||
|
value: 0.65446
|
||||||
|
- name: Accuracy (Norm)
|
||||||
|
type: acc_norm
|
||||||
|
value: 0.59343
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: HellaSwag
|
||||||
|
dataset:
|
||||||
|
name: HellaSwag
|
||||||
|
type: Rowan/hellaswag
|
||||||
|
split: validation
|
||||||
|
metrics:
|
||||||
|
- name: Accuracy
|
||||||
|
type: acc
|
||||||
|
value: 0.40709
|
||||||
|
- name: Accuracy (Norm)
|
||||||
|
type: acc_norm
|
||||||
|
value: 0.5235
|
||||||
|
---
|
||||||
|
|
||||||
|
# Atomight-V2.1-0.5B-Inference
|
||||||
|
|
||||||
|
<p align="center">
|
||||||
|
<img src="OfficialAtomight.png" alt="Atomight Logo" width="500" style="max-width: 100%;">
|
||||||
|
</p>
|
||||||
|
|
||||||
|
**Atomight-V2.1-0.5B-Inference** is an ultra-compact, reasoning-oriented causal language model developed under the **[Atomight Ecosystem](https://huggingface.co/NovatasticRoScript/collections)**. Currently our **best model** up-to-date. Built on a Qwen-derived 494M parameter foundation, the model has been refined using **GRPO (Group Relative Policy Optimization)** reinforcement tuning.
|
||||||
|
|
||||||
|
> [!Note]
|
||||||
|
> Use this model when you want explicit chain-of-thought before the final answer — complex debugging, multi-step planning, agentic workflows, and math- or reasoning-heavy tasks.
|
||||||
|
|
||||||
|
Despite its tiny physical footprint, Atomight-V2.1-0.5B targets highly efficient edge-device reasoning, structured text outputs, lightweight coding assistance, and rapid deployment workflows under severe compute constraints.
|
||||||
|
|
||||||
|
### Key Highlights
|
||||||
|
- **Parameter Footprint:** ~494M parameters (Loads into ~1GB VRAM at FP16).
|
||||||
|
- **Training Paradigm:** GRPO reinforcement learning focusing on high-signal reasoning vectors instead of brute-force dataset scale.
|
||||||
|
- **Edge-Optimized:** Designed specifically for low-overhead mobile, local, and browser-based inference loops (Google Colab / Kaggle native workflow).
|
||||||
|
|
||||||
|
Weighted/Imatrix Quants, and Static Quants by [mradermacher](https://huggingface.co/mradermacher) are available at:
|
||||||
|
https://huggingface.co/mradermacher/Atomight-V2.1-0.5B-Inference-i1-GGUF
|
||||||
|
https://huggingface.co/mradermacher/Atomight-V2.1-0.5B-Inference-GGUF
|
||||||
|
|
||||||
|
**NOTICE: Think tags (Chain-of-Thought reasoning) may not be working now for some reasons, but rest assured, the model's weights and structure are completely SAFE.**
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Evaluation & Benchmark Results
|
||||||
|
|
||||||
|
Official evaluations were conducted using the **EleutherAI LM Evaluation Harness** at FP16 precision.
|
||||||
|
|
||||||
|
### Core Evaluation Metrics
|
||||||
|
| Benchmark Task | Metric Typology | Atomight-V2.1-0.5B Score | Focus Domain |
|
||||||
|
| :--- | :--- | :--- | :--- |
|
||||||
|
| **ARC-Easy** | Accuracy (Normalized) | **59.34%** | Scientific Fact Retrieval |
|
||||||
|
| **HellaSwag** | Accuracy (Normalized) | **52.35%** | Commonsense Reasoning & Next-Sentence Prediction |
|
||||||
|
| **ARC-Challenge** | Accuracy (Normalized) | **33.79%** | Hard Analytical Exclusion Logic |
|
||||||
|
| **GSM8K (Flexible Extract)** | Exact Match (Regex Clean) | **32.45%** | Mathematical Thought & Resolution |
|
||||||
|
| **GSM8K (Strict)** | Exact Match (Rigid Parse) | **19.79%** | Formatted Mathematical Output |
|
||||||
|
|
||||||
|
<p align="center">
|
||||||
|
<img src="OfficialBenchmarkAtomight2.1.png" alt="Atomight V2.1 Benchmark" width="500" style="max-width: 100%;">
|
||||||
|
</p>
|
||||||
|
|
||||||
|
### Comparative Engineering Insights
|
||||||
|
|
||||||
|
* **Punching Above Weight Classes:** Atomight-V2.1-0.5B outpaces Meta's larger **Llama-3.2-1B-Instruct** on localized logic-retrieval metrics, clearing **59.3%** on ARC-Easy and **33.8%** on ARC-Challenge compared to Llama's *56.7%* and *31.8%* respectively.
|
||||||
|
* **The Reasoning Gap:** On mathematical reasoning (GSM8K), when evaluated with **Flexible Extraction parsing (32.45%)**, Atomight demonstrates higher raw mathematical accuracy than both Qwen2.5-0.5B-Instruct (*26.8%*) and Llama-3.2-1B-Instruct (*24.4%*).
|
||||||
|
* **The Formatting Note:** The delta between Atomight's Strict Math score (19.8%) and Flexible Math score (32.5%) stems from the internal reasoning tokens generated during the inference step. While the mathematical conclusion is correct nearly 1/3 of the time, the model frequently bypasses rigid formatting constraints in favor of dense thinking traces.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Quickstart: Inference Execution
|
||||||
|
|
||||||
|
Atomight utilizes system and sequence prompts to partition thinking spaces. For optimal reasoning convergence, use explicit `<thinking>` and `<answer>` encapsulation layers.
|
||||||
|
|
||||||
|
```python
|
||||||
|
import torch
|
||||||
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||||
|
|
||||||
|
model_id = "NovatasticRoScript/Atomight-V2.1-0.5B-Inference"
|
||||||
|
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
model_id,
|
||||||
|
torch_dtype=torch.float16,
|
||||||
|
device_map="auto"
|
||||||
|
)
|
||||||
|
|
||||||
|
# Structuring system guidelines for GRPO activation
|
||||||
|
messages = [
|
||||||
|
{
|
||||||
|
"role": "system",
|
||||||
|
"content": "You are a reasoning model. Think inside <thinking> and answer inside <answer>."
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"role": "user",
|
||||||
|
"content": "A farmer has 12 apples. He gives 4 to his neighbor and loses 2 on the way home. How many apples does he have left?"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
|
||||||
|
inputs = tokenizer.apply_chat_template(
|
||||||
|
messages,
|
||||||
|
tokenize=True,
|
||||||
|
add_generation_prompt=True,
|
||||||
|
return_tensors="pt"
|
||||||
|
).to("cuda")
|
||||||
|
|
||||||
|
with torch.no_grad():
|
||||||
|
outputs = model.generate(
|
||||||
|
inputs,
|
||||||
|
max_new_tokens=250,
|
||||||
|
temperature=0.01,
|
||||||
|
pad_token_id=tokenizer.eos_token_id
|
||||||
|
)
|
||||||
|
|
||||||
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
||||||
|
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 📄 Citations
|
||||||
|
|
||||||
|
@misc{shao2024deepseekmathpushinglimitsmathematical,
|
||||||
|
title={DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models},
|
||||||
|
author={Zhihong Shao and Peiyi Wang and Qihao Zhu and Junxiao Song and Daya Guo and et al.},
|
||||||
|
year={2024},
|
||||||
|
eprint={2402.03300},
|
||||||
|
archivePrefix={arXiv},
|
||||||
|
primaryClass={cs.CL},
|
||||||
|
url={https://arxiv.org/abs/2402.03300}
|
||||||
|
}
|
||||||
|
|
||||||
|
@misc{qwen_qwen25_2025,
|
||||||
|
title={Qwen2.5 Technical Report},
|
||||||
|
author={Qwen and Yang, An and Yang, Baosong and Zhang, Beichen and Hui, Binyuan and et al.},
|
||||||
|
year={2024},
|
||||||
|
eprint={2412.15115},
|
||||||
|
archivePrefix={arXiv},
|
||||||
|
primaryClass={cs.CL},
|
||||||
|
url={https://arxiv.org/abs/2412.15115}
|
||||||
|
}
|
||||||
|
|
||||||
|
@misc{eval-harness,
|
||||||
|
author={Gao, Leo and Tow, Jonathan and Abbasi, Baber and Biderman, Stella and Black, Sid and et al.},
|
||||||
|
title={A framework for few-shot language model evaluation},
|
||||||
|
month={12},
|
||||||
|
year={2023},
|
||||||
|
publisher={Zenodo},
|
||||||
|
version={v0.4.0},
|
||||||
|
doi={10.5281/zenodo.10257521},
|
||||||
|
url={https://github.com/EleutherAI/lm-evaluation-harness}
|
||||||
|
}
|
||||||
|
|
||||||
|
@article{allenai:arc,
|
||||||
|
author = {Peter Clark and Isaac Cowhey and Oren Etzioni and Tushar Khot and
|
||||||
|
Ashish Sabharwal and Carissa Schoenick and Oyvind Tafjord},
|
||||||
|
title = {Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge},
|
||||||
|
journal = {arXiv:1803.05457v1},
|
||||||
|
year = {2018},
|
||||||
|
}
|
||||||
|
|
||||||
|
@article{cobbe2021gsm8k,
|
||||||
|
title={Training Verifiers to Solve Math Word Problems},
|
||||||
|
author={Cobbe, Karl and Kosaraju, Vineet and Bavarian, Mohammad and Chen, Mark and Jun, Heewoo and Kaiser, Lukasz and Plappert, Matthias and Tworek, Jerry and Hilton, Jacob and Nakano, Reiichiro and Hesse, Christopher and Schulman, John},
|
||||||
|
journal={arXiv preprint arXiv:2110.14168},
|
||||||
|
year={2021}
|
||||||
|
}
|
||||||
54
chat_template.jinja
Normal file
54
chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
|||||||
|
{%- if tools %}
|
||||||
|
{{- '<|im_start|>system\n' }}
|
||||||
|
{%- if messages[0]['role'] == 'system' %}
|
||||||
|
{{- messages[0]['content'] }}
|
||||||
|
{%- else %}
|
||||||
|
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "\n\n# 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' }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||||
|
{%- elif message.role == "assistant" %}
|
||||||
|
{{- '<|im_start|>' + message.role }}
|
||||||
|
{%- if message.content %}
|
||||||
|
{{- '\n' + message.content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- for tool_call in message.tool_calls %}
|
||||||
|
{%- if tool_call.function is defined %}
|
||||||
|
{%- set tool_call = tool_call.function %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_call>\n{"name": "' }}
|
||||||
|
{{- tool_call.name }}
|
||||||
|
{{- '", "arguments": ' }}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{{- '}\n</tool_call>' }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- elif message.role == "tool" %}
|
||||||
|
{%- if (loop.index0 == 0) 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' }}
|
||||||
|
{%- endif %}
|
||||||
58
config.json
Normal file
58
config.json
Normal file
@@ -0,0 +1,58 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": null,
|
||||||
|
"torch_dtype": "float16",
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 896,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 4864,
|
||||||
|
"layer_types": [
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention"
|
||||||
|
],
|
||||||
|
"max_position_embeddings": 32768,
|
||||||
|
"max_window_layers": 21,
|
||||||
|
"model_type": "qwen2",
|
||||||
|
"num_attention_heads": 14,
|
||||||
|
"num_hidden_layers": 24,
|
||||||
|
"num_key_value_heads": 2,
|
||||||
|
"pad_token_id": 151665,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_parameters": {
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"rope_type": "default"
|
||||||
|
},
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"unsloth_fixed": true,
|
||||||
|
"unsloth_version": "2026.5.8",
|
||||||
|
"use_cache": false,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
|||||||
|
{
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
151645,
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"max_length": 32768,
|
||||||
|
"pad_token_id": 151665,
|
||||||
|
"repetition_penalty": 1.1,
|
||||||
|
"temperature": 0.7,
|
||||||
|
"top_k": 20,
|
||||||
|
"top_p": 0.8,
|
||||||
|
"transformers_version": "5.9.0"
|
||||||
|
}
|
||||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:abe6d64bf5bc330eeeacbb6a3ec08e7743e38870edc79961f11adbc2bc6edc09
|
||||||
|
size 988097824
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
|
||||||
|
size 11422356
|
||||||
203
tokenizer_config.json
Normal file
203
tokenizer_config.json
Normal file
@@ -0,0 +1,203 @@
|
|||||||
|
{
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"backend": "tokenizers",
|
||||||
|
"bos_token": null,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"is_local": false,
|
||||||
|
"local_files_only": false,
|
||||||
|
"model_max_length": 32768,
|
||||||
|
"pad_token": "<|PAD_TOKEN|>",
|
||||||
|
"padding_side": "left",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"151643": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"single_word": false,
|
||||||
|
"lstrip": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151644": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"single_word": false,
|
||||||
|
"lstrip": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151645": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"single_word": false,
|
||||||
|
"lstrip": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151646": {
|
||||||
|
"content": "<|object_ref_start|>",
|
||||||
|
"single_word": false,
|
||||||
|
"lstrip": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151647": {
|
||||||
|
"content": "<|object_ref_end|>",
|
||||||
|
"single_word": false,
|
||||||
|
"lstrip": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151648": {
|
||||||
|
"content": "<|box_start|>",
|
||||||
|
"single_word": false,
|
||||||
|
"lstrip": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151649": {
|
||||||
|
"content": "<|box_end|>",
|
||||||
|
"single_word": false,
|
||||||
|
"lstrip": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151650": {
|
||||||
|
"content": "<|quad_start|>",
|
||||||
|
"single_word": false,
|
||||||
|
"lstrip": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151651": {
|
||||||
|
"content": "<|quad_end|>",
|
||||||
|
"single_word": false,
|
||||||
|
"lstrip": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151652": {
|
||||||
|
"content": "<|vision_start|>",
|
||||||
|
"single_word": false,
|
||||||
|
"lstrip": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151653": {
|
||||||
|
"content": "<|vision_end|>",
|
||||||
|
"single_word": false,
|
||||||
|
"lstrip": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151654": {
|
||||||
|
"content": "<|vision_pad|>",
|
||||||
|
"single_word": false,
|
||||||
|
"lstrip": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151655": {
|
||||||
|
"content": "<|image_pad|>",
|
||||||
|
"single_word": false,
|
||||||
|
"lstrip": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151656": {
|
||||||
|
"content": "<|video_pad|>",
|
||||||
|
"single_word": false,
|
||||||
|
"lstrip": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151657": {
|
||||||
|
"content": "<tool_call>",
|
||||||
|
"single_word": false,
|
||||||
|
"lstrip": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151658": {
|
||||||
|
"content": "</tool_call>",
|
||||||
|
"single_word": false,
|
||||||
|
"lstrip": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151659": {
|
||||||
|
"content": "<|fim_prefix|>",
|
||||||
|
"single_word": false,
|
||||||
|
"lstrip": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151660": {
|
||||||
|
"content": "<|fim_middle|>",
|
||||||
|
"single_word": false,
|
||||||
|
"lstrip": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151661": {
|
||||||
|
"content": "<|fim_suffix|>",
|
||||||
|
"single_word": false,
|
||||||
|
"lstrip": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151662": {
|
||||||
|
"content": "<|fim_pad|>",
|
||||||
|
"single_word": false,
|
||||||
|
"lstrip": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151663": {
|
||||||
|
"content": "<|repo_name|>",
|
||||||
|
"single_word": false,
|
||||||
|
"lstrip": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151664": {
|
||||||
|
"content": "<|file_sep|>",
|
||||||
|
"single_word": false,
|
||||||
|
"lstrip": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151665": {
|
||||||
|
"content": "<|PAD_TOKEN|>",
|
||||||
|
"single_word": false,
|
||||||
|
"lstrip": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"special": true
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# 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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user