Downloads · 30 days
24
4% of all-time downloads
icecee/Qwen3.5-9B-Opus-S1M
Qwen3.5-9B-Opus-S1M is a text generation model from icecee. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
Downloads · 30 days
24
4% of all-time downloads
All-time downloads
567
Public
Parameters
9.7B
19.3 GB on disk
Likes
3
Public
Click a slice to open those files.
.safetensors19.3 GB · 100%
How the weights are stored.
BF169.7B · 100%
From the Hugging Face model README
基于 Qwen3.5-9B-Base 微调的工具调用 / Agent 模型。
使用 Unsloth + TRL 框架,在 100k 中英双语工具调用数据上进行 LoRA SFT,让 Base 模型具备结构化函数调用能力。
本项目目的是探索和开发 Qwen3.5 dense 模型在 Agentic 能力上的潜力。
该模型只是第一阶段 SFT 的阶段模型,RL 训练的模型还在训练中,后续会逐渐提供
| 项目 | 内容 |
|---|---|
| 基础模型 | Qwen/Qwen3.5-9B-Base |
| 微调方法 | LoRA (r=32, alpha=64) |
| 训练数据 | 100,366 条去重样本(90k 训练 / 10k 验证) |
| 最大序列长度 | 4096 |
| 训练步数 | 2000 |
| 优化器 | AdamW 8-bit |
| 学习率 | 2e-5 (cosine schedule) |
从 7 个公开数据集统一转换,覆盖中英双语工具调用场景:
| 数据集 | 数量 | 语言 | 类型 |
|---|---|---|---|
| Deepexi/function-calling-small | 24,608 | 中文 | 阿里云 API 函数调用 |
| llamafactory/glaive_toolcall_zh | 1,000 | 中文 | 工具调用多轮对话 |
| hiyouga/glaive-function-calling-v2-sharegpt | 100,561 | 英文 | 函数调用 (ShareGPT) |
| NousResearch/hermes-function-calling-v1 | 1,893 | 英文 | Hermes 工具调用 |
| tryumanshow/ToolACE-Qwen-cleaned | 10,547 | 英文 | ToolACE (Qwen 格式) |
| nohurry/Opus-4.6-Reasoning-3000x-filtered | 2,308 | 英文 | Claude Opus 推理蒸馏 |
| bellfire/openclaw-coder-dataset | 7,203 | 英文 | Agent 编排 |
其中 62.5% 含结构化工具定义,37.5% 为纯文本对话/推理。
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "icecee/Qwen3.5-9B-Tool-Calling"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
tools = [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get current weather for a city",
"parameters": {
"type": "object",
"properties": {
"city": {"type": "string", "description": "City name"}
},
"required": ["city"]
}
}
}
]
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "What's the weather in Tokyo?"}
]
text = tokenizer.apply_chat_template(messages, tools=tools, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True))
可通过训练仓库的 scripts/export_gguf.py 导出 GGUF 格式后使用:
python scripts/export_gguf.py --model_dir ./output/merged_bf16
所有数据统一为 TRL 兼容的 JSONL 格式,通过 tokenizer.apply_chat_template() 自动转为 Qwen3.5 原生工具调用格式:
{
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "What's the weather in Tokyo?"},
{"role": "assistant", "content": null, "tool_calls": [
{"type": "function", "function": {"name": "get_weather", "arguments": {"city": "Tokyo"}}}
]},
{"role": "tool", "content": "{\"temp\": 22}", "name": "get_weather"},
{"role": "assistant", "content": "The weather in Tokyo is 22°C."}
],
"tools": [
{"type": "function", "function": {"name": "get_weather", "description": "Get weather info", "parameters": {"type": "object", "properties": {"city": {"type": "string"}}, "required": ["city"]}}}
]
}
Qwen3.5-9B-Base 采用混合架构(非标准 Transformer):
<|im_start|>, <|im_end|>)已预训练,适合 LoRA 微调完整训练代码、数据准备脚本和 Colab Notebook:
👉 FuzzyFade/qwen35-tool-calling-sft
支持 Colab 一键训练(T4 免费 GPU 可用)。
LoRA rank: 32
LoRA alpha: 64
Target modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Gradient checkpointing: Unsloth optimized
Effective batch size: 16
训练代码:MIT
基础模型遵循 Qwen License,各数据集有独立许可证。