初始化项目，由ModelHub XC社区提供模型
Model: sxnnn111/qwen3-4b-xlam-function-calling-60k Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.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
|
||||
142
README.md
Normal file
142
README.md
Normal file
@@ -0,0 +1,142 @@
|
||||
---
|
||||
base_model: Qwen/Qwen3-4B-Instruct-2507
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
- sft
|
||||
- trl
|
||||
- function-calling
|
||||
- tool-use
|
||||
license: mit
|
||||
---
|
||||
|
||||
# Qwen3-4B Function Calling (Fine-Tuned) — Merged Model
|
||||
|
||||
This is the **fully merged model** (base weights + LoRA adapter combined) — a fine-tuned version of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) for **function calling / tool use**.
|
||||
|
||||
Fine-tuned by **Prabhu Nithin Gollapudi** on the [xLAM Function Calling 60K](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k) dataset using QLoRA on an NVIDIA RTX 3060 Laptop GPU.
|
||||
|
||||
> If you prefer loading a LoRA adapter on top of the original base model, see the standalone adapter: [`prabhu-nithin/qwen3-4b-xlam-function-calling-60k-lora`](https://huggingface.co/prabhu-nithin/qwen3-4b-xlam-function-calling-60k-lora)
|
||||
|
||||
## What this model does
|
||||
|
||||
The model decides **when to call a tool** vs. answer directly. When a tool call is needed, it outputs a structured JSON payload wrapped in `<tool_call>` tags. Given the tool result back as a `<tool_response>`, it then produces a natural language final answer.
|
||||
|
||||
```
|
||||
User Query → Model → <tool_call>{"name": "fn", "arguments": {...}}</tool_call>
|
||||
↓
|
||||
Execute Python function
|
||||
↓
|
||||
<tool_response>{"result": ...}</tool_response>
|
||||
↓
|
||||
Model → Final Answer
|
||||
```
|
||||
|
||||
## Quick start
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
import torch
|
||||
import json
|
||||
|
||||
model_id = "prabhu-nithin/qwen3-4b-xlam-function-calling-60k"
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")
|
||||
|
||||
tool_definitions = [
|
||||
{
|
||||
"name": "get_weather",
|
||||
"description": "Get current weather information for a given city.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"city": {"type": "string", "description": "The city name"},
|
||||
"unit": {"type": "string", "enum": ["celsius", "fahrenheit"], "default": "celsius"}
|
||||
},
|
||||
"required": ["city"]
|
||||
}
|
||||
}
|
||||
]
|
||||
|
||||
system_prompt = f"""You are a helpful assistant.
|
||||
|
||||
# Tools
|
||||
|
||||
You may call one or more functions to assist with the user query.
|
||||
|
||||
You are provided with function signatures within <tools></tools> XML tags:
|
||||
<tools>
|
||||
{json.dumps(tool_definitions, indent=2)}
|
||||
</tools>
|
||||
|
||||
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
|
||||
<tool_call>
|
||||
{{"name": "<function-name>", "arguments": <args-json-object>}}
|
||||
</tool_call>"""
|
||||
|
||||
messages = [
|
||||
{"role": "system", "content": system_prompt},
|
||||
{"role": "user", "content": "What's the weather like in Paris?"}
|
||||
]
|
||||
|
||||
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=512, temperature=0.7, top_p=0.8, top_k=20)
|
||||
print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
|
||||
```
|
||||
|
||||
## Training procedure
|
||||
|
||||
[](https://wandb.ai/prabhu-nithin-gollapudi-university-of-erlangen-nuremberg/qwen3-4b-function-calling/runs/7mc7otov)
|
||||
|
||||
This model was trained with **SFT (Supervised Fine-Tuning)** using **QLoRA** (4-bit quantization + LoRA adapters). Training took approximately **18 hours** on an NVIDIA RTX 3060 Laptop GPU.
|
||||
|
||||
### Dataset
|
||||
|
||||
- **Source**: [Salesforce/xlam-function-calling-60k](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k)
|
||||
- **Split**: 95% train / 5% eval
|
||||
- **Format**: Converted to Qwen3's chat template with `<tool_call>` / `<tool_response>` tokens
|
||||
|
||||
### Hyperparameters
|
||||
|
||||
| Parameter | Value |
|
||||
|-----------|-------|
|
||||
| Base model | Qwen/Qwen3-4B-Instruct-2507 |
|
||||
| Quantization | 4-bit (QLoRA) |
|
||||
| LoRA rank (`r`) | 16 |
|
||||
| LoRA alpha | 32 |
|
||||
| LoRA dropout | 0.05 |
|
||||
| LoRA target modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
|
||||
| Epochs | 3 |
|
||||
| Learning rate | 2e-4 |
|
||||
| LR scheduler | cosine |
|
||||
| Warmup ratio | 0.05 |
|
||||
| Batch size (per device) | 1 |
|
||||
| Gradient accumulation steps | 8 (effective batch size = 8) |
|
||||
| Weight decay | 0.01 |
|
||||
| Optimizer | paged_adamw_8bit |
|
||||
| Max sequence length | 2048 |
|
||||
| Precision | bf16 |
|
||||
|
||||
### Hardware
|
||||
|
||||
| Setting | Value |
|
||||
|---------|-------|
|
||||
| GPU | NVIDIA RTX 3060 Laptop |
|
||||
| VRAM | ~8 GB used (QLoRA 4-bit) |
|
||||
| Training time | ~18 hours |
|
||||
|
||||
### Framework versions
|
||||
|
||||
- TRL: 0.29.0
|
||||
- Transformers: 5.3.0
|
||||
- Pytorch: 2.5.1+cu121
|
||||
- Datasets: 4.6.1
|
||||
- Tokenizers: 0.22.2
|
||||
|
||||
## License
|
||||
|
||||
- **Code**: MIT License
|
||||
- **Base Model**: [Apache 2.0](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507)
|
||||
- **Dataset**: [CC-BY-4.0](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k)
|
||||
61
chat_template.jinja
Normal file
61
chat_template.jinja
Normal file
@@ -0,0 +1,61 @@
|
||||
{%- 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 %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content = message.content %}
|
||||
{%- else %}
|
||||
{%- set content = '' %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- 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' }}
|
||||
{{- 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 %}
|
||||
86
config.json
Normal file
86
config.json
Normal file
@@ -0,0 +1,86 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": null,
|
||||
"dtype": "float32",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 9728,
|
||||
"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",
|
||||
"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": 262144,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"quantization_config": {
|
||||
"_load_in_4bit": true,
|
||||
"_load_in_8bit": false,
|
||||
"bnb_4bit_compute_dtype": "bfloat16",
|
||||
"bnb_4bit_quant_storage": "uint8",
|
||||
"bnb_4bit_quant_type": "nf4",
|
||||
"bnb_4bit_use_double_quant": true,
|
||||
"llm_int8_enable_fp32_cpu_offload": false,
|
||||
"llm_int8_has_fp16_weight": false,
|
||||
"llm_int8_skip_modules": null,
|
||||
"llm_int8_threshold": 6.0,
|
||||
"load_in_4bit": true,
|
||||
"load_in_8bit": false,
|
||||
"quant_method": "bitsandbytes"
|
||||
},
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 5000000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.3.0",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "5.3.0"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5de5857f148c4866e887ef182d57e1b3ada3d14831c2e0e224e07154a83efd57
|
||||
size 3431444696
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
||||
size 11422650
|
||||
29
tokenizer_config.json
Normal file
29
tokenizer_config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_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|>"
|
||||
],
|
||||
"is_local": false,
|
||||
"model_max_length": 1010000,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
Reference in New Issue
Block a user