Instructions to use canbingol/qwen2.5-3B-Instruct-conversational-tool-call with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use canbingol/qwen2.5-3B-Instruct-conversational-tool-call with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct")
model = PeftModel.from_pretrained(base_model, "canbingol/qwen2.5-3B-Instruct-conversational-tool-call")

Transformers

How to use canbingol/qwen2.5-3B-Instruct-conversational-tool-call with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="canbingol/qwen2.5-3B-Instruct-conversational-tool-call")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("canbingol/qwen2.5-3B-Instruct-conversational-tool-call", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use canbingol/qwen2.5-3B-Instruct-conversational-tool-call with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "canbingol/qwen2.5-3B-Instruct-conversational-tool-call"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "canbingol/qwen2.5-3B-Instruct-conversational-tool-call",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/canbingol/qwen2.5-3B-Instruct-conversational-tool-call

SGLang

How to use canbingol/qwen2.5-3B-Instruct-conversational-tool-call with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "canbingol/qwen2.5-3B-Instruct-conversational-tool-call" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "canbingol/qwen2.5-3B-Instruct-conversational-tool-call",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "canbingol/qwen2.5-3B-Instruct-conversational-tool-call" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "canbingol/qwen2.5-3B-Instruct-conversational-tool-call",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use canbingol/qwen2.5-3B-Instruct-conversational-tool-call with Docker Model Runner:
```
docker model run hf.co/canbingol/qwen2.5-3B-Instruct-conversational-tool-call
```

qwen2.5-3B-Instruct-conversational-tool-call

This repository provides a LoRA fine-tuned adapter for Qwen/Qwen2.5-3B-Instruct, optimized specifically for multi-turn conversational tool-calling and function-execution accuracy.

Benchmark Results

Evaluation across standard tool-calling benchmark categories compared against the base model:

Model	simple_python	multiple	parallel	parallel_multiple	irrelevance
Qwen2.5-3B-Instruct (Base)	92.00%	88.50%	79.00%	75.50%	72.08%
canbingol/qwen2.5-3B-Instruct-conversational-tool-call	93.75%	92.50%	82.50%	77.50%	81.25%

Key Takeaways:

Consistent improvements across single, multiple, and parallel tool calling scenarios.
Significant reduction in false tool triggers with 81.25% accuracy on irrelevance detection (+9.17% over base).

Dataset

Dataset: Salesforce/APIGen-MT-5k
Preprocessing: Formatted via the model's native chat template and filtered to a maximum sequence length of 8,500 tokens.
Splits:
- Train: 4,291 samples
- Test: 469 samples

Training Details

Method: LoRA (PEFT)
Epochs: 1 (67 steps)
Effective Batch Size: 64 (Batch size per device: 2, Gradient Accumulation Steps: 32)
Learning Rate: 2e-4 (Linear schedule)
Optimizer: AdamW Torch Fused
Final Validation Loss: 0.2295

Quickstart

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model_id = "Qwen/Qwen2.5-3B-Instruct"
adapter_id = "canbingol/qwen2.5-3B-Instruct-conversational-tool-call"

tokenizer = AutoTokenizer.from_pretrained(base_model_id)
base_model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
model = PeftModel.from_pretrained(base_model, adapter_id)

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_current_weather",
            "description": "Get the current weather for a given location.",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {"type": "string", "description": "City and state/country"}
                },
                "required": ["location"]
            }
        }
    }
]

messages = [{"role": "user", "content": "What's the weather like in Istanbul right now?"}]
prompt = tokenizer.apply_chat_template(messages, tools=tools, add_generation_prompt=True, tokenize=False)

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))