Instructions to use Cheng-1/agenttune-qwen2.5-3b-react-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Cheng-1/agenttune-qwen2.5-3b-react-lora 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, "Cheng-1/agenttune-qwen2.5-3b-react-lora")

Transformers

How to use Cheng-1/agenttune-qwen2.5-3b-react-lora with Transformers:

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

pipe = pipeline("text-generation", model="Cheng-1/agenttune-qwen2.5-3b-react-lora")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Cheng-1/agenttune-qwen2.5-3b-react-lora", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Cheng-1/agenttune-qwen2.5-3b-react-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Cheng-1/agenttune-qwen2.5-3b-react-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Cheng-1/agenttune-qwen2.5-3b-react-lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Cheng-1/agenttune-qwen2.5-3b-react-lora

SGLang

How to use Cheng-1/agenttune-qwen2.5-3b-react-lora 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 "Cheng-1/agenttune-qwen2.5-3b-react-lora" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Cheng-1/agenttune-qwen2.5-3b-react-lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Cheng-1/agenttune-qwen2.5-3b-react-lora" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Cheng-1/agenttune-qwen2.5-3b-react-lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Cheng-1/agenttune-qwen2.5-3b-react-lora with Docker Model Runner:
```
docker model run hf.co/Cheng-1/agenttune-qwen2.5-3b-react-lora
```

AgentTune: Qwen2.5-3B ReAct Agent LoRA

QLoRA fine-tuned adapter that teaches Qwen2.5-3B-Instruct multi-step agent reasoning using the ReAct (Thought → Action → Observation → Answer) framework.

Key Results

Metric	Zero-Shot	Fine-Tuned	Improvement
Task Success Rate	93.3%	100%	+6.7%
Tool Selection Accuracy	30.0%	100%	+70.0%
Exact Tool Match	30.0%	100%	+70.0%

Training Details

Method: QLoRA (4-bit NF4, double quantization)
LoRA rank / alpha: 16 / 32
Target modules: All attention + MLP projections
Training samples: 500 ReAct trajectories
Epochs: 3
Learning rate: 2e-4 (cosine schedule)
Training time: ~10 minutes on L4 GPU
Final loss: 0.419

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct")
model = PeftModel.from_pretrained(base_model, "Cheng-1/agenttune-qwen2.5-3b-react-lora")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-3B-Instruct")

Model tree for Cheng-1/agenttune-qwen2.5-3b-react-lora

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Adapter

(1270)

this model

Cheng-1
/

agenttune-qwen2.5-3b-react-lora

AgentTune: Qwen2.5-3B ReAct Agent LoRA

Key Results

Training Details

Usage

Links

Model tree for Cheng-1/agenttune-qwen2.5-3b-react-lora