Instructions to use ayushnangia-sdft/qwen2.5-7b-instruct-sdft-tooluse-step-400 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ayushnangia-sdft/qwen2.5-7b-instruct-sdft-tooluse-step-400 with Transformers:

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

pipe = pipeline("text-generation", model="ayushnangia-sdft/qwen2.5-7b-instruct-sdft-tooluse-step-400")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ayushnangia-sdft/qwen2.5-7b-instruct-sdft-tooluse-step-400")
model = AutoModelForCausalLM.from_pretrained("ayushnangia-sdft/qwen2.5-7b-instruct-sdft-tooluse-step-400")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ayushnangia-sdft/qwen2.5-7b-instruct-sdft-tooluse-step-400 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ayushnangia-sdft/qwen2.5-7b-instruct-sdft-tooluse-step-400"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ayushnangia-sdft/qwen2.5-7b-instruct-sdft-tooluse-step-400",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ayushnangia-sdft/qwen2.5-7b-instruct-sdft-tooluse-step-400

SGLang

How to use ayushnangia-sdft/qwen2.5-7b-instruct-sdft-tooluse-step-400 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 "ayushnangia-sdft/qwen2.5-7b-instruct-sdft-tooluse-step-400" \
    --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": "ayushnangia-sdft/qwen2.5-7b-instruct-sdft-tooluse-step-400",
		"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 "ayushnangia-sdft/qwen2.5-7b-instruct-sdft-tooluse-step-400" \
        --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": "ayushnangia-sdft/qwen2.5-7b-instruct-sdft-tooluse-step-400",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ayushnangia-sdft/qwen2.5-7b-instruct-sdft-tooluse-step-400 with Docker Model Runner:
```
docker model run hf.co/ayushnangia-sdft/qwen2.5-7b-instruct-sdft-tooluse-step-400
```

Qwen2.5-7B-Instruct SDFT — Tool Use (Step 400)

This model is a Self-Distillation Fine-Tuned (SDFT) version of Qwen/Qwen2.5-7B-Instruct, trained on the ToolAlpaca tool-use dataset.

SDFT is an on-policy learning method from "Self-Distillation Enables Continual Learning" that acquires new skills while preserving prior capabilities, significantly reducing catastrophic forgetting compared to standard SFT.

Training Details

Parameter	Value
Base model	Qwen/Qwen2.5-7B-Instruct
Method	SDFT (On-Policy Self-Distillation)
Dataset	ToolAlpaca (4,046 training examples)
Training step	400 / 1011
Learning rate	2e-5 (cosine schedule, 10% warmup)
Batch size	32 (gradient accumulation)
Epochs	1
Precision	bf16
Max prompt length	1024
Max completion length	1024
EMA alpha	0.01
Hardware	1x NVIDIA L40S 48GB
Training time	~42 hours (full run)

Evaluation Results

Tool-Use Accuracy (ToolAlpaca test set, 68 examples)

Metric	Base Model	This Model (Step 400)
Greedy Accuracy	54.4%	47.1%
pass@1	52.6%	40.3%
pass@5	61.5%	56.2%
pass@10	64.3%	61.3%

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-400")
tokenizer = AutoTokenizer.from_pretrained("Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-400")

messages = [{"role": "user", "content": "Your tool-use prompt here"}]
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=1024)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

All Checkpoints

Step	HuggingFace
100	Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-100
200	Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-200
300	Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-300
400	Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-400
500	Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-500
600	Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-600
700	Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-700
800	Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-800
900	Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-900
1000	Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-1000
1011	Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-1011

Citation

@article{shenfeld2025selfdistillation,
  title={Self-Distillation Enables Continual Learning},
  author={Shenfeld, Idan and others},
  journal={arXiv preprint arXiv:2601.19897},
  year={2025}
}