Instructions to use fenyo/Qwen2.5-7B-base2instruct-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fenyo/Qwen2.5-7B-base2instruct-SFT with Transformers:

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

pipe = pipeline("text-generation", model="fenyo/Qwen2.5-7B-base2instruct-SFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fenyo/Qwen2.5-7B-base2instruct-SFT")
model = AutoModelForCausalLM.from_pretrained("fenyo/Qwen2.5-7B-base2instruct-SFT")
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 fenyo/Qwen2.5-7B-base2instruct-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fenyo/Qwen2.5-7B-base2instruct-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fenyo/Qwen2.5-7B-base2instruct-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fenyo/Qwen2.5-7B-base2instruct-SFT

SGLang

How to use fenyo/Qwen2.5-7B-base2instruct-SFT 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 "fenyo/Qwen2.5-7B-base2instruct-SFT" \
    --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": "fenyo/Qwen2.5-7B-base2instruct-SFT",
		"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 "fenyo/Qwen2.5-7B-base2instruct-SFT" \
        --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": "fenyo/Qwen2.5-7B-base2instruct-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fenyo/Qwen2.5-7B-base2instruct-SFT with Docker Model Runner:
```
docker model run hf.co/fenyo/Qwen2.5-7B-base2instruct-SFT
```

Qwen2.5-7B-base2instruct — étape SFT

Checkpoint intermédiaire (SFT seul) du pipeline base→instruct SFT → DPO → RLVR appliqué à Qwen/Qwen2.5-7B. Premier maillon : le modèle de base apprend ici le format chat (ChatML) et le suivi d'instructions par fine-tuning supervisé.

🏁 Modèle final (après DPO + RLVR) : fenyo/Qwen2.5-7B-base2instruct
🧪 Étape suivante (DPO) : fenyo/Qwen2.5-7B-base2instruct-DPO
📦 Code & recette : https://github.com/AlexandreFenyo/qwen2.5-7b-base2instruct

Entraînement

Full fine-tuning (TRL SFTTrainer), format ChatML, loss sur la réponse assistant uniquement (assistant_only_loss + balises {% generation %}), liger-kernel, packing, bf16, attention SDPA. 1 epoch, lr 5e-6 cosine, seq_len 4096. Données : allenai/tulu-3-sft-mixture (180k).

Résultats (lm-eval, backend vLLM)

étape	IFEval (prompt strict)	GSM8K (flexible)	MMLU
base Qwen2.5-7B	27.4	83.0	71.8
+ SFT (ce modèle)	44.9	77.5	69.1
+ DPO	44.7	77.1	69.9
+ RLVR	45.1	77.4	69.9

C'est le SFT qui apporte l'essentiel du gain en suivi d'instructions (IFEval 27→45). Détails et analyse : dépôt GitHub.

Usage

Format ChatML, via tokenizer.apply_chat_template. Voir l'exemple sur le modèle final.

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for fenyo/Qwen2.5-7B-base2instruct-SFT

Base model

Qwen/Qwen2.5-7B

Finetuned

(869)

this model

fenyo
/

Qwen2.5-7B-base2instruct-SFT

Qwen2.5-7B-base2instruct — étape SFT

Entraînement

Résultats (lm-eval, backend vLLM)

Usage

Model tree for fenyo/Qwen2.5-7B-base2instruct-SFT

Dataset used to train fenyo/Qwen2.5-7B-base2instruct-SFT