Instructions to use FlyPig23/Qwen3-4B_Paper_Impact_code_SFT_1ep with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FlyPig23/Qwen3-4B_Paper_Impact_code_SFT_1ep with Transformers:

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

pipe = pipeline("text-generation", model="FlyPig23/Qwen3-4B_Paper_Impact_code_SFT_1ep")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FlyPig23/Qwen3-4B_Paper_Impact_code_SFT_1ep")
model = AutoModelForCausalLM.from_pretrained("FlyPig23/Qwen3-4B_Paper_Impact_code_SFT_1ep")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FlyPig23/Qwen3-4B_Paper_Impact_code_SFT_1ep with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FlyPig23/Qwen3-4B_Paper_Impact_code_SFT_1ep"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FlyPig23/Qwen3-4B_Paper_Impact_code_SFT_1ep",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FlyPig23/Qwen3-4B_Paper_Impact_code_SFT_1ep

SGLang

How to use FlyPig23/Qwen3-4B_Paper_Impact_code_SFT_1ep 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 "FlyPig23/Qwen3-4B_Paper_Impact_code_SFT_1ep" \
    --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": "FlyPig23/Qwen3-4B_Paper_Impact_code_SFT_1ep",
		"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 "FlyPig23/Qwen3-4B_Paper_Impact_code_SFT_1ep" \
        --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": "FlyPig23/Qwen3-4B_Paper_Impact_code_SFT_1ep",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FlyPig23/Qwen3-4B_Paper_Impact_code_SFT_1ep with Docker Model Runner:
```
docker model run hf.co/FlyPig23/Qwen3-4B_Paper_Impact_code_SFT_1ep
```

Qwen3-4B_Paper_Impact_code_SFT_1ep / trainer_log.jsonl

FlyPig23

Upload folder using huggingface_hub

d910f96 verified about 2 months ago

raw

history blame contribute delete

2.25 kB

	{"current_steps": 5, "total_steps": 58, "loss": 0.4234, "lr": 1.3333333333333333e-05, "epoch": 0.08620689655172414, "percentage": 8.62, "elapsed_time": "0:01:44", "remaining_time": "0:18:26"}
	{"current_steps": 10, "total_steps": 58, "loss": 0.0817, "lr": 1.983619906947144e-05, "epoch": 0.1724137931034483, "percentage": 17.24, "elapsed_time": "0:03:38", "remaining_time": "0:17:30"}
	{"current_steps": 15, "total_steps": 58, "loss": 0.0811, "lr": 1.8854560256532098e-05, "epoch": 0.25862068965517243, "percentage": 25.86, "elapsed_time": "0:05:24", "remaining_time": "0:15:31"}
	{"current_steps": 20, "total_steps": 58, "loss": 0.0808, "lr": 1.7071067811865477e-05, "epoch": 0.3448275862068966, "percentage": 34.48, "elapsed_time": "0:07:07", "remaining_time": "0:13:32"}
	{"current_steps": 25, "total_steps": 58, "loss": 0.078, "lr": 1.4647231720437687e-05, "epoch": 0.43103448275862066, "percentage": 43.1, "elapsed_time": "0:08:58", "remaining_time": "0:11:50"}
	{"current_steps": 30, "total_steps": 58, "loss": 0.0781, "lr": 1.180255037813906e-05, "epoch": 0.5172413793103449, "percentage": 51.72, "elapsed_time": "0:10:48", "remaining_time": "0:10:05"}
	{"current_steps": 35, "total_steps": 58, "loss": 0.0779, "lr": 8.79463319744677e-06, "epoch": 0.603448275862069, "percentage": 60.34, "elapsed_time": "0:12:45", "remaining_time": "0:08:22"}
	{"current_steps": 40, "total_steps": 58, "loss": 0.0772, "lr": 5.895871945472434e-06, "epoch": 0.6896551724137931, "percentage": 68.97, "elapsed_time": "0:14:27", "remaining_time": "0:06:30"}
	{"current_steps": 45, "total_steps": 58, "loss": 0.0776, "lr": 3.3687734175920505e-06, "epoch": 0.7758620689655172, "percentage": 77.59, "elapsed_time": "0:16:07", "remaining_time": "0:04:39"}
	{"current_steps": 50, "total_steps": 58, "loss": 0.0779, "lr": 1.4421872769855262e-06, "epoch": 0.8620689655172413, "percentage": 86.21, "elapsed_time": "0:17:52", "remaining_time": "0:02:51"}
	{"current_steps": 55, "total_steps": 58, "loss": 0.0776, "lr": 2.905818257394799e-07, "epoch": 0.9482758620689655, "percentage": 94.83, "elapsed_time": "0:19:36", "remaining_time": "0:01:04"}
	{"current_steps": 58, "total_steps": 58, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:21:12", "remaining_time": "0:00:00"}