Instructions to use tengfeima-ai/Qwen2.5-0.5B-Math-SFT-Concise with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tengfeima-ai/Qwen2.5-0.5B-Math-SFT-Concise with Transformers:

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

pipe = pipeline("text-generation", model="tengfeima-ai/Qwen2.5-0.5B-Math-SFT-Concise")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tengfeima-ai/Qwen2.5-0.5B-Math-SFT-Concise")
model = AutoModelForCausalLM.from_pretrained("tengfeima-ai/Qwen2.5-0.5B-Math-SFT-Concise", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tengfeima-ai/Qwen2.5-0.5B-Math-SFT-Concise with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tengfeima-ai/Qwen2.5-0.5B-Math-SFT-Concise"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tengfeima-ai/Qwen2.5-0.5B-Math-SFT-Concise",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tengfeima-ai/Qwen2.5-0.5B-Math-SFT-Concise

SGLang

How to use tengfeima-ai/Qwen2.5-0.5B-Math-SFT-Concise 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 "tengfeima-ai/Qwen2.5-0.5B-Math-SFT-Concise" \
    --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": "tengfeima-ai/Qwen2.5-0.5B-Math-SFT-Concise",
		"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 "tengfeima-ai/Qwen2.5-0.5B-Math-SFT-Concise" \
        --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": "tengfeima-ai/Qwen2.5-0.5B-Math-SFT-Concise",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tengfeima-ai/Qwen2.5-0.5B-Math-SFT-Concise with Docker Model Runner:
```
docker model run hf.co/tengfeima-ai/Qwen2.5-0.5B-Math-SFT-Concise
```

sft_concise_qwen25_0.5b

This model is a fine-tuned version of Qwen/Qwen2.5-0.5B-Instruct on the concise_sft dataset. It achieves the following results on the evaluation set:

Loss: 0.6725

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 4
total_train_batch_size: 64
total_eval_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.6735	0.3592	500	0.6793
0.6381	0.7184	1000	0.6572
0.5229	1.0776	1500	0.6521
0.521	1.4368	2000	0.6386
0.5014	1.7960	2500	0.6232
0.3465	2.1552	3000	0.6751
0.3495	2.5144	3500	0.6769
0.3564	2.8736	4000	0.6726

Framework versions

Transformers 4.57.1
Pytorch 2.4.1+cu124
Datasets 4.0.0
Tokenizers 0.22.2

Downloads last month: 8

Safetensors

Model size

0.6B params

Tensor type

BF16

Model tree for tengfeima-ai/Qwen2.5-0.5B-Math-SFT-Concise

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Finetuned

(1,180)

this model