Instructions to use pkuAI4M/QwenLeanSFT_0326 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pkuAI4M/QwenLeanSFT_0326 with Transformers:

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

pipe = pipeline("text-generation", model="pkuAI4M/QwenLeanSFT_0326")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pkuAI4M/QwenLeanSFT_0326")
model = AutoModelForCausalLM.from_pretrained("pkuAI4M/QwenLeanSFT_0326", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pkuAI4M/QwenLeanSFT_0326 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pkuAI4M/QwenLeanSFT_0326"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pkuAI4M/QwenLeanSFT_0326",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pkuAI4M/QwenLeanSFT_0326

SGLang

How to use pkuAI4M/QwenLeanSFT_0326 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 "pkuAI4M/QwenLeanSFT_0326" \
    --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": "pkuAI4M/QwenLeanSFT_0326",
		"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 "pkuAI4M/QwenLeanSFT_0326" \
        --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": "pkuAI4M/QwenLeanSFT_0326",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pkuAI4M/QwenLeanSFT_0326 with Docker Model Runner:
```
docker model run hf.co/pkuAI4M/QwenLeanSFT_0326
```

QwenLeanSFT_0326 / README.md

WhiteGiverPlus

Upload folder using huggingface_hub

49de29c verified over 1 year ago

preview code

Raw History Blame Contribute Delete

1.41 kB

	---
	library_name: transformers
	license: other
	base_model: Qwen/Qwen2.5-7B
	tags:
	- llama-factory
	- full
	- generated_from_trainer
	model-index:
	- name: LeanCoT_qwen2.5_7B_sft
	results: []
	---
	<!-- This model card has been generated automatically according to the information the Trainer had access to. You
	should probably proofread and complete it, then remove this comment. -->

	# LeanCoT_qwen2.5_7B_sft

	This model is a fine-tuned version of [/AI4M/users/qzh/dotLLM/LLaMA-Factory/saves/LeanCoT_qwen2_5_7B_pt](https://huggingface.co//AI4M/users/qzh/dotLLM/LLaMA-Factory/saves/LeanCoT_qwen2_5_7B_pt) on the leanwkbk_sft and the fake_lean_cot datasets.

	## 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: 3e-05
	- train_batch_size: 16
	- eval_batch_size: 8
	- seed: 42
	- distributed_type: multi-GPU
	- num_devices: 8
	- gradient_accumulation_steps: 4
	- total_train_batch_size: 512
	- total_eval_batch_size: 64
	- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
	- lr_scheduler_type: cosine
	- lr_scheduler_warmup_ratio: 0.05
	- num_epochs: 2.0

	### Training results

	### Framework versions

	- Transformers 4.45.0
	- Pytorch 2.5.1+cu124
	- Datasets 2.21.0
	- Tokenizers 0.20.3