Instructions to use DongfuJiang/prm_qwen25_coder_version3_subsample_hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DongfuJiang/prm_qwen25_coder_version3_subsample_hf with Transformers:

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

pipe = pipeline("text-generation", model="DongfuJiang/prm_qwen25_coder_version3_subsample_hf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DongfuJiang/prm_qwen25_coder_version3_subsample_hf")
model = AutoModelForCausalLM.from_pretrained("DongfuJiang/prm_qwen25_coder_version3_subsample_hf")
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

vLLM

How to use DongfuJiang/prm_qwen25_coder_version3_subsample_hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DongfuJiang/prm_qwen25_coder_version3_subsample_hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DongfuJiang/prm_qwen25_coder_version3_subsample_hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DongfuJiang/prm_qwen25_coder_version3_subsample_hf

SGLang

How to use DongfuJiang/prm_qwen25_coder_version3_subsample_hf 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 "DongfuJiang/prm_qwen25_coder_version3_subsample_hf" \
    --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": "DongfuJiang/prm_qwen25_coder_version3_subsample_hf",
		"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 "DongfuJiang/prm_qwen25_coder_version3_subsample_hf" \
        --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": "DongfuJiang/prm_qwen25_coder_version3_subsample_hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DongfuJiang/prm_qwen25_coder_version3_subsample_hf with Docker Model Runner:
```
docker model run hf.co/DongfuJiang/prm_qwen25_coder_version3_subsample_hf
```

prm_qwen25_coder_version3_subsample_hf

This model is a fine-tuned version of Qwen/Qwen2.5-Coder-7B-Instruct on the prm_conversations_prm_version3_math+webinstructsub-mcq+webinstructsub-oe+apps+gsm_mix_ref_subsample_hf dataset. It achieves the following results on the evaluation set:

Loss: 0.1426

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: 5e-06
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 8
total_train_batch_size: 64
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.1991	0.1127	500	0.1923
0.1785	0.2253	1000	0.1767
0.1513	0.3380	1500	0.1663
0.1557	0.4506	2000	0.1581
0.1425	0.5633	2500	0.1521
0.1417	0.6759	3000	0.1473
0.148	0.7886	3500	0.1442
0.1278	0.9012	4000	0.1428

Framework versions

Transformers 4.45.0
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.3

Downloads last month: 3

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for DongfuJiang/prm_qwen25_coder_version3_subsample_hf

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-Coder-7B

Finetuned

Qwen/Qwen2.5-Coder-7B-Instruct

Finetuned

(360)

this model