Instructions to use jahyungu/Qwen2.5-Math-7B-Instruct-Qasper with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jahyungu/Qwen2.5-Math-7B-Instruct-Qasper with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Math-7B-Instruct")
model = PeftModel.from_pretrained(base_model, "jahyungu/Qwen2.5-Math-7B-Instruct-Qasper")

Transformers

How to use jahyungu/Qwen2.5-Math-7B-Instruct-Qasper with Transformers:

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("jahyungu/Qwen2.5-Math-7B-Instruct-Qasper", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jahyungu/Qwen2.5-Math-7B-Instruct-Qasper with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/jahyungu/Qwen2.5-Math-7B-Instruct-Qasper

SGLang

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

Docker Model Runner
How to use jahyungu/Qwen2.5-Math-7B-Instruct-Qasper with Docker Model Runner:
```
docker model run hf.co/jahyungu/Qwen2.5-Math-7B-Instruct-Qasper
```

Qwen2.5-Math-7B-Instruct-Qasper

This model is a fine-tuned version of Qwen/Qwen2.5-Math-7B-Instruct on an unknown dataset.

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: 0.0002
train_batch_size: 4
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 4
total_train_batch_size: 32
total_eval_batch_size: 16
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
lr_scheduler_warmup_ratio: 0.03
num_epochs: 3

Training results

Framework versions

PEFT 0.18.1
Transformers 4.56.0
Pytorch 2.10.0+cu130
Datasets 2.21.0
Tokenizers 0.22.2

Downloads last month: -

Model tree for jahyungu/Qwen2.5-Math-7B-Instruct-Qasper

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-Math-7B

Finetuned

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

Adapter

(321)

this model