Instructions to use qingy2024/Qwen2.5-Math-14B-Instruct-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use qingy2024/Qwen2.5-Math-14B-Instruct-Preview with Transformers:

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

pipe = pipeline("text-generation", model="qingy2024/Qwen2.5-Math-14B-Instruct-Preview")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("qingy2024/Qwen2.5-Math-14B-Instruct-Preview")
model = AutoModelForCausalLM.from_pretrained("qingy2024/Qwen2.5-Math-14B-Instruct-Preview", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use qingy2024/Qwen2.5-Math-14B-Instruct-Preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "qingy2024/Qwen2.5-Math-14B-Instruct-Preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qingy2024/Qwen2.5-Math-14B-Instruct-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/qingy2024/Qwen2.5-Math-14B-Instruct-Preview

SGLang

How to use qingy2024/Qwen2.5-Math-14B-Instruct-Preview 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 "qingy2024/Qwen2.5-Math-14B-Instruct-Preview" \
    --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": "qingy2024/Qwen2.5-Math-14B-Instruct-Preview",
		"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 "qingy2024/Qwen2.5-Math-14B-Instruct-Preview" \
        --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": "qingy2024/Qwen2.5-Math-14B-Instruct-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use qingy2024/Qwen2.5-Math-14B-Instruct-Preview with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for qingy2024/Qwen2.5-Math-14B-Instruct-Preview to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for qingy2024/Qwen2.5-Math-14B-Instruct-Preview to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for qingy2024/Qwen2.5-Math-14B-Instruct-Preview to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="qingy2024/Qwen2.5-Math-14B-Instruct-Preview",
    max_seq_length=2048,
)

Docker Model Runner
How to use qingy2024/Qwen2.5-Math-14B-Instruct-Preview with Docker Model Runner:
```
docker model run hf.co/qingy2024/Qwen2.5-Math-14B-Instruct-Preview
```

Qwen2.5-Math-14B-Instruct-Preview / README.md

Qingyun Li

Update README.md

1dae394 over 1 year ago

preview code

Raw

History Blame Contribute Delete

3.9 kB

metadata

language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - qwen2
  - trl
base_model: unsloth/qwen2.5-14b-instruct-bnb-4bit
model-index:
  - name: Qwen2.5-Math-14B-Instruct
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: HuggingFaceH4/ifeval
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 60.66
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=qingy2019/Qwen2.5-Math-14B-Instruct
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: BBH
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 47.02
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=qingy2019/Qwen2.5-Math-14B-Instruct
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: hendrycks/competition_math
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 28.47
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=qingy2019/Qwen2.5-Math-14B-Instruct
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 16.33
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=qingy2019/Qwen2.5-Math-14B-Instruct
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 19.63
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=qingy2019/Qwen2.5-Math-14B-Instruct
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 48.12
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=qingy2019/Qwen2.5-Math-14B-Instruct
          name: Open LLM Leaderboard

Uploaded model

Developed by: qingy2019
License: apache-2.0
Finetuned from model : unsloth/qwen2.5-14b-instruct-bnb-4bit

This Qwen 2.5 model was trained 2x faster with Unsloth and Huggingface's TRL library.

I fine-tuned it for 400 steps on garage-bAInd/Open-Platypus with a batch size of 3.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	36.71
IFEval (0-Shot)	60.66
BBH (3-Shot)	47.02
MATH Lvl 5 (4-Shot)	28.47
GPQA (0-shot)	16.33
MuSR (0-shot)	19.63
MMLU-PRO (5-shot)	48.12