Instructions to use thlurte/Qwen2.5-CodeMath-1.5B-TaskArith with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thlurte/Qwen2.5-CodeMath-1.5B-TaskArith with Transformers:

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

pipe = pipeline("text-generation", model="thlurte/Qwen2.5-CodeMath-1.5B-TaskArith")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("thlurte/Qwen2.5-CodeMath-1.5B-TaskArith")
model = AutoModelForCausalLM.from_pretrained("thlurte/Qwen2.5-CodeMath-1.5B-TaskArith", 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 thlurte/Qwen2.5-CodeMath-1.5B-TaskArith with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thlurte/Qwen2.5-CodeMath-1.5B-TaskArith"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thlurte/Qwen2.5-CodeMath-1.5B-TaskArith",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/thlurte/Qwen2.5-CodeMath-1.5B-TaskArith

SGLang

How to use thlurte/Qwen2.5-CodeMath-1.5B-TaskArith 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 "thlurte/Qwen2.5-CodeMath-1.5B-TaskArith" \
    --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": "thlurte/Qwen2.5-CodeMath-1.5B-TaskArith",
		"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 "thlurte/Qwen2.5-CodeMath-1.5B-TaskArith" \
        --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": "thlurte/Qwen2.5-CodeMath-1.5B-TaskArith",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use thlurte/Qwen2.5-CodeMath-1.5B-TaskArith with Docker Model Runner:
```
docker model run hf.co/thlurte/Qwen2.5-CodeMath-1.5B-TaskArith
```

Qwen2.5-CodeMath-1.5B-TaskArith / README.md

thlurte

Upload folder using huggingface_hub

fa7906f verified 5 days ago

preview code

Raw

History Blame Contribute Delete

1.26 kB

metadata

base_model:
  - Qwen/Qwen2.5-1.5B
  - Qwen/Qwen2.5-Math-1.5B
  - Qwen/Qwen2.5-Coder-1.5B
library_name: transformers
tags:
  - mergekit
  - merge

Qwen2.5-CodeMath-1.5B-TaskArith

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Task Arithmetic merge method using Qwen/Qwen2.5-1.5B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: Qwen/Qwen2.5-1.5B
dtype: bfloat16
merge_method: task_arithmetic
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 28]
        model: Qwen/Qwen2.5-Coder-1.5B
        parameters:
          weight: 1.0
      - layer_range: [0, 28]
        model: Qwen/Qwen2.5-Math-1.5B
        parameters:
          weight: 0.25
      - layer_range: [0, 28]
        model: Qwen/Qwen2.5-1.5B
tokenizer_source: Qwen/Qwen2.5-Coder-1.5B