Instructions to use haoyuw/Qwen2.5-1.5B-Math-Instruct-LIMO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use haoyuw/Qwen2.5-1.5B-Math-Instruct-LIMO with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("haoyuw/Qwen2.5-1.5B-Math-Instruct-LIMO")
model = AutoModelForCausalLM.from_pretrained("haoyuw/Qwen2.5-1.5B-Math-Instruct-LIMO", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use haoyuw/Qwen2.5-1.5B-Math-Instruct-LIMO with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/haoyuw/Qwen2.5-1.5B-Math-Instruct-LIMO

SGLang

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

Docker Model Runner
How to use haoyuw/Qwen2.5-1.5B-Math-Instruct-LIMO with Docker Model Runner:
```
docker model run hf.co/haoyuw/Qwen2.5-1.5B-Math-Instruct-LIMO
```

haoyuw commited on Mar 8, 2025

Commit

ca6d0ad

verified ·

1 Parent(s): 71e1c37

Training in progress, step 400

Browse files

Files changed (3) hide show

README.md +4 -5
model.safetensors +1 -1
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -1,17 +1,16 @@
 ---
 base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
 library_name: transformers
-model_name: Qwen2.5-1.5B-Math-Instruct-LIMO
 tags:
 - generated_from_trainer
-- trl
-- sft
 licence: license
 ---
-# Model Card for Qwen2.5-1.5B-Math-Instruct-LIMO
-This model is a fine-tuned version of [Qwen/Qwen2.5-Math-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start

 ---
 base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
+datasets: GAIR/LIMO
 library_name: transformers
 tags:
 - generated_from_trainer
+- open-r1
 licence: license
 ---
+# Model Card for None
+This model is a fine-tuned version of [Qwen/Qwen2.5-Math-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B-Instruct) on the [GAIR/LIMO](https://huggingface.co/datasets/GAIR/LIMO) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec391e725a94f5c5f49284648afce7533a433321cef25f5380d9595f234bb231
 size 3087467144

 version https://git-lfs.github.com/spec/v1
+oid sha256:92585d7c82c9612e7669739f7edc9ffece340f950b7c1626a38a4cdfcd76e6fa
 size 3087467144

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a1d92eaf7cee5326cdc05469b7a76c479c91d1a17d079df2df4b227d0d0a1e
 size 7288

 version https://git-lfs.github.com/spec/v1
+oid sha256:3b409394e25acf73b390e0025c7436efd94476635e29d0fdecc735650e452c8c
 size 7288