Instructions to use thanghf/math_model_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thanghf/math_model_v1 with Transformers:

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

pipe = pipeline("text-generation", model="thanghf/math_model_v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("thanghf/math_model_v1")
model = AutoModelForCausalLM.from_pretrained("thanghf/math_model_v1")
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 thanghf/math_model_v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thanghf/math_model_v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thanghf/math_model_v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/thanghf/math_model_v1

SGLang

How to use thanghf/math_model_v1 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 "thanghf/math_model_v1" \
    --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": "thanghf/math_model_v1",
		"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 "thanghf/math_model_v1" \
        --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": "thanghf/math_model_v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use thanghf/math_model_v1 with Docker Model Runner:
```
docker model run hf.co/thanghf/math_model_v1
```

thanghf commited on Apr 10, 2025

Commit

8ae23ff

verified ·

1 Parent(s): 0938cbc

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -10,8 +10,8 @@ license: apache-2.0
 ---
 ## Quick Start
-This model is upgraded version of demo_math_version.
-Trained on 1500 row clean data
 ### 🤗 Hugging Face Transformers
@@ -21,8 +21,8 @@ Here we show a code snippet to show you how to use the chat model with `transfor
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
-model = AutoModelForCausalLM.from_pretrained("thanghf/demo_math_model",torch_dtype=torch.bfloat16,device_map='auto')
-tokenizer = AutoTokenizer.from_pretrained("thanghf/demo_math_model")
 model.eval()
 streamer = TextStreamer(tokenizer)
 prompt = """Gieo hai con súc xắc cân đối và đồng chất. Xác suất để tổng số chấm trên mặt xuất hiện của hai con súc xắc bằng 7 là:"""

 ---
 ## Quick Start
+This model is upgraded version of demo_math_model.
+Trained on 1500 row clean data instead of raw data
 ### 🤗 Hugging Face Transformers
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
+model = AutoModelForCausalLM.from_pretrained("thanghf/math_model_v1",torch_dtype=torch.bfloat16,device_map='auto')
+tokenizer = AutoTokenizer.from_pretrained("thanghf/math_model_v1")
 model.eval()
 streamer = TextStreamer(tokenizer)
 prompt = """Gieo hai con súc xắc cân đối và đồng chất. Xác suất để tổng số chấm trên mặt xuất hiện của hai con súc xắc bằng 7 là:"""