Instructions to use AI-MO/NuminaMath-7B-CoT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AI-MO/NuminaMath-7B-CoT with Transformers:

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

pipe = pipeline("text-generation", model="AI-MO/NuminaMath-7B-CoT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AI-MO/NuminaMath-7B-CoT")
model = AutoModelForCausalLM.from_pretrained("AI-MO/NuminaMath-7B-CoT")
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

vLLM

How to use AI-MO/NuminaMath-7B-CoT with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AI-MO/NuminaMath-7B-CoT

SGLang

How to use AI-MO/NuminaMath-7B-CoT 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 "AI-MO/NuminaMath-7B-CoT" \
    --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": "AI-MO/NuminaMath-7B-CoT",
		"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 "AI-MO/NuminaMath-7B-CoT" \
        --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": "AI-MO/NuminaMath-7B-CoT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AI-MO/NuminaMath-7B-CoT with Docker Model Runner:
```
docker model run hf.co/AI-MO/NuminaMath-7B-CoT
```

Adding Evaluation Results

by leaderboard-pr-bot - opened Sep 12, 2024

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+17

-4

Files changed (1) hide show

README.md +17 -4

README.md CHANGED Viewed

@@ -1,18 +1,18 @@
 ---
 license: apache-2.0
-base_model: deepseek-ai/deepseek-math-7b-base
 tags:
 - alignment-handbook
 - generated_from_trainer
 - aimo
 - math
 datasets:
 - AI-MO/NuminaMath-CoT
 model-index:
 - name: AI-MO/NuminaMath-7B-CoT
   results: []
-language:
-- en
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -141,4 +141,17 @@ The following hyperparameters were used during training:
 - Transformers 4.42.3
 - Pytorch 2.3.0+cu121
 - Datasets 2.18.0
-- Tokenizers 0.19.1

 ---
+language:
+- en
 license: apache-2.0
 tags:
 - alignment-handbook
 - generated_from_trainer
 - aimo
 - math
+base_model: deepseek-ai/deepseek-math-7b-base
 datasets:
 - AI-MO/NuminaMath-CoT
 model-index:
 - name: AI-MO/NuminaMath-7B-CoT
   results: []
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 - Transformers 4.42.3
 - Pytorch 2.3.0+cu121
 - Datasets 2.18.0
+- Tokenizers 0.19.1
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_AI-MO__NuminaMath-7B-CoT)
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |12.95|
+|IFEval (0-Shot)    |26.89|
+|BBH (3-Shot)       |19.15|
+|MATH Lvl 5 (4-Shot)| 7.93|
+|GPQA (0-shot)      | 2.13|
+|MuSR (0-shot)      | 0.83|
+|MMLU-PRO (5-shot)  |20.76|