Instructions to use NorthernTribe-Research/math-conjecture-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NorthernTribe-Research/math-conjecture-model with Transformers:

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

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

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("NorthernTribe-Research/math-conjecture-model", dtype="auto")

PEFT
How to use NorthernTribe-Research/math-conjecture-model with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use NorthernTribe-Research/math-conjecture-model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/NorthernTribe-Research/math-conjecture-model

SGLang

How to use NorthernTribe-Research/math-conjecture-model 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 "NorthernTribe-Research/math-conjecture-model" \
    --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": "NorthernTribe-Research/math-conjecture-model",
		"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 "NorthernTribe-Research/math-conjecture-model" \
        --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": "NorthernTribe-Research/math-conjecture-model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NorthernTribe-Research/math-conjecture-model with Docker Model Runner:
```
docker model run hf.co/NorthernTribe-Research/math-conjecture-model
```

NorthernTribe-Research commited on Feb 25

Commit

41a7495

verified ·

1 Parent(s): a86edac

Refine professional project description and training metadata wording.

Browse files

Files changed (2) hide show

README.md +1 -1
configs/deepseek_math_sota.yaml +1 -1

README.md CHANGED Viewed

@@ -17,7 +17,7 @@ datasets:
 # NorthernTribe-Research/math-conjecture-model
-Launch multi-stage DeepSeek-Math fine-tuning on Space GPU and push adapters to your model repo.
 This folder contains the autonomous training/evaluation stack used by the Space and local runs.

 # NorthernTribe-Research/math-conjecture-model
+An autonomous DeepSeek-Math training and evaluation stack that powers multi-stage Space GPU fine-tuning, quality-gated adapter promotion, and reproducible publishing to your Hugging Face model repository.
 This folder contains the autonomous training/evaluation stack used by the Space and local runs.

configs/deepseek_math_sota.yaml CHANGED Viewed

@@ -145,7 +145,7 @@ hub:
   repo_id: NorthernTribe-Research/math-conjecture-model
   private: false
   upload_stage_checkpoints: true
-  commit_message: Launch multi-stage DeepSeek-Math fine-tuning on Space GPU and push adapters to your model repo.
 credentials:
   path: huggingface-api-key.json

   repo_id: NorthernTribe-Research/math-conjecture-model
   private: false
   upload_stage_checkpoints: true
+  commit_message: Run autonomous multi-stage DeepSeek-Math training with post-eval quality gates and publish qualified adapters/checkpoints.
 credentials:
   path: huggingface-api-key.json