Instructions to use NorthernTribe-Research/UMSR-Reasoner-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NorthernTribe-Research/UMSR-Reasoner-7B with Transformers:

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

pipe = pipeline("text-generation", model="NorthernTribe-Research/UMSR-Reasoner-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NorthernTribe-Research/UMSR-Reasoner-7B")
model = AutoModelForCausalLM.from_pretrained("NorthernTribe-Research/UMSR-Reasoner-7B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NorthernTribe-Research/UMSR-Reasoner-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NorthernTribe-Research/UMSR-Reasoner-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NorthernTribe-Research/UMSR-Reasoner-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NorthernTribe-Research/UMSR-Reasoner-7B

SGLang

How to use NorthernTribe-Research/UMSR-Reasoner-7B 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/UMSR-Reasoner-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NorthernTribe-Research/UMSR-Reasoner-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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/UMSR-Reasoner-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NorthernTribe-Research/UMSR-Reasoner-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NorthernTribe-Research/UMSR-Reasoner-7B with Docker Model Runner:
```
docker model run hf.co/NorthernTribe-Research/UMSR-Reasoner-7B
```

UMSR-Reasoner-7B

Purpose

UMSR-Reasoner-7B is a general reasoning model designed for structured problem solving and consistent answer formatting in production and research workflows.

Model repository: https://huggingface.co/NorthernTribe-Research/UMSR-Reasoner-7B
Primary dataset: https://huggingface.co/datasets/NorthernTribe-Research/UMSR-v1

Intended Use

Use this model for tasks that require:

multi-step quantitative reasoning
logic and strategy-style question answering
science and technical problem decomposition
deterministic final-answer formatting for downstream parsers

Core Capabilities

Produces step-aware reasoning outputs for complex prompts
Handles open-form and exam-style tasks across math, logic, and science domains
Supports structured response contracts for automation pipelines
Works well in teacher-student continuous improvement loops

Recommended Prompting

For highest reliability, use explicit instructions about reasoning depth and enforce a final-answer tag in every response.

Suggested system instruction:

Solve step by step and end with <final_answer>...</final_answer>.

Output Contract

Required final output tag:

<final_answer>...</final_answer>

Optional reasoning tag:

<reasoning>...</reasoning>

Training Profile

Student model: NorthernTribe-Research/UMSR-Reasoner-7B
Training mode: teacher-student distillation
Teacher model(s): NorthernTribe-Research/UMSR-Reasoner-7B

Operational Guidance

Prefer lower sampling temperature for deterministic workflows
Validate final answers for high-stakes usage
Run domain-specific evaluation before production rollout

Limitations

May produce plausible but incorrect reasoning traces
Performance varies with prompt quality and task domain
Not a substitute for expert review in legal, medical, financial, or safety-critical decisions

Downloads last month: 410

Safetensors

Model size

103k params

Tensor type

F32

Model tree for NorthernTribe-Research/UMSR-Reasoner-7B

Finetunes

2 models

NorthernTribe-Research
/

UMSR-Reasoner-7B