Text Generation
Transformers
Safetensors
English
gpt2
reasoning
structured-output
instruction-following
math
logic
science
text-generation-inference
Instructions to use NorthernTribe-Research/UMSR-Reasoner-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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")# pip install -U transformers accelerate # 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", device_map="auto") - 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
Download live_progress.json from NorthernTribe-Research/UMSR-Reasoner-7B: direct link, hf CLI and curl.
- Browser
- Download file 1.68 kB
-
https://huggingface.co/NorthernTribe-Research/UMSR-Reasoner-7B/resolve/main/live_progress.json
- Command line
-
hf download hf://NorthernTribe-Research/UMSR-Reasoner-7B/live_progress.json
-
curl -L -o live_progress.json https://huggingface.co/NorthernTribe-Research/UMSR-Reasoner-7B/resolve/main/live_progress.json
1.68 kB
| { | |
| "distill_enabled": true, | |
| "epoch": 1.0, | |
| "global_step": 256, | |
| "max_steps": 256, | |
| "message": "training finished", | |
| "metrics": { | |
| "distill_ce_loss": 10.826531410217285, | |
| "distill_ce_weight": 0.5, | |
| "distill_kd_loss": 0.0498046875, | |
| "distill_kd_weight": 0.5, | |
| "distill_temperature": 1.2, | |
| "epoch": 1.0, | |
| "eval_loss": 5.438441753387451, | |
| "grad_norm": 0.00159454345703125, | |
| "learning_rate": 4.032258064516129e-07, | |
| "loss": 5.431174278259277 | |
| }, | |
| "runtime_hardware": { | |
| "cuda_available": false, | |
| "cuda_compute_capability_0": "", | |
| "cuda_device_0": "", | |
| "cuda_device_count": 0, | |
| "cuda_total_memory_gb_0": null, | |
| "mps_available": false, | |
| "torch_available": true, | |
| "torch_version": "2.11.0+cu130" | |
| }, | |
| "runtime_system": { | |
| "arch": "x86_64", | |
| "binaries": { | |
| "bash": "/usr/bin/bash", | |
| "curl": "/usr/bin/curl", | |
| "git": "/usr/bin/git", | |
| "python3": "/usr/local/bin/python3" | |
| }, | |
| "collected_at": "2026-05-23T06:11:39.136659+00:00", | |
| "cpu_count": 16, | |
| "disk_free_gb": 326.3, | |
| "disk_total_gb": 1699.93, | |
| "in_venv": false, | |
| "is_ubuntu": false, | |
| "kernel": "6.12.79-101.147.amzn2023.x86_64", | |
| "memory_gb": 123.79, | |
| "missing_required_bins": [], | |
| "native_mode": true, | |
| "native_ready": true, | |
| "nvidia_smi_output": "", | |
| "nvidia_smi_present": false, | |
| "os_id": "debian", | |
| "os_name": "Debian GNU/Linux 13 (trixie)", | |
| "python_executable": "/usr/local/bin/python", | |
| "python_version": "3.13.13", | |
| "required_bins": [ | |
| "bash", | |
| "python3", | |
| "git", | |
| "curl" | |
| ] | |
| }, | |
| "status": "completed", | |
| "updated_at": "2026-05-23T06:27:43.871485+00:00" | |
| } | |