Text Generation
Transformers
Safetensors
English
boris2
chat
instruct
small-language-model
causal-lm
conversational
custom_code
Eval Results (legacy)
Instructions to use opencerebral/Boris-2-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use opencerebral/Boris-2-Instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="opencerebral/Boris-2-Instruct", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("opencerebral/Boris-2-Instruct", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use opencerebral/Boris-2-Instruct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "opencerebral/Boris-2-Instruct" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "opencerebral/Boris-2-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/opencerebral/Boris-2-Instruct
- SGLang
How to use opencerebral/Boris-2-Instruct 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 "opencerebral/Boris-2-Instruct" \ --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": "opencerebral/Boris-2-Instruct", "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 "opencerebral/Boris-2-Instruct" \ --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": "opencerebral/Boris-2-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use opencerebral/Boris-2-Instruct with Docker Model Runner:
docker model run hf.co/opencerebral/Boris-2-Instruct
Commit History
Yesterday
-
Add a Code link to the training code at git.kunix.org
Verified signatureAction Automated by Claude Code9f60d91
4 days ago
-
Add evaluation results (model-index) from the card's tables
Verified signatureAction Automated by Claude Code3e07edb
5 days ago
-
modeling: plain `import transformers` instead of __import__() (same behaviour; passes static code audits)
Verified signatureLogits are bit-identical (max |diff| 0.0). Action Automated by Claude Code493aa46
6 days ago
-
Card: restore the V100 in the description
Verified signatureAction Automated by Claude Code2458618 -
Card: drop the V100 from the description
Verified signatureAction Automated by Claude Coded0bf257
7 days ago
-
Card: replace automation label with OpenCerebral copyright notice
Verified signature0d6a9d7 -
Add IFEval, TruthfulQA, MMLU and other chat/knowledge benchmarks vs SmolLM2-135M-Instruct
Verified signatureAction Automated by Claude Code2a6121e -
Release Boris-2-Instruct
Verified signatureAction Automated by Claude Code375743f -
initial commit
Verified signature2f968b8