Instructions to use kuotient/mamba-ko-2.8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kuotient/mamba-ko-2.8b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="kuotient/mamba-ko-2.8b")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("kuotient/mamba-ko-2.8b", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use kuotient/mamba-ko-2.8b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "kuotient/mamba-ko-2.8b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kuotient/mamba-ko-2.8b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/kuotient/mamba-ko-2.8b
- SGLang
How to use kuotient/mamba-ko-2.8b 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 "kuotient/mamba-ko-2.8b" \ --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": "kuotient/mamba-ko-2.8b", "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 "kuotient/mamba-ko-2.8b" \ --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": "kuotient/mamba-ko-2.8b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use kuotient/mamba-ko-2.8b with Docker Model Runner:
docker model run hf.co/kuotient/mamba-ko-2.8b
모델 최대 컨텍스트 및 훈련 상태
#1
by maywell - opened
안녕하세요. 모델에 대해 궁금한 점 몇가지가 있어 discussion을 생성했습니다.
모델의 컨텍스트 len
해당 모델의 최대 컨텍스트 len이 궁금합니다.현재 instruct 부분이 노란색이던데, 얼마나 학습 된 건가요?
현재 가지고 있는 instruct 데이터셋으로 훈련 해보고자 하는데 가능하면 원본 모델이 완성된 후 하고자 하기에 여쭈어 봅니다.
멋진 모델 만들어주셔서 감사합니다. ❤️
4096 token
방금 업로드했습니다! 현재 글 쓰는 기준으로 올라온 모델이 korean_textbooks 데이터셋 전부 학습한 모델입니다.
답변 감사합니다. 일단 현재 repo에서는 final이라고 생각하고 학습 진행하겠습니다!
maywell changed discussion status to closed