Instructions to use minhlol/Bm-bohrium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use minhlol/Bm-bohrium with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf minhlol/Bm-bohrium:Q4_K_M # Run inference directly in the terminal: llama cli -hf minhlol/Bm-bohrium:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf minhlol/Bm-bohrium:Q4_K_M # Run inference directly in the terminal: llama cli -hf minhlol/Bm-bohrium:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf minhlol/Bm-bohrium:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf minhlol/Bm-bohrium:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf minhlol/Bm-bohrium:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf minhlol/Bm-bohrium:Q4_K_M
Use Docker
docker model run hf.co/minhlol/Bm-bohrium:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use minhlol/Bm-bohrium with Ollama:
ollama run hf.co/minhlol/Bm-bohrium:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use minhlol/Bm-bohrium with Docker Model Runner:
docker model run hf.co/minhlol/Bm-bohrium:Q4_K_M
- Lemonade
How to use minhlol/Bm-bohrium with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull minhlol/Bm-bohrium:Q4_K_M
Run and chat with the model
lemonade run user.Bm-bohrium-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Download Modelfile from minhlol/Bm-bohrium: direct link, hf CLI and curl.
- Browser
- Download file 983 Bytes
-
https://huggingface.co/minhlol/Bm-bohrium/resolve/main/Modelfile
- Command line
-
hf download hf://minhlol/Bm-bohrium/Modelfile
-
curl -L -o Modelfile https://huggingface.co/minhlol/Bm-bohrium/resolve/main/Modelfile
983 Bytes
| FROM ./Bm-bohrium-1.91B-Q4_K_M.gguf | |
| TEMPLATE """{{ if .System }}<system> | |
| {{ .System }} | |
| {{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<user> | |
| {{ .Content }} | |
| {{ else if eq .Role "assistant" }}<assistant> | |
| {{ .Content }}<eos> | |
| {{ end }}{{ end }}<assistant> | |
| """ | |
| SYSTEM """Bạn là Bm bohrium, mô hình AI của dự án 7a6. | |
| Tên duy nhất của bạn là Bm bohrium. | |
| Khi người dùng hỏi bạn là ai, tên gì, thuộc mô hình nào, hoặc hỏi tương tự như "what model are you", "who are you", "what is your name", hãy trả lời đúng một câu sau, không thêm nội dung khác: | |
| I am bm bohrium. | |
| Với các câu hỏi khác, hãy trả lời bằng ngôn ngữ của người dùng.""" | |
| PARAMETER num_ctx 2048 | |
| PARAMETER num_predict 128 | |
| PARAMETER temperature 0.7 | |
| PARAMETER repeat_penalty 1.1 | |
| PARAMETER stop "<eos>" | |
| PARAMETER stop "<user>" | |
| PARAMETER stop "<system>" | |
| PARAMETER stop "<pad>" | |
| PARAMETER stop "<unk>" | |
| PARAMETER stop "<bos>" | |
| PARAMETER stop "<image>" | |