Instructions to use minhlol/Bm-bohrium-3.7B 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-3.7B 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-3.7B:Q8_0 # Run inference directly in the terminal: llama cli -hf minhlol/Bm-bohrium-3.7B:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf minhlol/Bm-bohrium-3.7B:Q8_0 # Run inference directly in the terminal: llama cli -hf minhlol/Bm-bohrium-3.7B:Q8_0
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf minhlol/Bm-bohrium-3.7B:Q8_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf minhlol/Bm-bohrium-3.7B:Q8_0
Use Docker
docker model run hf.co/minhlol/Bm-bohrium-3.7B:Q8_0
- Llama new
- LM Studio
- Jan
- Ollama
How to use minhlol/Bm-bohrium-3.7B with Ollama:
ollama run hf.co/minhlol/Bm-bohrium-3.7B:Q8_0
- Unsloth Desktop
- Docker Model Runner
How to use minhlol/Bm-bohrium-3.7B with Docker Model Runner:
docker model run hf.co/minhlol/Bm-bohrium-3.7B:Q8_0
- Lemonade
How to use minhlol/Bm-bohrium-3.7B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull minhlol/Bm-bohrium-3.7B:Q8_0
Run and chat with the model
lemonade run user.Bm-bohrium-3.7B-Q8_0
List all available models
lemonade list
- Atomic Chat
Download training_progress.json from minhlol/Bm-bohrium-3.7B: direct link, hf CLI and curl.
- Browser
- Download file 1.5 kB
-
https://huggingface.co/minhlol/Bm-bohrium-3.7B/resolve/main/training_progress.json
- Command line
-
hf download hf://minhlol/Bm-bohrium-3.7B/training_progress.json
-
curl -L -o training_progress.json https://huggingface.co/minhlol/Bm-bohrium-3.7B/resolve/main/training_progress.json
1.5 kB
| { | |
| "model_name": "Bm bohrium", | |
| "total_parameters": 3692637952, | |
| "language_parameters": 3601068032, | |
| "layers": 74, | |
| "source_model": "minhlol/Bm-bohrium-3B", | |
| "source_revision": "22a59804eaa30d4f2843c792fb9ac7da8f930578", | |
| "source_updates": 23, | |
| "new_updates": 1002, | |
| "supervised_tokens": 75196, | |
| "held_out_baseline_loss": 9.958833044853764, | |
| "preserved_expansion_loss": 9.958833044853764, | |
| "peak_gpu_GB": 15.35, | |
| "seq_len": 256, | |
| "optimizer": "Adafactor per-parameter, FP32 weights, FP16 autocast, no gradient accumulation", | |
| "new_training_examples": 17296, | |
| "validation_examples": 16, | |
| "seed": 42, | |
| "vision_updates": 401, | |
| "vision_parameter_updates_verified": 202, | |
| "tasks": { | |
| "text_probe": 1, | |
| "vi_image": 201, | |
| "en_image": 200, | |
| "vi_text": 300, | |
| "en_text": 300 | |
| }, | |
| "vision_sources": { | |
| "V3_CAP": { | |
| "repo": "ai-enthusiasm-community/UIT-ViIC", | |
| "revision": "4c9816758ac863a0a7c2907b0787cf45f31e7f4b" | |
| }, | |
| "V3_VQA": { | |
| "repo": "HuggingFaceM4/the_cauldron", | |
| "revision": "847a98a779b1652d65111daf20c972dfcd333605" | |
| } | |
| }, | |
| "task_mix": { | |
| "en_text": 0.3, | |
| "vi_text": 0.3, | |
| "en_image": 0.2, | |
| "vi_image": 0.2 | |
| }, | |
| "evaluation_history": [ | |
| { | |
| "step": 102, | |
| "text_loss": 7.868882630461005, | |
| "image_loss": 5.493708421022464 | |
| }, | |
| { | |
| "step": 1002, | |
| "text_loss": 6.478127247488014, | |
| "image_loss": 4.747814701153682 | |
| } | |
| ], | |
| "vision_validation_loss_after_checks": 9.459292203952105 | |
| } |