Any-to-Any
MLX
Safetensors
Transformers
GGUF
English
gemma4
image-text-to-text
4-bit precision
8-bit precision
Instructions to use LetheanNetwork/lemma-bk with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use LetheanNetwork/lemma-bk with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir lemma-bk LetheanNetwork/lemma-bk
- Transformers
How to use LetheanNetwork/lemma-bk with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("LetheanNetwork/lemma-bk") model = AutoModelForMultimodalLM.from_pretrained("LetheanNetwork/lemma-bk", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "bos_token_id": 2, | |
| "do_sample": true, | |
| "eos_token_id": [ | |
| 1, | |
| 106, | |
| 50 | |
| ], | |
| "pad_token_id": 0, | |
| "temperature": 1.0, | |
| "top_k": 64, | |
| "top_p": 0.95, | |
| "transformers_version": "5.5.0.dev0" | |
| } | |