lthn
/

lemma-mlx-8bit

Image-Text-to-Text

8-bit precision

Model card Files Files and versions

9 GB

Ctrl+K

Ctrl+K

4 contributors

History: 12 commits

Snider

Virgil

docs: correct base_model lineage for HF model tree

fa76a33 4 days ago

.gitattributes

1.57 kB
Upload folder using huggingface_hub 6 days ago
LICENSE

13.8 kB
fix: replace LICENSE symlink with real EUPL-1.2 file 6 days ago
README.md

1.39 kB
docs: correct base_model lineage for HF model tree 4 days ago
chat_template.jinja

11.9 kB
feat: merge LEK into lemma weights 5 days ago
config.json

36.5 kB
feat: merge LEK into lemma weights 5 days ago
generation_config.json

208 Bytes
Upload folder using huggingface_hub 6 days ago
model-00001-of-00002.safetensors

4.96 GB
xet

feat: merge LEK into lemma weights 5 days ago
model-00002-of-00002.safetensors

4 GB
xet

feat: merge LEK into lemma weights 5 days ago
model.safetensors.index.json

295 kB
feat: merge LEK into lemma weights 5 days ago
processor_config.json

902 Bytes
fix: apply proven configs from mlx-community/unsloth references 6 days ago
tokenizer.json

32.2 MB
xet

Upload folder using huggingface_hub 6 days ago
tokenizer_config.json

2.69 kB
fix: apply proven configs from mlx-community/unsloth references 6 days ago