Hugging Face's logo

lthn
/
lemrd-mlx-8bit

Image-Text-to-Text
MLX
Safetensors
gemma4
lemma
8bit
apple-silicon
multimodal
on-device
conversational
8-bit precision
Model card Files
xet
 Community
lemrd-mlx-8bit

Commit History

docs: correct base_model lineage for HF model tree
d31df73

Snider Virgil commited on

feat: merge LEK into lemrd weights
826e60a

Snider Virgil commited on

fix: pull Google's chat_template.jinja fix (26B/31B variant)
4407e16

Snider Cladius Maximus commited on

fix: replace LICENSE symlink with real EUPL-1.2 file
7f0ef4d

Snider Cladius Maximus commited on

fix: exact configs from unsloth 31b-8bit reference
d51392e

Snider Cladius Maximus commited on

Upload config.json with huggingface_hub
4af73c7
verified

lthn commited on

Upload tokenizer_config.json with huggingface_hub
e539a3a
verified

lthn commited on

Upload config.json with huggingface_hub
7b26f19
verified

lthn commited on

Upload processor_config.json with huggingface_hub
0e8f8a8
verified

lthn commited on

Upload config.json with huggingface_hub
a4314e3
verified

lthn commited on

Upload folder using huggingface_hub
54958a0
verified

lthn commited on

initial commit
80f7dd9
verified

lthn commited on