lthn
/

lemmy

Image-Text-to-Text

4-bit precision

Model card Files Files and versions

14.2 GB

Ctrl+K

Ctrl+K

1 contributor

History: 13 commits

lthn's picture

Upload config.json with huggingface_hub

b3bba13 verified 1 day ago

.gitattributes

1.83 kB
Upload folder using huggingface_hub 1 day ago
README.md

130 Bytes
Update README.md 1 day ago
chat_template.jinja

12 kB
Upload Lemmy 26B bf16 (MLX format) — LEK-activated Gemma 4 26B-A4B MoE 3 days ago
config.json

10.5 kB
Upload config.json with huggingface_hub 1 day ago
generation_config.json

208 Bytes
Upload Lemmy 26B bf16 (MLX format) — LEK-activated Gemma 4 26B-A4B MoE 3 days ago
model-00001-of-00003.safetensors

5.32 GB
xet

Replace bf16 with Q4 MLX — consumer-ready quantisation 3 days ago
model-00002-of-00003.safetensors

5.36 GB
xet

Replace bf16 with Q4 MLX — consumer-ready quantisation 3 days ago
model-00003-of-00003.safetensors

3.52 GB
xet

Replace bf16 with Q4 MLX — consumer-ready quantisation 3 days ago
model.safetensors.index.json

139 kB
Replace bf16 with Q4 MLX — consumer-ready quantisation 3 days ago
processor_config.json

1.69 kB
Upload processor_config.json with huggingface_hub 1 day ago
tokenizer.json

32.2 MB
xet

Upload Lemmy 26B bf16 (MLX format) — LEK-activated Gemma 4 26B-A4B MoE 3 days ago
tokenizer_config.json

2.07 kB
Upload tokenizer_config.json with huggingface_hub 1 day ago