lthn
/

lemer

image-text-to-text

4-bit precision

8-bit precision

Model card Files Files and versions

2.67 GB

Ctrl+K

Ctrl+K

1 contributor

History: 13 commits

lthn's picture

Update README.md

b9f8b03 verified about 14 hours ago

.gitattributes

1.89 kB
Add GGUF quants (bf16, q3-q8) about 15 hours ago
README.md

321 Bytes
Update README.md about 14 hours ago
chat_template.jinja

11.9 kB
Upload Lemer E2B bf16 (MLX format) — LEK-activated Gemma 4 E2B about 17 hours ago
config.json

4.7 kB
Replace bf16 with Q4 MLX — consumer-ready quantisation about 14 hours ago
generation_config.json

208 Bytes
Upload Lemer E2B bf16 (MLX format) — LEK-activated Gemma 4 E2B about 17 hours ago
model.safetensors

2.63 GB
xet

Replace bf16 with Q4 MLX — consumer-ready quantisation about 14 hours ago
model.safetensors.index.json

108 kB
Replace bf16 with Q4 MLX — consumer-ready quantisation about 14 hours ago
tokenizer.json

32.2 MB
xet

Upload Lemer E2B bf16 (MLX format) — LEK-activated Gemma 4 E2B about 17 hours ago
tokenizer_config.json

2.72 kB
Upload Lemer E2B bf16 (MLX format) — LEK-activated Gemma 4 E2B about 17 hours ago