67.2 GB

Ctrl+K

1 contributor

History: 42 commits

jangq

capabilities: stamp reasoning/tool parser + cache_type for vmlx CapabilityDetector Tier-1

b900d53 verified about 13 hours ago

.gitattributes

1.68 kB
v2 format + gs=128 + per-tensor router gs=64 + chat_template about 1 month ago
README.md

5.92 kB
Add open-source links and provenance to README 26 days ago
chat_template.jinja

6.64 kB
chat_template.jinja with enable_thinking toggle 29 days ago
config.json

1.74 kB
Fix: add eos_token_id=200020 to prevent generation loops 29 days ago
jang_config.json

1.04 kB
capabilities: stamp reasoning/tool parser + cache_type for vmlx CapabilityDetector Tier-1 about 13 hours ago
merges.txt

2.41 MB
Upload folder using huggingface_hub about 1 month ago
mlx-studio-app.png

840 kB
xet

Upload mlx-studio-app.png with huggingface_hub about 1 month ago
mlx-studio-banner.png

45.6 kB
Upload mlx-studio-banner.png with huggingface_hub about 1 month ago
model-00001-of-00014.safetensors

5.34 GB
xet

v2 format + gs=128 + per-tensor router gs=64 + chat_template about 1 month ago
model-00002-of-00014.safetensors

5.1 GB
xet

v2 format + gs=128 + per-tensor router gs=64 + chat_template about 1 month ago
model-00003-of-00014.safetensors

5.1 GB
xet

v2 format + gs=128 + per-tensor router gs=64 + chat_template about 1 month ago
model-00004-of-00014.safetensors

5.1 GB
xet

v2 format + gs=128 + per-tensor router gs=64 + chat_template about 1 month ago
model-00005-of-00014.safetensors

5.1 GB
xet

v2 format + gs=128 + per-tensor router gs=64 + chat_template about 1 month ago
model-00006-of-00014.safetensors

5.1 GB
xet

v2 format + gs=128 + per-tensor router gs=64 + chat_template about 1 month ago
model-00007-of-00014.safetensors

5.1 GB
xet

v2 format + gs=128 + per-tensor router gs=64 + chat_template about 1 month ago
model-00008-of-00014.safetensors

5.1 GB
xet

v2 format + gs=128 + per-tensor router gs=64 + chat_template about 1 month ago
model-00009-of-00014.safetensors

5.1 GB
xet

v2 format + gs=128 + per-tensor router gs=64 + chat_template about 1 month ago
model-00010-of-00014.safetensors

5.1 GB
xet

v2 format + gs=128 + per-tensor router gs=64 + chat_template about 1 month ago
model-00011-of-00014.safetensors

5.1 GB
xet

v2 format + gs=128 + per-tensor router gs=64 + chat_template about 1 month ago
model-00012-of-00014.safetensors

5.1 GB
xet

v2 format + gs=128 + per-tensor router gs=64 + chat_template about 1 month ago
model-00013-of-00014.safetensors

5.1 GB
xet

v2 format + gs=128 + per-tensor router gs=64 + chat_template about 1 month ago
model-00014-of-00014.safetensors

681 MB
xet

v2 format + gs=128 + per-tensor router gs=64 + chat_template about 1 month ago
model.safetensors.index.json

163 kB
v2 format + gs=128 + per-tensor router gs=64 + chat_template about 1 month ago
tokenizer.json

15.5 MB
xet

v2 format + gs=128 + per-tensor router gs=64 + chat_template about 1 month ago
tokenizer_config.json

8.26 kB
Fix: embed chat_template in tokenizer_config.json (was only in .jinja file, vMLX needs it inline) 29 days ago
vocab.json

4.71 MB
Upload folder using huggingface_hub about 1 month ago