CoolFace
Modelpublic

cstr/octen-0.6b-GGUF

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face
0likes238downloads
20 commits on main
0b845282mo ago

docs: add provenance / EU AI Act Art. 53 note

cstr
1d8cf903mo ago

importance matrix (calibration)

cstr
33213b43mo ago

A/B summary (cos vs gold)

cstr
66926693mo ago

iq4_xs +imatrix (cos_vs_f16=0.9751)

cstr
0cb2ab63mo ago

q4_k +imatrix (cos_vs_f16=0.9759)

cstr
d5bb9575mo ago

Upload README.md with huggingface_hub

cstr
c9eec865mo ago

Update README with Ollama instructions and quality metrics

cstr
0671a816mo ago

Add octen-0.6b-q4_k.gguf (Ollama-compatible)

cstr
a7c80b46mo ago

Update Q8_0 GGUF with Ollama-compatible tensor names and metadata

cstr
fe4e5f16mo ago

Update F32 GGUF with Ollama-compatible tensor names and metadata

cstr
a48bb046mo ago

Add octen-0.6b-q4_k.gguf

cstr
f0ab83c6mo ago

Add model card for octen-0.6b GGUF

cstr
7f5ce4b6mo ago

Add octen-0.6b-q8_0.gguf

cstr
9d74c3e6mo ago

Add octen-0.6b-q4_k.gguf

cstr
4833ede6mo ago

Add model card for octen-0.6b GGUF

cstr
95e6c6d6mo ago

Add octen-0.6b.gguf

cstr
8644fb06mo ago

Add octen-0.6b-q8_0.gguf

cstr
ff6e5646mo ago

Add octen-0.6b-q4_k.gguf

cstr
3c0d4c86mo ago

Add model card for octen-0.6b GGUF

cstr
3814e146mo ago

initial commit

cstr