diffuse-cpp
/

LLaDA-8B-Instruct-GGUF

Text Generation

Model card Files Files and versions

LLaDA-8B-Instruct-GGUF

Commit History

docs: improve model card with quickstart, benchmarks, Apache-2.0

f80c9ca
verified

Carmenest commited on 26 days ago

Remove F16 GGUF (redundant, keep Q4_K_M + Q8_0)

1c65114
verified

Carmenest commited on about 1 month ago

Upload README.md with huggingface_hub

faffe6f
verified

Carmenest commited on Mar 22

Update model card with inter-step cache benchmark results (v0.2.0)

9dc8866
verified

Carmenest commited on Mar 22

Update model card with B=256 real-prompt benchmarks

e00b07f
verified

Carmenest commited on Mar 20

Add paper DOI reference

0092801
verified

Carmenest commited on Mar 19

Update benchmarks with rigorous real-prompt results (buffer 1.5x fix)

deb1e7f
verified

Carmenest commited on Mar 19

Upload llada-8b-f16.gguf with huggingface_hub

6ce1b66
verified

Carmenest commited on Mar 19

Upload llada-8b-q8_0.gguf with huggingface_hub

9e81666
verified

Carmenest commited on Mar 19

Upload llada-8b-q4km.gguf with huggingface_hub

60c457a
verified

Carmenest commited on Mar 19

Upload README.md with huggingface_hub

927092d
verified

Carmenest commited on Mar 19

initial commit

3ed377e
verified

Carmenest commited on Mar 19