axolotl-quants
/

Llama-4-Scout-17B-16E-Linearized-bnb-nf4-bf16

Image-Text-to-Text

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Llama-4-Scout-17B-16E-Linearized-bnb-nf4-bf16

Commit History

fix: update pad token in special tokens following upstream (#3)

36a12ea
verified

Nanobit commited on 25 days ago

fix: update rope configs following upstream (#1)

2e52807
verified

Nanobit commited on 25 days ago

fix: update old pad token following upstream (#2)

62281cf
verified

Nanobit commited on 25 days ago

Link to sample YAML

529c1c5
verified

winglian commited on Apr 8

Upload folder using huggingface_hub

eb77729
verified

winglian commited on Apr 7

initial commit

56e1e36
verified

winglian commited on Apr 7