Commit History

Update integrity hash for latest model.safetensors
56aa924
verified

chknlittle commited on

Upload latest exportfix1 model.safetensors with corrected scales
8ab6078
verified

chknlittle commited on

Add explicit note about HF model-size badge for packed NVFP4 tensors
f92a329
verified

chknlittle commited on

Fix model metadata: explicit MoE model size and tag
4d28a7d
verified

chknlittle commited on

Add Ampere performance notes and tested tuning guidance
15ecb1c
verified

chknlittle commited on

Fix model card formatting and clarify required custom image build
30bb23b
verified

chknlittle commited on

Clarify required custom vLLM image and build steps
80eef0f
verified

chknlittle commited on

docs: document validated serving runtime and fallback profile
2009e8a
verified

chknlittle commited on

docs: add runtime compatibility guidance for vllm 0.16
3ce9671
verified

chknlittle commited on

docs: clarify model size as 30B-A3B base architecture
31aa2f2
verified

chknlittle commited on

docs: clarify NVFP4 is 4-bit quantization
1d0ec8b
verified

chknlittle commited on

Add files using upload-large-folder tool
551066e
verified

chknlittle commited on

initial commit
c5472b8
verified

chknlittle commited on