Cactus-Compute
/

gemma4-e2b-grouped-k96

Mixture of Experts

grouped-experts

Model card Files Files and versions

gemma4-e2b-grouped-k96

10.6 GB

Ctrl+K

Ctrl+K

1 contributor

History: 44 commits

ncylich's picture

Upload gemma4.py with huggingface_hub

ea203cb verified 12 days ago

groups
Upload groups/s50_K96_layer9.pt with huggingface_hub 12 days ago
.gitattributes

1.52 kB
initial commit 12 days ago
README.md

2.33 kB
Upload README.md with huggingface_hub 12 days ago
Sw_grouped_50_K96_lora_long.pt
Detected Pickle imports (5)
- "collections.OrderedDict",
- "torch.LongStorage",
- "torch.BFloat16Storage",
- "torch.FloatStorage",
- "torch._utils._rebuild_tensor_v2"
What is a pickle import?
10.6 GB
xet

Upload Sw_grouped_50_K96_lora_long.pt with huggingface_hub 12 days ago
gemma4.py

27.2 kB
Upload gemma4.py with huggingface_hub 12 days ago
gemma4_hf.py

2.14 kB
Upload gemma4_hf.py with huggingface_hub 12 days ago
inference_k96.py

9.63 kB
Upload inference_k96.py with huggingface_hub 12 days ago
rung6_moe_g4.py

73.9 kB
Upload rung6_moe_g4.py with huggingface_hub 12 days ago
rung7_swiglu_g4.py

18.3 kB
Upload rung7_swiglu_g4.py with huggingface_hub 12 days ago
rung8_grouped_g4.py

13.5 kB
Upload rung8_grouped_g4.py with huggingface_hub 12 days ago