hmkim97
/

tangram-gate

kv-cache-compression

Model card Files Files and versions

1.28 GB

Ctrl+K

Ctrl+K

2 contributors

History: 14 commits

hmkim97's picture

Upload qwen3-30b-a3b-instruct-2507/q8_dim16_sink16.pt with huggingface_hub

06a628f verified 3 days ago

gemma-3-12b-it
Upload gemma-3-12b-it/q2_dim16_sink16.pt with huggingface_hub 19 days ago
gpt-oss-20b
Add gpt-oss-20b gate (q8_dim16_sink16) 19 days ago
llama3.1-8b-instruct
Upload llama3.1-8b-instruct/q4_dim16_sink16_v0.pt with huggingface_hub 19 days ago
qwen2.5-7b-instruct-1m
Upload qwen2.5-7b-instruct-1m/q7_dim16_sink16.pt with huggingface_hub 19 days ago
qwen3-14b
Upload qwen3-14b/q5_dim16_sink16.pt with huggingface_hub 19 days ago
qwen3-30b-a3b-instruct-2507
Upload qwen3-30b-a3b-instruct-2507/q8_dim16_sink16.pt with huggingface_hub 3 days ago
qwen3-4b-instruct-2507
Upload qwen3-4b-instruct-2507/q4_dim16_sink16.pt with huggingface_hub 19 days ago
qwen3-8b
Upload qwen3-8b/q4_dim16_sink16.pt with huggingface_hub 19 days ago
.gitattributes

1.52 kB
initial commit 19 days ago
README.md

1.24 kB
List gpt-oss-20b gate 19 days ago