Commit History
4 days ago
-
Update LlmMetadata for litert-lm 0.18.0: chat template with content parts, supports_thinking / supports_function_calling (weights unchanged) (#12)
- Update LlmMetadata for litert-lm 0.18.0: chat template with content parts, supports_thinking / supports_function_calling (weights unchanged) (7ca2923178d74ced081f5fe3028b9522723fc712) - Metadata update v3: the official LiteRT-LM config verbatim (models/<family> at 4a363c07) with the original max_num_tokens; weights, tokenizer and executor metadata unchanged (c79e6c907c7c001f7fd4e8e78f9c78ea5fa0ec8d) Co-authored-by: Daisuke Majima (MLBoy) <mlboydaisuke@users.noreply.huggingface.co>d417eaa
5 days ago
-
Add measured on-device speed table; note wi8 runtime requirement (#11)
- Add measured on-device speed table; note wi8 runtime requirement (a9daed20ec1037aa7448617b9f2cb6b32609ac71) Co-authored-by: Daisuke Majima (MLBoy) <mlboydaisuke@users.noreply.huggingface.co>f6a837a
-
add gpu optimized wi4b32_wi8_afp32 model (#10)
- add gpu optimized wi4b32_wi8_afp32 model (545a00a862c6d08cc2d6854ed276f84d09ddbff0) Co-authored-by: CarreyZhan <CarreyZhan@users.noreply.huggingface.co>8025a98
-
Clean up (#8)
- Clean up (f87b0fb08a855217b82c3e0e37440f256ef57051) - Clean up (c54d87648326a47e52028bc565a3d7873449f0d5) Co-authored-by: Harsha Veena <hvt4@users.noreply.huggingface.co>085a703 -
Add new model (#7)
- Upload MiniCPM5-1B_dynamic_wi8_afp32.litertlm with huggingface_hub (bb032a0854271173c4bc47cf38a7735bcccf603c) - Upload README.md with huggingface_hub (f301191a79b1be304aaf443228b766c5a47057bf) Co-authored-by: Harsha Veena <hvt4@users.noreply.huggingface.co>7a4a3f2
-
Update README.md (#6)
- Update README.md (c22a1b989dfbd5f8371fc23ac789a8fb70ccb3c2) Co-authored-by: CarreyZhan <CarreyZhan@users.noreply.huggingface.co>d5c3680
-
Update README (#2)
- Update README with detailed instrcutions for Gallery app (24c35e9d31ca90190e0f6449b8a287d9f627aaa4) - Minor changes (41f3a4ec5f46a09be98295be7b7436bd3fa897d7) Co-authored-by: Harsha Veena <hvt4@users.noreply.huggingface.co>ba6b8a5
-
Update README.md
Verified signaturec1ab4bc -
Add GPU-optimized LiteRT model and update README (#1)
- Add GPU-optimized LiteRT model and update README (704e47b1277ac5d3c9b86e479c42a969ade16a98) - Update README, with model files (befc43c018efe448823b81882e73587585757269) Co-authored-by: Harsha Veena <hvt4@users.noreply.huggingface.co>770a9b5
-
Update README.md
Verified signaturec13ea54 -
initial commit
Verified signaturedff771b