SF

Yoursmiling's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in litert-community/Kokoro-82M 3 days ago

Add FP16-safe kokoro_int8_gpu_fp16 / kokoro_int8_fp16 bundles and update model card

#3 opened 3 days ago by

yichunkuo

New activity in litert-community/Kokoro-82M 8 days ago

Update README for LiteRT-LM main (C++ API rename, GPU fallback, build notes)

#2 opened 8 days ago by

Yoursmiling

New activity in litert-community/Qwen3-TTS-12Hz-0.6B-Base 8 days ago

Update README.md

#3 opened 8 days ago by

yichunkuo

Update Quality section with 1,000-sentence evaluation across all 10 supported languages

#4 opened 8 days ago by

yichunkuo

Add Qwen3-TTS-12Hz-0.6B-Base .litertlm models (INT8 & INT4), samples, and updated model card; move legacy .tflite files to legacy/

#2 opened 8 days ago by

yichunkuo

New activity in litert-community/Kokoro-82M 8 days ago

Release Kokoro-82M as single-file .litertlm bundles; move FP32 tflite preview to legacy/

#1 opened 8 days ago by

yichunkuo

New activity in litert-community/Qwen3-0.6B 11 days ago

Qwen3-0.6B.litertlm: replace the tokenizer section with Qwen/Qwen3-0.6B's tokenizer.json, weights and LlmMetadata unchanged

#8 opened 12 days ago by

mlboydaisuke

New activity in litert-community/Qwen3-4B 12 days ago

qwen3_4b_channelwise_int8_float32kv.litertlm: update LlmMetadata for litert-lm 0.18.0, weights unchanged

#4 opened 13 days ago by

mlboydaisuke

New activity in litert-community/Qwen3-0.6B 13 days ago

Qwen3-0.6B.litertlm: update LlmMetadata for litert-lm 0.18.0, weights unchanged

1

#7 opened 13 days ago by

mlboydaisuke

New activity in litert-community/Qwen3-1.7B 14 days ago

Update LlmMetadata for litert-lm 0.18.0: chat template with content parts, supports_thinking / supports_function_calling (weights unchanged)

#6 opened 15 days ago by

mlboydaisuke

New activity in litert-community/Qwen2.5-1.5B-Instruct 14 days ago

Update LlmMetadata for litert-lm 0.18.0: chat template with content parts, supports_thinking / supports_function_calling (weights unchanged)

#7 opened 15 days ago by

mlboydaisuke

New activity in litert-community/MiniCPM5-2B 14 days ago

Update LlmMetadata for litert-lm 0.18.0: chat template with content parts, supports_thinking / supports_function_calling (weights unchanged)

#6 opened 15 days ago by

mlboydaisuke

New activity in litert-community/MiniCPM5-1B 14 days ago

Update LlmMetadata for litert-lm 0.18.0: chat template with content parts, supports_thinking / supports_function_calling (weights unchanged)

#12 opened 15 days ago by

mlboydaisuke

New activity in litert-community/bonsai-image-ternary-4b-litert 16 days ago

Update app.py

1

#1 opened 22 days ago by

XBFDI

New activity in litert-community/MiniCPM5-1B 16 days ago

Add measured on-device speed table; note wi8 runtime requirement

#11 opened 2 months ago by

mlboydaisuke

New activity in litert-community/README 25 days ago

Community's Picks: the Laya line

#11 opened 26 days ago by

mlboydaisuke

New activity in litert-community/gemma-4-31B-it-litert-lm about 1 month ago

Update README.md

#3 opened about 1 month ago by

tylermullen

New activity in litert-community/Qwen3-0.6B about 1 month ago

Refresh Qwen3-0.6B_dynamic_wi4b32_afp32.litertlm: current litert-torch export, chat template that takes content parts

#6 opened about 1 month ago by

mlboydaisuke

New activity in litert-community/VibeThinker-1.5B about 1 month ago

Add measured Galaxy S26 GPU-vs-CPU Performance section

#2 opened about 2 months ago by

mlboydaisuke

New activity in litert-community/MiniCPM-V-4 about 1 month ago

Update MiniCPM-V-4 model to be compatible with LiteRT-LM runtime at HEAD

#6 opened about 1 month ago by

yichunkuo