🔄 In a Training Loop

Asankhaya Sharma

codelion

hugging-science

·

http://asankhaya.github.io/

AI & ML interests

Creator of OptiLLM, OpenEvolve, Adaptive Classifier, and Ellora. Pioneering a new category in AI infrastructure: inference-time compute for LLMs.

Recent Activity

updated a dataset about 10 hours ago

adaptive-classifier/ai-detector-data

new activity 1 day ago

zero-gpu-explorers/README:ZeroGPU clone fails during tensor packing with Errno 28 — 82.1 GB pack target

new activity 1 day ago

google/timesfm-3.0-pytorch:MCP server: call TimesFM-3 from Claude / Cursor (median + q10–q90)

View all activity

Organizations

updated a dataset about 10 hours ago

adaptive-classifier/ai-detector-data

Viewer • Updated about 6 hours ago • 2.17k • 1.01k • 4

New activity in zero-gpu-explorers/README 1 day ago

ZeroGPU clone fails during tensor packing with Errno 28 — 82.1 GB pack target

#185 opened 1 day ago by

New activity in google/timesfm-3.0-pytorch 1 day ago

MCP server: call TimesFM-3 from Claude / Cursor (median + q10–q90)

#2 opened 2 days ago by

liked a model 2 days ago

mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B

Text Generation • 19B • Updated 8 days ago • 526 • 1

commented on Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI 2 days ago

The Fleet part may matter as much as the kernels. The 809 comparable cases on an M4 are useful, but browser, driver and device variance is where WebGPU tends to get painful. Will Fleet eventually expose per-device distributions, or is the plan to use the runs only for aggregate selection rules?

upvoted a paper 2 days ago

H3-World: Turning Language Understanding into World Control

Paper • 2609.01560 • Published 4 days ago • 47

liked 2 models 2 days ago

npario/Qwen3.8-27B-MLX-5bit

Image-Text-to-Text • 27B • Updated 3 days ago • 144 • 1

ByteDance/Ouro-1.4B

Text Generation • 1B • Updated Jan 18 • 22.2k • 146

liked a dataset 3 days ago

VoiceArena/MonsoonASR-Open-ASR-leaderboard-hi-IN

Viewer • Updated 6 days ago • 753 • 168 • 2

liked a model 3 days ago

CabbageWyh/PaperGym-Model

Updated 4 days ago • 3

New activity in onnx-community/OmniVoice-Onnx 4 days ago

Is this model compatible with Transformers.js?

#2 opened 7 days ago by

liked 2 models 4 days ago

jingyaogong/minimind-3

63.9M • Updated Apr 4 • 798 • 14

inductiveML/Qwen3.6-35B-A3B-evolved-mxbit

Text Generation • 35B • Updated Jun 17 • 101 • 2

liked 3 models 5 days ago

pipecat-ai/phonellm-alpha-1

Text Generation • 32B • Updated 5 days ago • 18.9k • 209

FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree

Text-to-Video • 35B • Updated 7 days ago • 267

peculiar-ragdoll/Dirk-Qwen3.8-27B-MLX-oQ4e

Image-Text-to-Text • 28B • Updated 1 day ago • 1.54k • 11

updated a model 6 days ago

mlx-community/gpt-oss-20b-OptiQ-4bit

Text Generation • 21B • Updated 6 days ago • 11.5k • 8

liked 3 models 6 days ago

mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B

Text Generation • 19B • Updated 7 days ago • 352 • 2

mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit-REAP-18B

Text Generation • 19B • Updated 7 days ago • 702 • 3

mlx-community/gemma-4-26B-A4B-it-OptiQ-4bit-REAP-14B

Text Generation • 14B • Updated 7 days ago • 978 • 3