🔄 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

new activity 14 minutes ago

mlx-community/Qwen3.6-27B-OptiQ-4bit:I got the 29 parameters error message for this model

updated a dataset about 1 hour ago

adaptive-classifier/ai-detector-data

new activity about 9 hours ago

migtissera/Tess-4-27B:OptiQ

View all activity

Organizations

New activity in mlx-community/Qwen3.6-27B-OptiQ-4bit 14 minutes ago

I got the 29 parameters error message for this model

#3 opened 34 minutes ago by

New activity in migtissera/Tess-4-27B about 9 hours ago

OptiQ

#6 opened about 10 hours ago by

New activity in tencent/Hy3 about 15 hours ago

Can you do an optiq quant?

#11 opened 2 days ago by

New activity in InternScience/Agents-A1 about 22 hours ago

OptiQ quant

#20 opened about 22 hours ago by

New activity in aisamdasu/Algocean-Qwen3.6-35B-A3B-mlx-OptiQ 1 day ago

Thanks for the quant

#1 opened 1 day ago by

New activity in mlx-community/diffusiongemma-26B-A4B-it-OptiQ-4bit 2 days ago

Update chat_template.jinja

#1 opened 3 days ago by

New activity in zai-org/GLM-5.2 2 days ago

Publish an optiq quant

#42 opened 2 days ago by

New activity in empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF 2 days ago

Can you also release a optiq quant?

#30 opened 2 days ago by

New activity in mlx-community/gpt-oss-20b-OptiQ-4bit 10 days ago

很棒的模型，比其他人的oss-20B都好

#1 opened 10 days ago by

New activity in mlx-community/gemma-4-e4b-it-qat-OptiQ-4bit 15 days ago

Fix Request: Tensor shape mismatch in audio_tower causing complete fallback from VLM to LLM on gemma-4-e4b-it-qat-OptiQ-4bit

#1 opened 16 days ago by

New activity in mlx-community/gemma-4-12B-it-OptiQ-4bit 26 days ago

MLX_LM valueError: Model type gemma4_unified not supported.

#1 opened about 1 month ago by

New activity in codelion/sprog-9m 29 days ago

Add GSM8K eval result (self-reported, symbolic verifier)

#1 opened 29 days ago by

New activity in mlx-community/Qwen3.6-27B-OptiQ-4bit about 1 month ago

Adding the kv_config.json to the repo

#2 opened about 1 month ago by

New activity in HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive about 1 month ago

MLX/AWQ

#11 opened 3 months ago by

New activity in mlx-community/gemma-4-31B-it-OptiQ-4bit about 1 month ago

Throws error in LM Studio with Jinja template

#1 opened about 1 month ago by

New activity in mlx-community/gemma-4-e4b-it-OptiQ-4bit about 1 month ago

Missing parameters

#1 opened about 1 month ago by

New activity in mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit about 1 month ago

Tool Calling Failure: Qwen3.6-35B-A3B-OptiQ-4bit on oMLX

#2 opened 2 months ago by

New activity in mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit about 2 months ago

What is the reason to use this model instead of simple mlx 4 bit?

#1 opened 2 months ago by

New activity in mlx-community/Qwen3.6-27B-OptiQ-4bit 3 months ago

model loses its vision capabilities ?

#1 opened 3 months ago by

New activity in codelion/dhara-70m 6 months ago

1024 in max_position_embeddings

#2 opened 6 months ago by