Awni Hannun's picture

66 3 5

Awni Hannun

awni

apple

·

https://www.awnihannun.com/

AI & ML interests

None yet

Recent Activity

updated a model about 5 hours ago

mlx-community/GLM-5-4bit

published a model about 5 hours ago

mlx-community/GLM-5-4bit

new activity about 7 hours ago

mlx-community/Jan-v2-VL-med-4bit-mlx:Missing tie_word_embeddings in config.json causes incorrect weight tying

View all activity

Organizations

New activity in mlx-community/Jan-v2-VL-med-4bit-mlx about 7 hours ago

Missing tie_word_embeddings in config.json causes incorrect weight tying

#1 opened about 11 hours ago by

New activity in MiniMaxAI/MiniMax-M2.1 21 days ago

Transformers v5 support

#15 opened about 1 month ago by

New activity in MiniMaxAI/MiniMax-M2.1 about 1 month ago

Update tokenizer_config.json

#14 opened about 1 month ago by

New activity in mlx-community/MiniMax-M2.1-4bit about 1 month ago

Update tokenizer_config.json

#3 opened about 1 month ago by

New activity in mlx-community/DeepSeek-V3-0324-4bit 5 months ago

How to get such good quality as this quant? (For translations)

#3 opened 6 months ago by

New activity in mlx-community/mlx-my-repo 6 months ago

Fail early if model requires `trust_remote_code`

#63 opened 6 months ago by

New activity in mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit 6 months ago

Model size

#1 opened 7 months ago by

New activity in mlx-community/Qwen3-30B-A3B-Instruct-2507-6bit-DWQ-lr5e-9 6 months ago

Protocol for experiments

#1 opened 6 months ago by

New activity in Qwen/Qwen3-Coder-480B-A35B-Instruct 7 months ago

Update README.md

#4 opened 7 months ago by

New activity in google/gemma-3-4b-it 7 months ago

Tokenizer's `model_max_length` unusual value

#48 opened 10 months ago by

New activity in rednote-hilab/dots.llm1.inst 8 months ago

eos token id mismatch

#12 opened 8 months ago by

New activity in mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit 9 months ago

tokenizer_config.json is not correct

#1 opened 9 months ago by

New activity in mlx-community/Qwen3-235B-A22B-4bit 9 months ago

Token generation speed is very slow

#4 opened 9 months ago by

New activity in mlx-community/Qwen3-235B-A22B-8bit 9 months ago

Model not found..?

#1 opened 9 months ago by

New activity in mlx-community/gemma-3-12b-it-qat-4bit 10 months ago

bfloat16-conversion

#1 opened 10 months ago by

New activity in mlx-community/mlx-my-repo 11 months ago

Error when converting huihui-ai/Llama-3.2-3B-Instruct-abliterated: Received parameters not in model: lm_head.weight.

#36 opened 12 months ago by

New activity in mlx-community/mlx-my-repo 12 months ago

Error converting microsoft/Phi-4-mini-instruct: Shapes (48) and (64) cannot be broadcast.

#35 opened 12 months ago by

New activity in mlx-community/DeepSeek-V3-4bit about 1 year ago

VRAM Requirements for Running the Model

#1 opened about 1 year ago by

New activity in mlx-community/DeepSeek-V3-3bit-bf16 about 1 year ago

3bit-bf16

#1 opened about 1 year ago by

New activity in mlx-community/DeepSeek-V3-3bit about 1 year ago

Upload folder using huggingface_hub

#1 opened about 1 year ago by