Awni Hannun

awni's activity

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

New activity in mlx-community/Jan-v2-VL-med-4bit-mlx 3 months ago

Missing tie_word_embeddings in config.json causes incorrect weight tying

#1 opened 3 months ago by

louis-jan

New activity in MiniMaxAI/MiniMax-M2.1 3 months ago

Transformers v5 support

9

#15 opened 4 months ago by

AntonV

New activity in MiniMaxAI/MiniMax-M2.1 4 months ago

Update tokenizer_config.json

🚀 2

1

#14 opened 4 months ago by

awni

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

Update tokenizer_config.json

1

#3 opened 4 months ago by

ArthurZ

New activity in mlx-community/DeepSeek-V3-0324-4bit 8 months ago

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

24

#3 opened 9 months ago by

bibproj

New activity in mlx-community/mlx-my-repo 9 months ago

Fail early if model requires `trust_remote_code`

5

#63 opened 9 months ago by

pcuenq

New activity in mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit 9 months ago

Model size

➕ 1

2

#1 opened 9 months ago by

depasquale

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

Protocol for experiments

👍 3

#1 opened 9 months ago by

awni

New activity in Qwen/Qwen3-Coder-480B-A35B-Instruct 10 months ago

Update README.md

#4 opened 10 months ago by

awni

New activity in google/gemma-3-4b-it 10 months ago

Tokenizer's `model_max_length` unusual value

2

#48 opened about 1 year ago by

awni

New activity in rednote-hilab/dots.llm1.inst 10 months ago

eos token id mismatch

1

#12 opened 10 months ago by

awni

New activity in mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit 11 months ago

tokenizer_config.json is not correct

12

#1 opened 11 months ago by

depasquale

New activity in mlx-community/Qwen3-235B-A22B-4bit 12 months ago

Token generation speed is very slow

4

#4 opened 12 months ago by

huynguyendbs

New activity in mlx-community/Qwen3-235B-A22B-8bit 12 months ago

Model not found..?

2

#1 opened 12 months ago by

balnazzar

New activity in mlx-community/gemma-3-12b-it-qat-4bit about 1 year ago

bfloat16-conversion

#1 opened about 1 year ago by

neilmehta24

New activity in mlx-community/mlx-my-repo about 1 year ago

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

5

#36 opened about 1 year ago by

Felladrin

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

4

#35 opened about 1 year ago by

Felladrin

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

VRAM Requirements for Running the Model

3

#1 opened over 1 year ago by

wilfoderek

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

3bit-bf16

4

#1 opened over 1 year ago by

ehartford

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

Upload folder using huggingface_hub

2

#1 opened over 1 year ago by

awni