Anthony

depasquale's activity

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

New activity in mlx-community/gemma-3n-E4B-it-4bit 5 days ago

Why mlx-vlm not mlx-lm?

3

#2 opened 7 days ago by

olegshulyakov

Got bug when loading model with `mlx-vlm`

👍 1

2

#1 opened 7 days ago by

GiaHuy

updated a model 17 days ago

mlx-community/gemma-3n-E4B-it-4bit

Image-Text-to-Text • Updated about 3 hours ago • 1.92k • 1

published a model 17 days ago

mlx-community/gemma-3n-E4B-it-4bit

Image-Text-to-Text • Updated about 3 hours ago • 1.92k • 1

updated a model 17 days ago

mlx-community/gemma-3n-E2B-it-4bit

Image-Text-to-Text • 2B • Updated 1 day ago • 1.65k • 4

published a model 17 days ago

mlx-community/gemma-3n-E2B-it-4bit

Image-Text-to-Text • 2B • Updated 1 day ago • 1.65k • 4

New activity in Qwen/Qwen3-Embedding-8B 18 days ago

Is `tie_word_embeddings: false` correct for this model?

#17 opened 18 days ago by

depasquale

New activity in mlx-community/Qwen3-Embedding-8B-4bit-DWQ 20 days ago

Update config.json

#3 opened 20 days ago by

depasquale

New activity in google/gemma-3-4b-it 29 days ago

Missing values in 4B, 12B config.json

2

#56 opened 29 days ago by

depasquale

New activity in mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit about 1 month ago

tokenizer_config.json is not correct

12

#1 opened about 1 month ago by

depasquale

New activity in mlx-community/Qwen3-14B-4bit-AWQ 2 months ago

Please use standard naming convention for MLX Community

#1 opened 2 months ago by

depasquale

New activity in google/gemma-3-27b-it 3 months ago

Function calling with Gemma 3

5

#24 opened 4 months ago by

jasonisaac

New activity in mlx-community/mlx-my-repo 4 months ago

Please fix naming scheme

4

#37 opened 4 months ago by

depasquale

updated a Space 4 months ago

Running

121

121

MLX My Repo

🐐

Convert and upload Hugging Face models to MLX format

New activity in mlx-community/DeepSeek-R1-Distill-Qwen-1.5B-4bit 4 months ago

after updating file! model response is changed! now <think> tag is missing for this model from the beganing of the response. critical issue!

3

#2 opened 5 months ago by

Norixxxx

New activity in mlx-community/Phi-4-mini-instruct-4bit 5 months ago

Please rename

11

#1 opened 5 months ago by

depasquale

New activity in Qwen/Qwen2.5-VL-3B-Instruct 5 months ago

Vision tokens missing from chat template

4

#11 opened 5 months ago by

depasquale

liked a model 6 months ago

hexgrad/Kokoro-82M

Text-to-Speech • Updated Apr 10 • 1.5M • • 4.65k

New activity in meta-llama/Llama-3.1-8B-Instruct 6 months ago

Improve chat template for function calling

1

#170 opened 6 months ago by

depasquale

new tokenizer contains the cutoff date and today date by default

5

#74 opened 12 months ago by

yuchenlin