Joao Gante

joaogante's activity

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

New activity in google/diffusiongemma-26B-A4B-it 3 months ago

fix: chat template — null handling, reasoning preservation, turn-tag balance, input validation

1

#23 opened 3 months ago by

joaogante

License clarification

2

#22 opened 3 months ago by

Lounafa1

New activity in mlx-community/diffusiongemma-26B-A4B-it-nvfp4 3 months ago

Update chat_template.jinja

#1 opened 3 months ago by

joaogante

New activity in mlx-community/diffusiongemma-26B-A4B-it-mxfp8 3 months ago

Update chat_template.jinja

#1 opened 3 months ago by

joaogante

New activity in mlx-community/diffusiongemma-26B-A4B-it-mxfp4 3 months ago

Update chat_template.jinja

#1 opened 3 months ago by

joaogante

New activity in mlx-community/diffusiongemma-26B-A4B-it-8bit 3 months ago

Update chat_template.jinja

#2 opened 3 months ago by

joaogante

New activity in mlx-community/diffusiongemma-26B-A4B-it-bf16 3 months ago

Update chat_template.jinja

#1 opened 3 months ago by

joaogante

New activity in mlx-community/diffusiongemma-26B-A4B-it-6bit 3 months ago

Update chat_template.jinja

#1 opened 3 months ago by

joaogante

New activity in mlx-community/diffusiongemma-26B-A4B-it-5bit 3 months ago

Update chat_template.jinja

#1 opened 3 months ago by

joaogante

New activity in mlx-community/diffusiongemma-26B-A4B-it-4bit 3 months ago

Update chat_template.jinja

#3 opened 3 months ago by

joaogante

New activity in mlx-community/diffusiongemma-26B-A4B-it-OptiQ-4bit 3 months ago

Update chat_template.jinja

👍 1

#1 opened 3 months ago by

joaogante

New activity in google/diffusiongemma-26B-A4B-it 3 months ago

Add files for diffusers loading

4

#20 opened 3 months ago by

dg845

Update non-thinking chat template

1

#15 opened 3 months ago by

joaogante

Custom chat template: empty content in multi-turn conversations (with fix)

1

#16 opened 3 months ago by

buzman

RuntimeError: Tensor.item() cannot be called on meta tensors

4

#6 opened 4 months ago by

kimyong95

New activity in google/diffusiongemma-26B-A4B-it 4 months ago

Argument input_ids not found in the forward method

👍 5

5

#5 opened 4 months ago by

mohamedemam

New activity in transformers-community/contrastive-search 12 months ago

Update cache format

#3 opened 12 months ago by

cyrilvallez

New activity in transformers-community/group-beam-search 12 months ago

downcast the scores after upcasting to prevent runtime errors

1

#1 opened 12 months ago by

ischemist

New activity in ByteDance-Seed/Seed-OSS-36B-Instruct about 1 year ago

Prevent tokenizer calls from returning `token_type_ids`

❤️ 1

2

#26 opened about 1 year ago by

joaogante

New activity in ByteDance-Seed/Seed-OSS-36B-Base about 1 year ago

Prevent tokenizer calls from returning `token_type_ids`

#5 opened about 1 year ago by

joaogante