Kashif Rasul

kashif's activity

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

liked a Space about 13 hours ago

Running

Featured

31

Distilling 100B+ Models 40x Faster with TRL

📝

31

TRL distillation for 100B+ teachers, 40x faster

liked a Space 7 days ago

Running

25

JEPA Wiki

🧠

25

Explore JEPA research and concepts in an interactive wiki

liked a dataset 11 days ago

hq-bench/quito-corpus

Viewer • Updated 15 days ago • 313M • 75 • 4

upvoted an article 13 days ago

view article

Article

How I contributed a new model to the Transformers library using Codex

• 

14 days ago

•

45

upvoted an article 14 days ago

view article

Article

Transformers.js v4: Now Available on NPM!

• 
• 

Feb 9

•

92

liked a Space 18 days ago

Running on Zero

6

LLaDA 2.1

🚀

6

Large Language Diffusion Models

New activity in kuleshov-group/bd3lm-owt-block_size16 19 days ago

Add post_init() and register_buffer(persistent=False) for transformers v5

#3 opened 19 days ago by

kashif

New activity in kuleshov-group/bd3lm-owt-block_size8 19 days ago

Add post_init() and register_buffer(persistent=False) for transformers v5

#2 opened 19 days ago by

kashif

commented a paper 19 days ago

LLaDA2.1: Speeding Up Text Diffusion via Token Editing

Paper • 2602.08676 • Published Feb 9 • 70 •

5

New activity in kuleshov-group/bd3lm-owt-block_size4 19 days ago

Add post_init() call for transformers v5 compatibility

#2 opened 19 days ago by

kashif

commentedon Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries 20 days ago

view reply

Thanks, @Jackmin108 . Do you mind opening a PR to update the context with references via: https://github.com/huggingface/blog/blob/main/async-rl-training-landscape.md

New activity in inclusionAI/LLaDA2.1-mini 26 days ago

fixes for transforemrs v5

2

#4 opened 29 days ago by

kashif

New activity in inclusionAI/LLaDA2.0-mini-CAP 29 days ago

fix: align RotaryEmbedding and _init_weights with Qwen2Moe for transformers compat

#2 opened 29 days ago by

kashif

New activity in inclusionAI/LLaDA2.1-flash 29 days ago

fix: align RotaryEmbedding with Qwen2Moe pattern for transformers compat

1

#4 opened 29 days ago by

kashif

updated a model about 1 month ago

kashif/stormcast-regression-conus-v0

Image-to-Image • Updated about 1 month ago

upvoted 3 articles about 1 month ago

view article

Article

The ML Engineer's Guide to Protein AI

• 

Mar 3

•

31

view article

Article

Introducing Storage Buckets on the Hugging Face Hub

• 
• 
• +10

Mar 10

•

191

view article

Article

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

• 
• 
• +7

Mar 10

•

124

published an article about 1 month ago

view article

Article

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

• 
• 
• +7

Mar 10

•

124

upvoted an article about 1 month ago

view article

Article

TiRex on the Edge

• 

Mar 5

•

13