Kashif Rasul

kashif's activity

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

commented 2 papers 4 months ago

On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes

Paper • 2306.13649 • Published Jun 23, 2023 • 16 •

2

Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning

Paper • 2407.18248 • Published Jul 25 • 31 •

4

New activity in hf-internal-testing/llama-tokenizer 4 months ago

chat template is none

#4 opened 4 months ago by kashif

commented a paper 5 months ago

LETS-C: Leveraging Language Embedding for Time Series Classification

Paper • 2407.06533 • Published Jul 9 • 2 •

5

New activity in google/timesfm-1.0-200m 7 months ago

add time-series tag

2

#5 opened 7 months ago by kashif

Update tag

3

#3 opened 7 months ago by nielsr

add time-series tag

#4 opened 7 months ago by kashif

update the load_from_checkpoint

#2 opened 7 months ago by kashif

New activity in huggingface/documentation-images 10 months ago

add images for patchtst blog

1

#267 opened 10 months ago by kashif

[pref-tuning] updated images for blog post

#265 opened 10 months ago by kashif

New activity in huggingface/documentation-images 11 months ago

plots for blogpost

#257 opened 11 months ago by kashif

New activity in HuggingFaceH4/orca_dpo_pairs 11 months ago

initial model card

#1 opened 11 months ago by kashif

New activity in laion/CLIP-ViT-bigG-14-laion2B-39B-b160k 11 months ago

Add projection dim to text and vision model configs for CLIPVisionModelWithProjection and CLIPTextModelWithProjection support

1

#15 opened 11 months ago by kashif

New activity in huggingface/documentation-images 11 months ago

patchtstmixer blog post images

#253 opened 11 months ago by kashif

New activity in trl-lib/OpenHermes-2-Mistral-7B-ipo-beta-0.1-steps-200 11 months ago

Do you have results?

4

#1 opened 11 months ago by Hugs4Llamas

New activity in togethercomputer/StripedHyena-Nous-7B 12 months ago

checkpoint() method is missing

1

#4 opened 12 months ago by kashif

New activity in Monash-University/monash_tsf about 1 year ago

update hourly prediction lengths

#5 opened about 1 year ago by kashif

New activity in huggingface/documentation-images about 1 year ago

trl ddpo blog images

#191 opened about 1 year ago by kashif

New activity in huggingface/documentation-images over 1 year ago

images for distill_sd blog post

2

#148 opened over 1 year ago by kashif

added files for blog post 149

4

#110 opened over 1 year ago by kashif