tianzujie

tian9's activity

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

upvoted a paper 4 days ago

A Survey of Reinforcement Learning for Large Reasoning Models

Paper • 2509.08827 • Published 5 days ago • 139

liked a model 4 days ago

baidu/ERNIE-4.5-21B-A3B-Thinking

Text Generation • 22B • Updated 4 days ago • 100k • 675

upvoted a collection 7 months ago

LlavaGuard

Collection

This collection contains the original repos of the LlavaGuard releases • 19 items • Updated May 12 • 7

updated a dataset 7 months ago

tian9/lab1

Viewer • Updated Feb 19 • 819

published a dataset 7 months ago

tian9/lab1

Viewer • Updated Feb 19 • 819

updated a dataset 9 months ago

tian9/copyright_roles

Preview • Updated Dec 24, 2024 • 1

updated a dataset 10 months ago

tian9/flower_classification

Viewer • Updated Dec 4, 2024 • 3.67k • 1

New activity in therem/CLEAR 10 months ago

Will the weight of the model after unlearn be disclosed in the future?

2

#3 opened 11 months ago by

tian9

New activity in meta-llama/Meta-Llama-3-8B-Instruct 11 months ago

PretrainedTokenizerFast has no attribute 'legacy'

3

#43 opened over 1 year ago by

tian9

New activity in meta-llama/Meta-Llama-3-8B over 1 year ago

How can I eval the quality and literariness of generation by this model ?

#97 opened over 1 year ago by

tian9

Tokenizer.pad_token_id is NoneType, which requires float

2

#36 opened over 1 year ago by

tian9