An Yang's picture

An Yang

yangapku

·

https://scholar.google.com/citations?user=vO9FZekAAAAJ

AI & ML interests

NLP and Deep Learning

Recent Activity

authored a paper 20 days ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

authored a paper 20 days ago

Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability

authored a paper 20 days ago

Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models

View all activity

Organizations

New activity in Qwen/Qwen2.5-Math-RM-72B 9 months ago

Create README.md

#1 opened 9 months ago by

New activity in Qwen/Qwen-7B-Chat-Int4 over 1 year ago

Update README of branch dev_triton.

#11 opened over 1 year ago by

New activity in Qwen/Qwen-7B-Chat almost 2 years ago

Does Qwen support 16k context, what is the best config for max_new_tokens?

#22 opened almost 2 years ago by

RuntimeError: The size of tensor a (8192) must match the size of tensor b (11581) at non-singleton dimension 3

#32 opened almost 2 years ago by

Fix typo

#29 opened almost 2 years ago by

很不错的效果

#30 opened almost 2 years ago by

Load tokenizer and model in no internet kernel?

#33 opened almost 2 years ago by

FlashAttention推理时还是需要关闭，目前开启输出是错乱的

#27 opened almost 2 years ago by

我看模型更新了，有说明吗

#21 opened almost 2 years ago by

New activity in Qwen/Qwen-7B almost 2 years ago

_convert_id_to_token方法没有实现

#1 opened almost 2 years ago by

New activity in OFA-Sys/chinese-clip-vit-large-patch14 over 2 years ago

does it support Chinese and English mixed input?

#1 opened over 2 years ago by

New activity in OFA-Sys/chinese-clip-zero-shot-image-classification over 2 years ago

How can I add context with text input along with the image and the labels?

#5 opened over 2 years ago by

remove styling to fix spacing

#4 opened over 2 years ago by

Minor nit

#3 opened over 2 years ago by