Hu's picture

6

Hu

YalunHu

·

AI & ML interests

None yet

Organizations

None yet

YalunHu's activity

New activity in jinaai/jina-embeddings-v2-base-en 4 months ago

Some weights of the model checkpoint at ./model_dir were not used when initializing BertModel

#30 opened over 1 year ago by

New activity in Salesforce/codet5p-110m-embedding 5 months ago

What is the best metric choice when retrieve code snippets based on the embeddings L2 or IP or Cosine similarity?

#4 opened 5 months ago by

New activity in BAAI/bge-large-zh-v1.5 7 months ago

Why does the max-position-embedding only has 512?

#26 opened 7 months ago by

New activity in Qwen/Qwen2-7B-Instruct 8 months ago

How to do continue-pre-training on the 7B-Instruct model?

#13 opened 8 months ago by

New activity in deepseek-ai/deepseek-coder-33b-instruct 9 months ago

Why we do not set the <EOT> token as a special token?

#28 opened 9 months ago by

New activity in meta-llama/Meta-Llama-3-8B-Instruct 10 months ago

Max output tokens?

#12 opened 11 months ago by