Su Zhu

suzhu001's activity

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

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

Reset attention mask across doc boundary

3

#14 opened over 1 year ago by

jimmyhbx

New activity in internlm/internlm2-chat-20b almost 2 years ago

tokenizer adds default eos_token_id while build_inputs function adds eos_token too!

#9 opened almost 2 years ago by

suzhu001