Alyssa Vance

alyssavance's activity

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

New activity in togethercomputer/LLaMA-2-7B-32K about 1 year ago

Training diverges when used with Llama 2 70B and 4-bit QLoRA

3

#10 opened about 1 year ago by alyssavance

Training diverges when used with Llama 2 70B and 4-bit QLoRA

3

#10 opened about 1 year ago by alyssavance