Alchan Kim

Alchan's activity

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

New activity in neuralmagic/Meta-Llama-3-8B-Instruct-FP8 3 months ago

Potential problematic behavior of truncation and/or padding?

1

#5 opened 3 months ago by Alchan

New activity in neuralmagic/Meta-Llama-3-8B-Instruct-FP8 5 months ago

`model.safetensors.index.json` still has the legacy name`act_scale` for activation scales

1

#3 opened 5 months ago by Alchan