Anmol Reddy

molereddy's activity

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

New activity in neuralmagic/Meta-Llama-3.1-70B-Instruct-quantized.w8a16 about 2 months ago

Poorer performance than W8A8

#6 opened about 2 months ago by

molereddy

New activity in CalamitousFelicitousness/Qwen2.5-0.5B-Instruct-fp8-dynamic 2 months ago

How was the quantization performed - do you have a recipe?

#1 opened 2 months ago by

molereddy

New activity in neuralmagic/Meta-Llama-3.1-70B-Instruct-quantized.w8a16 2 months ago

Is this the standard GPTQ quantization?

1

#5 opened 2 months ago by

molereddy

New activity in neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16 2 months ago

Model weights are not loaded

4

#3 opened 5 months ago by

MarvelousMouse