Road To AGI

roadtoagi's activity

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

New activity in cyankiwi/Qwen3-30B-A3B-Instruct-2507-AWQ-4bit 10 months ago

Does this work with vllm?

7

#1 opened 10 months ago by

Ainonake

New activity in unsloth/Qwen3-235B-A22B-GGUF about 1 year ago

It seems like model have serious repetition issues (both gguf and on openrouter)

6

#8 opened about 1 year ago by

roadtoagi

[Qwen3-235B-A22B-UD-Q4_K_XL.gguf] UD Quant seems to be invalid.

2

#7 opened about 1 year ago by

XelotX

Ud quants please🥺

2

#5 opened about 1 year ago by

Ainonake

Test on 3090 + Tesla P40 (48gb vram total) + 64gb ram (Q2K)

1

#6 opened about 1 year ago by

roadtoagi

New activity in answerdotai/ModernBERT-base over 1 year ago

nan or 0.0 loss when training with flash attention

16

#59 opened over 1 year ago by

roadtoagi

nan or 0.0 loss when training with flash attention

16

#59 opened over 1 year ago by

roadtoagi

nan or 0.0 loss when training with flash attention

16

#59 opened over 1 year ago by

roadtoagi