Dan Voyce

the1dv's activity

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

New activity in stelterlab/DeepSeek-R1-0528-Qwen3-8B-AWQ 7 months ago

Rope Scaling pre-applied?

6

#1 opened 8 months ago by

the1dv

New activity in mlx-community/DeepSeek-R1-Qwen3-0528-8B-4bit-AWQ 8 months ago

ValueError: There is no module or parameter named 'lm_head.biases' in Qwen3ForCausalLM

2

#1 opened 8 months ago by

the1dv

ValueError: There is no module or parameter named 'lm_head.biases' in Qwen3ForCausalLM

2

#1 opened 8 months ago by

the1dv

New activity in stelterlab/DeepSeek-R1-0528-Qwen3-8B-AWQ 8 months ago

Rope Scaling pre-applied?

6

#1 opened 8 months ago by

the1dv