yex

xiaoxiao218's activity

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

New activity in deepseek-ai/DeepSeek-V4-Pro 2 days ago

I'm very disappointed in this release

🔥➕ 12

10

#131 opened 4 days ago by

Dampfinchen

New activity in Qwen/Qwen3-Next-80B-A3B-Thinking 8 months ago

The Thinking model has a higher hallucination rate than the Instruct model and tends to overlook details in long contexts.

1

#4 opened 8 months ago by

xiaoxiao218

The Thinking model has a higher hallucination rate than the Instruct model and tends to overlook details in long contexts.

1

#4 opened 8 months ago by

xiaoxiao218