liyang31163150

liyang31163150's activity

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

New activity in deepseek-ai/DeepSeek-V3 14 days ago

无辅助损失专家偏置代码实现的小问题 A Small Issue in the Code Implementation of Auxiliary-Loss-Free Load Balancing Expert Bias

#89 opened 14 days ago by

liyang31163150

无辅助损失的专家路由

2

#56 opened 2 months ago by

qing9

New activity in fnlp/moss-moon-003-sft-plugin-int4 almost 2 years ago

moss-moon-003-sft-plugin-int4运行提示not a folder containing a `.index.json` file

13

#1 opened almost 2 years ago by

citibank

New activity in lmsys/vicuna-13b-delta-v1.1 almost 2 years ago

Can you provide the merged version（with llama version）

1

#2 opened almost 2 years ago by

liyang31163150

Maybe some tokenizer files are missing?

10

#1 opened almost 2 years ago by

lpy86786

New activity in eachadea/ggml-vicuna-7b-1.1 almost 2 years ago

AutoModelForCausalLM.from_pretrained() error

1

#2 opened almost 2 years ago by

liyang31163150