Shenzhi Wang

shenzhi-wang's activity

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

commented a paper 4 months ago

LLM-based Optimization of Compound AI Systems: A Survey

Paper • 2410.16392 • Published Oct 21, 2024 • 14 •

2

New activity in shenzhi-wang/Llama3.1-70B-Chinese-Chat 6 months ago

部署了一下试用，非常感谢这样的工作

3

#2 opened 7 months ago by

WEI21321

New activity in shenzhi-wang/Llama3-8B-Chinese-Chat-GGUF-8bit 6 months ago

中文模型很弱智

1

#10 opened 6 months ago by

Jerry-SDUA

New activity in shenzhi-wang/Llama3.1-8B-Chinese-Chat 6 months ago

根本没法用，它认为 ”你好吗“有5个汉字

1

#15 opened 6 months ago by

Jerry-SDUA

这个是训练的词库特地指定的？

2

#13 opened 6 months ago by

roamerxv

坐等70b chinese

1

#1 opened 7 months ago by

iwaitu

遇到了无穷回复问题

6

#4 opened 7 months ago by

Orion-zhen

训练数据模板是什么

1

#6 opened 7 months ago by

Libraone

感觉效果不如之前orpo的llama3

2

#8 opened 7 months ago by

ztyl-tech

大佬。啥时候出3.1的4bit版本啊

1

#9 opened 7 months ago by

shenbushou

config.json中的rope_scaling字段为什么没有包含type和factor？

2

#11 opened 6 months ago by

Alexcccn

New activity in shenzhi-wang/Llama3.1-8B-Chinese-Chat 7 months ago

Train data?

2

#5 opened 7 months ago by

yyq90

New activity in shenzhi-wang/Llama3.1-70B-Chinese-Chat 7 months ago

遇到了和8b版本一样的无限输出问题

1

#5 opened 7 months ago by

Orion-zhen

希望有一个30G左右的量化版本

2

#1 opened 7 months ago by

yxh0774

New activity in shenzhi-wang/Llama3-70B-Chinese-Chat 7 months ago

请问加载这个模型要多少GPU？我24000+的提示out of memory

1

#10 opened 8 months ago by

zyc1128

[AUTOMATED] Model Memory Requirements

#12 opened 7 months ago by

model-sizer-bot

New activity in shenzhi-wang/Gemma-2-9B-Chinese-Chat 7 months ago

Better formatting for CAUTION

2

#1 opened 7 months ago by

mishig

New activity in shenzhi-wang/Gemma-2-27B-Chinese-Chat 7 months ago

Default to eager attention

2

#1 opened 7 months ago by

lysandre

New activity in shenzhi-wang/Llama3-70B-Chinese-Chat-GGUF-4bit 8 months ago

中文理解有点差

1

#2 opened 9 months ago by

chaochaoli

New activity in shenzhi-wang/Llama3-8B-Chinese-Chat 9 months ago

error

#42 opened 9 months ago by

LuffyDreams