Resources

Deos baichuan2_13B_chat support function calling ?

#40 opened about 2 months ago by

daisr

Fast tokenizer

#39 opened about 2 months ago by

soominc

使用哪个加速推理框架比较好？

#38 opened 2 months ago by

daisr

Adding `safetensors` variant of this model

#37 opened 2 months ago by

SFconvertbot

Can not infer, depolyed Baichuan2-13b-Chat with 2x RTX3090 24G and FastChat.

#36 opened 3 months ago by

Rethen

如何流式输出

#35 opened 3 months ago by

DeyangKong

百川大模型本地量化部署的问题

#34 opened 3 months ago by

Jason123321123

v2的具体提升

#32 opened 5 months ago by

YueJie

部署Baichuan2-13b-chat时候使用官网代码推理输出的时候报错

#31 opened 6 months ago by

lhlnlp

update modeling_baichuan.py for torchscript mode with past_kv

#30 opened 6 months ago by

changwangss

各位大佬，微调baichuan2-13b后得到pth文件，该如何推理

#29 opened 6 months ago by

ddq2020

Asking about new version of Baichuan LLM

#28 opened 6 months ago by

phamvantoan

Update modeling_baichuan.py

#27 opened 6 months ago by

ybelkada

Asking about the performance of retrieving local data

#25 opened 7 months ago by

phamvantoan

Asking about prompt template for Baichuan2-13B-Chat

#24 opened 7 months ago by

phamvantoan

AttributeError: 'list' object has no attribute 'as_dict'

#23 opened 7 months ago by

RR0825

how to accelerate the inference speed

#22 opened 7 months ago by

tobywang

Baichuan 2 192k context length

#21 opened 7 months ago by

Ekolawole

baichuan 192K weight release?

#20 opened 7 months ago by

Yhyu13

AttributeError: 'BaichuanTokenizer' object has no attribute 'sp_model'

#18 opened 8 months ago by

lucasjin

关于Alibi位置编码

#17 opened 8 months ago by

Hunter1943

百川大模型本地部署

#14 opened 9 months ago by

Yuwh07

Update modeling_baichuan.py

#12 opened 9 months ago by

JaheimLee

xops使用与7B模型不一致

#11 opened 9 months ago by

JaheimLee

使用fastchat加载百川2，性能与魔搭的demo差距非常大

#10 opened 9 months ago by

ye7love7

model

#9 opened 9 months ago by

bzxlZhou

model

#8 opened 9 months ago by

bzxlZhou