Zhengxiao Du
zxdu20
AI & ML interests
None yet
Organizations
zxdu20's activity
flash_attention_2
#51 opened 3 months ago
by
zxdu20
Can not inference
1
#4 opened 4 months ago
by
lucasjin
有pro版本开源了吗?
#95 opened 11 months ago
by
LycheeX
fix when use_cache = False,inference 乱码
#85 opened about 1 year ago
by
ShiJueXiaofei
MacBook使用本地下载模型为什么会提示OSError: Can't load the configuration of 'your local path'.
3
#36 opened about 1 year ago
by
Amy0829
Update README.md
#41 opened about 1 year ago
by
Azzeddine-1
Request: DOI
#42 opened about 1 year ago
by
tradequant
Ggml version please
1
#44 opened about 1 year ago
by
Hoioi
Update README.md for typo
#87 opened about 1 year ago
by
Bojun-Feng
It is so faaaaaast!
#30 opened about 1 year ago
by
AIReach
Update README.md
#37 opened about 1 year ago
by
linoUCV
我做SFT微调时,发现tokenizer save的问题,需要改下
2
#13 opened about 1 year ago
by
shibing624
RuntimeError: Internal: src/sentencepiece_processor.cc(1101) [model_proto->ParseFromArray(serialized.data(), serialized.size())]
1
#25 opened about 1 year ago
by
charles2030
这个模型太强大了 , 感受到清华的威力,赞赞赞
#17 opened about 1 year ago
by
yuerski
请教一下推理使用Multi-Query Attention 是需要在训练的时候就要使用Multi-Query Attention训练么
1
#21 opened about 1 year ago
by
zhuhai123
0.0.216 版本 , 引入不了from langchain.document_loaders , 报错
2
#18 opened about 1 year ago
by
yuerski
add default model_type
#10 opened about 1 year ago
by
songyouwei
可以处理更长的上下文,那么max_length应该设置更长?
3
#15 opened about 1 year ago
by
chaochaoli
how to suppress warning Setting `pad_token_id` to `eos_token_id`:2 for open-end generation.
4
#5 opened about 1 year ago
by
huashiyiqike
add missing `model_type`
#9 opened about 1 year ago
by
songyouwei
Add task to model card for discoverability
#6 opened about 1 year ago
by
osanseviero
some problem with cpu
2
#3 opened about 1 year ago
by
zhangbo2008
fix(Tokenizer): fix save_pretrained error
1
#2 opened about 1 year ago
by
sharpbai
peft微调不兼容
1
#7 opened about 1 year ago
by
JaheimLee
完整模型参数下载问题
4
#50 opened over 1 year ago
by
Yuchangz
Avoid Loading CPU kernel if User Have a GPU and Cuda Environment
3
#8 opened over 1 year ago
by
rdo4920
Why cant chinese people just write comments in English ?
5
#47 opened over 1 year ago
by
praff1234
Update modeling_chatglm.py for inputs_embeds
2
#45 opened over 1 year ago
by
Xipotzzz
A slim version of chatglm-6b. Image tokens are removed to save memory and computation.
#8 opened over 1 year ago
by
silver
Error in loding models
1
#10 opened over 1 year ago
by
huvee
[bug] get_position_ids
#11 opened over 1 year ago
by
kebo
离线下载了8个model文件
1
#23 opened over 1 year ago
by
q113
"Local variable ‘context_length’ referenced before assignment" when tokenizing a sentence
1
#39 opened over 1 year ago
by
liliang
Update README.md
1
#25 opened over 1 year ago
by
baby12
skip_init causes bugs when finetuning using deepspeed.
1
#37 opened over 1 year ago
by
sunworshipper
Can you combine ChatGLM-6B with ChatRWKV and Open-Assistant ?
1
#36 opened over 1 year ago
by
anon4364
Create handler.py
1
#18 opened over 1 year ago
by
wensun
Cool Project.
#3 opened over 1 year ago
by
kanseaveg
这个问题有人遇到过吗?请问一下如何解决,昨天运行的好好的,今天不知道为啥突然维度不对应了
1
#30 opened over 1 year ago
by
zxjyes
Fix LogitsProcessor using slim checkpoint
#29 opened over 1 year ago
by
bcol
Rename README.md to hey can
#31 opened over 1 year ago
by
RavyaloMark
Update slim checkpoint
#28 opened over 1 year ago
by
zxdu20
fix typo in use_gmask
#21 opened over 1 year ago
by
fzhang
感谢研究团队
1
#22 opened over 1 year ago
by
kuroneko5943
最新的commit好像有bug,但是不确定该怎么修复
1
#26 opened over 1 year ago
by
qingsonglv
Support single integer or empty list as input to decode
#7 opened over 1 year ago
by
peakji
fix GLM6BBlock name typo
#20 opened over 1 year ago
by
richbrain