Hugging Face's logo
michael jefferson's picture
8 1 47

michael jefferson

520jefferson
21world's profile picture
·

AI & ML interests

None yet

Recent Activity

liked a model 3 days ago
RLHFlow/Llama3.1-8B-PRM-Deepseek-Data
liked a dataset 3 days ago
SimpleBerry/OpenLongCoT-SFT
upvoted a paper 6 days ago
Qwen2.5 Technical Report
View all activity

Organizations

Skywork's profile picture

520jefferson's activity

New activity in breezedeus/pix2text-mfr 2 months ago

Run on iOS

4
#1 opened 8 months ago by
evgeniymikholap
New activity in qihoo360/360LayoutAnalysis 4 months ago

模型能区分下吗？

2
#2 opened 4 months ago by
520jefferson
New activity in Qwen/Qwen1.5-14B 6 months ago

在此基础上能训练100k吗？
#6 opened 6 months ago by
520jefferson
New activity in deepseek-ai/DeepSeek-V2-Chat 6 months ago

How much memory is needed if you make the 128k context length

1
#13 opened 7 months ago by
ggbondcxk
New activity in ZenMoore/RoleBench 11 months ago

multiturn roleplay

2
#2 opened 11 months ago by
520jefferson
New activity in Phind/Phind-CodeLlama-34B-v2 about 1 year ago

what's wrong with my program. i just use input() to get the prompt and give it to the generation, then i got this below.
#30 opened about 1 year ago by
520jefferson
New activity in THUDM/chatglm3-6b-32k about 1 year ago

how can i limit the generate length , i haven't see the new max length in chat().

2
#6 opened about 1 year ago by
520jefferson

my i use deepspeed to accelerate the model infer process?

1
#5 opened about 1 year ago by
520jefferson