9 1 47

michael jefferson

520jefferson

520jefferson

AI & ML interests

None yet

Recent Activity

new activity about 12 hours ago

deepseek-ai/DeepSeek-V3-Base:模型区别

liked a model 4 days ago

RLHFlow/Llama3.1-8B-PRM-Deepseek-Data

liked a dataset 4 days ago

SimpleBerry/OpenLongCoT-SFT

View all activity

Organizations

520jefferson's activity

New activity in deepseek-ai/DeepSeek-V3-Base about 12 hours ago

模型区别

#22 opened about 12 hours ago by

520jefferson

New activity in breezedeus/pix2text-mfr 2 months ago

Run on iOS

#1 opened 8 months ago by

evgeniymikholap

New activity in qihoo360/360LayoutAnalysis 4 months ago

模型能区分下吗？

#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

#13 opened 7 months ago by

ggbondcxk

New activity in ZenMoore/RoleBench 11 months ago

multiturn roleplay

#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().

#6 opened about 1 year ago by

520jefferson

my i use deepspeed to accelerate the model infer process?

#5 opened about 1 year ago by

520jefferson