Young Jin Kim

ykim362's activity

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

New activity in microsoft/Phi-4-mini-instruct 10 days ago

[Bug]:Phi-4-Mini giving garbage outputs with torch 2.5.1 and vllm==0.7.3 with multiple parallel requests on Long context prompts #14058

4

#11 opened 14 days ago by

raghavgg

New activity in microsoft/Phi-4-mini-instruct 11 days ago

pipeline for text generation seems to be giving garbage outputs

2

#12 opened 13 days ago by

lunahr

commented a paper 13 days ago

Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs

Paper • 2503.01743 • Published 13 days ago • 72 •

6

New activity in unsloth/Phi-4-mini-instruct 16 days ago

Phi-4 mini does not work inside of unsloth.

5

#1 opened 18 days ago by

Pinkstack

New activity in microsoft/Phi-4-mini-instruct 16 days ago

Update README.md

#10 opened 16 days ago by

ykim362

Update README.md

#9 opened 16 days ago by

ykim362

Different number of attention heads, makes rotary_ndims vs rope scaling factors wrong?

14

#1 opened 18 days ago by

bartowski

New activity in microsoft/Phi-3.5-MoE-instruct 6 months ago

VRAM requirements

1

#43 opened 6 months ago by

otacilio-psf

QAT

3

#42 opened 6 months ago by

rezzie-rich

need gguf

19

#4 opened 7 months ago by

windkkk

New activity in microsoft/Phi-3.5-MoE-instruct 7 months ago

The model 'PhiMoEForCausalLM' is not supported for text-generation. Supported models are ['BartForCausalLM', 'BertLMHeadModel', .......

11

#34 opened 7 months ago by

xxbadarxx

The provided example doesn't work

5

#32 opened 7 months ago by

kqsong

New activity in microsoft/Phi-3.5-mini-instruct 7 months ago

What changed for people using this model in english?

3

#3 opened 7 months ago by

migueltalka

New activity in microsoft/Phi-3.5-MoE-instruct 7 months ago

About training mem usage for moe

3

#2 opened 7 months ago by

lucasjin