Sherman Chann's picture

Sherman Chann

152334H

·

https://152334H.github.io

152334H

AI & ML interests

None yet

Organizations

152334H's activity

commented a paper 3 months ago

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27 • 566 •

New activity in 152334H/miqu-1-70b-hermes2.5-qlora 3 months ago

What are tokens 32002:32031

#1 opened 3 months ago by

New activity in 152334H/miqu-1-70b-sf 3 months ago

vllm support?

#19 opened 3 months ago by

Remove extra degrees of freedom by dequantizing the `q5_K_M`, `q4_K_M` and `q2_K` models together?

#18 opened 3 months ago by

Sticking a restrictive license on a model that's not even yours to begin with?

#14 opened 3 months ago by

2.4bpp exl2 waiting room

#3 opened 4 months ago by

New activity in 152334H/miqu-1-70b-sf 4 months ago

Model load fail

#13 opened 4 months ago by

Chat template

#11 opened 4 months ago by

Commerical Use?

#12 opened 4 months ago by

more quantized versions？

#10 opened 4 months ago by

New activity in miqudev/miqu-1-70b 4 months ago

An interesting yet useless consideration over the fp16 being out or not.

#21 opened 4 months ago by

New activity in 152334H/miqu-1-70b-sf 4 months ago

Adding tokenizer to the repo (request/suggestion)

#9 opened 4 months ago by

Adding Evaluation Results

#8 opened 4 months ago by

Fix config.json

#6 opened 4 months ago by

add chat template

#5 opened 4 months ago by

New activity in 152334H/miqu-1-70b-exl2 4 months ago

Is a higher quant possible?

#1 opened 4 months ago by

New activity in 152334H/miqu-1-70b-sf 4 months ago

Conversion to pytorch

#1 opened 4 months ago by

Conversion script?

#2 opened 4 months ago by

New activity in elevenlabs/tts about 1 year ago

pshhhhhh not working

#1 opened about 1 year ago by