 AlpinDale
|
6154031a85
feat: add TP support for bitsandbytes
|
vor 3 Monaten |
 AlpinDale
|
f98e7b2f8c
feat: add HQQ quantization support (#795)
|
vor 3 Monaten |
|
AlpinDale
|
43965f7bd9
fix: kobold lite embedded UI on windows (#797)
|
vor 3 Monaten |
|
AlpinDale
|
2d97f4014e
fix: windows wheel url (#794)
|
vor 3 Monaten |
|
AlpinDale
|
0256ed236b
feat: windows support (#790)
|
vor 3 Monaten |
|
AlpinDale
|
dcb794a340
fix: revert incorrect commit
|
vor 3 Monaten |
|
AlpinDale
|
76367b5ae7
wip
|
vor 3 Monaten |
 50h100a
|
be4fa5b4cc
Merge pull request #785 from 50h100a/loadfix
|
vor 3 Monaten |
 50h100a
|
9022c6d869
remove progress_bar imports
|
vor 3 Monaten |
|
50h100a
|
9576096b9d
iterate over weights normally
|
vor 3 Monaten |
|
50h100a
|
1a5e612eaf
pass tensor progress bar as weight iterator
|
vor 3 Monaten |
|
50h100a
|
1ca5f47075
use tensor progress bar
|
vor 3 Monaten |
|
50h100a
|
a061d7578d
gather estimated weight bytes alongside iterator and pass it to model.load_weights
|
vor 3 Monaten |
|
50h100a
|
371d57af82
filesize-driven progress bar for loading tensors
|
vor 3 Monaten |
|
AlpinDale
|
4d3d819507
ci: bump version to 0.6.2.post1 (#779)
|
vor 3 Monaten |
|
AlpinDale
|
fb96041ae3
fix: demote skip_special_tokens assertion to logger error (#778)
|
vor 3 Monaten |
|
AlpinDale
|
4d781b22d3
docker: apply AMD patch in the dockerfile (#777)
|
vor 3 Monaten |
 Naomiusearch
|
eee3cf5dab
fix: make AMD usable (#775)
|
vor 3 Monaten |
|
AlpinDale
|
7222b84582
feat: ministral support (#776)
|
vor 3 Monaten |
 Fizz~
|
8a71788372
Add OLMoE (#772)
|
vor 3 Monaten |
|
50h100a
|
5795565e4b
Merge pull request #766 from 50h100a/simplifymeta
|
vor 3 Monaten |
 Pyroserenus
|
ee5964465d
chore: max_num_seqs in throughput benchmark (#770)
|
vor 3 Monaten |
|
Pyroserenus
|
99fc6f4697
fix: crash in token bans (#764)
|
vor 4 Monaten |
|
AlpinDale
|
a604ab69c4
fix: kobold api for horde (#763)
|
vor 4 Monaten |
|
50h100a
|
ed87b5dd32
remove special-case values for prompt sequences
|
vor 4 Monaten |
|
50h100a
|
06bb8400ce
sampling_metadata:
|
vor 4 Monaten |
|
AlpinDale
|
0e0bd02b52
ci: bump version to 0.6.2 (#758)
|
vor 4 Monaten |
|
AlpinDale
|
5878e887f2
docs: update readme and docs (#757)
|
vor 4 Monaten |
|
AlpinDale
|
d7309453f6
fix: add pandas to requirements (#756)
|
vor 4 Monaten |
|
AlpinDale
|
73177656ed
feat: quant_llm support (#755)
|
vor 4 Monaten |
