Add RWKV-4 #22797

sgugger merged 31 commits into main from add_rwkv
sgugger
Blealtan
Blealtan commented on 2023-04-23
sgugger First draft of RWKV-4
3e0855b7
sgugger Add support for generate
db50d8b8
sgugger Style post-rebase
b6273e9e
sgugger sgugger force pushed from c483bdf5 to b6273e9e 2 years ago
sgugger Properly use state
7b819307
sgugger Write doc
400147ec
sgugger Fix doc
86035324
HuggingFaceDocBuilderDev
sgugger More math
bc0cd7cb
sgugger Add model to README, dummies and clean config
77365843
sgugger Fix init
a6aa9327
younesbelkada multiple fixes:
a50d49cc
younesbelkada Merge branch 'main' into add_rwkv
1ca42ad9
younesbelkada correct tokenizer
848ccf81
younesbelkada Merge branch 'add_rwkv' of https://github.com/huggingface/transformer…
a33c5aa8
younesbelkada some tweaks
b679baa8
younesbelkada Merge remote-tracking branch 'upstream/main' into add_rwkv
6ce80d2a
younesbelkada fix CI tests
10b5b81d
younesbelkada fix conversion script
ffb55f99
younesbelkada add slow tests + more fixes on conversion script
7fd5702c
younesbelkada add another test
e52be94d
younesbelkada final fixes
3c02506a
younesbelkada younesbelkada requested a review from amyeroberts amyeroberts 2 years ago
younesbelkada
younesbelkada change single name variable
69774da9
sgugger
sgugger commented on 2023-05-04
younesbelkada add mock attention mask for pipeline to work
d52d6dbc
younesbelkada
younesbelkada commented on 2023-05-05
younesbelkada correct eos token id
0d758e13
younesbelkada fix nits
df44a606
younesbelkada add checkpoints
9e3efc5a
amyeroberts
amyeroberts approved these changes on 2023-05-05
younesbelkada Apply suggestions from code review
0b095c79
younesbelkada add `tie_word_embeddings` in docstring
f912a0d5
younesbelkada change tensor name
2a6dd617
younesbelkada
younesbelkada approved these changes on 2023-05-05
BlinkDL
Blealtan
Blealtan commented on 2023-05-09
Blealtan
Blealtan commented on 2023-05-09
younesbelkada fix final nits
4fdbeefa
Blealtan
Blealtan commented on 2023-05-09
younesbelkada Merge remote-tracking branch 'upstream/main' into add_rwkv
dc221691
sgugger Trigger CI
d1c2b15e
sgugger sgugger merged b4d4d6fe into main 2 years ago
sgugger sgugger deleted the add_rwkv branch 2 years ago
YovaKem
YovaKem
Blealtan
YovaKem
lambdaofgod
amyeroberts
Blealtan
sgugger
sgugger
Wednesday657
fullstackwebdev
younesbelkada

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone