 oobabooga
|
145c725c39
Bump RWKV version
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
2af66a4d4c
Fix <USER> in pygmalion replies
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
a54b91af77
Improve readability
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
8e706df20e
Fix a memory leak when text streaming is on
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
5492e2e9f8
Add sentencepiece
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
90206204aa
Merge pull request #163 from oobabooga/hf_llama
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
c33715ad5b
Move towards HF LLaMA implementation
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
bd8aac8fa4
Add LLaMA 8-bit support
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
c93f1fa99b
Count the tokens more conservatively
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
736f61610b
Update README
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
ed8b35efd2
Add --pin-weight parameter for FlexGen
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
05e703b4a4
Print the performance information more reliably
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
5a79863df3
Increase the sequence length, decrease batch size
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
e62b9b1074
Revamp the "Default" preset with HF defaults
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
a345a2acd2
Add a tokenizer placeholder
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
4cc36dc434
Tweak the Naive preset (for LLaMA/RWKV)
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
5b354817f6
Make chat minimally work with LLaMA
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
ea5c5eb3da
Add LLaMA support
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
2bff646130
Stop chat from flashing dark when processing
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
7c70e0e2a6
Fix the download script (sort of)
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
bcea196c9d
Bump flexgen version
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
76378c6cc2
Update README
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
169209805d
Model-aware prompts and presets
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
024d30d1b4
Reorder imports
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
7bbe32f618
Don't return a value in an iterator function
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
ff9f649c0c
Remove some unused imports
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
1a05860ca3
Ensure proper no-streaming with generation_attempts > 1
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
a2a3e8f797
Add --rwkv-strategy parameter
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
99dc95e14e
Minor aesthetic change
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
449116a510
Fix RWKV paths on Windows (attempt)
|
%!s(int64=2) %!d(string=hai) anos |
