PanQiWei
|
a87d0b6e08
|
release v0.0.5
|
2023-04-26 18:00:14 +08:00 |
|
PanQiWei
|
938a746eea
|
release v0.0.5
|
2023-04-26 17:56:45 +08:00 |
|
潘其威(William)
|
1acb0c5eba
|
Merge pull request #18 from PanQiWei/push_to_hub_integration
push_to_hub integration
|
2023-04-26 17:52:45 +08:00 |
|
潘其威(William)
|
5a700529f9
|
Merge pull request #17 from PanQiWei/simple-demo
add simple demo ppl test with wikitext2
|
2023-04-26 17:52:27 +08:00 |
|
PanQiWei
|
e5e9296617
|
update README.md
|
2023-04-26 17:51:07 +08:00 |
|
PanQiWei
|
f2359f56cb
|
add support to use push_to_hub to upload and share quantized model
|
2023-04-26 16:55:01 +08:00 |
|
qwopqwop200
|
2d85af5f6d
|
add simple demo ppl test with wikitext2
|
2023-04-26 17:19:54 +09:00 |
|
PanQiWei
|
a8e748c511
|
empty cache before switch model
|
2023-04-26 15:22:30 +08:00 |
|
PanQiWei
|
1367677c45
|
set version to v0.0.5-dev
|
2023-04-26 14:17:39 +08:00 |
|
潘其威(William)
|
f8aa8e27e7
|
Update README.md
|
2023-04-26 14:07:22 +08:00 |
|
潘其威(William)
|
82815471fd
|
Merge pull request #16 from PanQiWei/triton_integration
Triton integration
|
2023-04-26 14:03:54 +08:00 |
|
PanQiWei
|
e2c83bd363
|
update README.md
|
2023-04-26 13:56:29 +08:00 |
|
PanQiWei
|
bf2ae6768d
|
bug fix
|
2023-04-26 13:33:56 +08:00 |
|
PanQiWei
|
73cb1dbf09
|
optimize import and format code
|
2023-04-26 13:08:47 +08:00 |
|
PanQiWei
|
c6dee93f5d
|
update README.md
|
2023-04-26 13:01:07 +08:00 |
|
PanQiWei
|
9a7e4430f8
|
update setup.py
|
2023-04-26 12:58:07 +08:00 |
|
PanQiWei
|
975f100d0f
|
init Quantizer() at GPTQ() init stage
|
2023-04-25 23:13:09 +08:00 |
|
PanQiWei
|
c35dce525e
|
format code
|
2023-04-25 22:58:52 +08:00 |
|
PanQiWei
|
9f7f44146f
|
format code
|
2023-04-25 22:45:27 +08:00 |
|
PanQiWei
|
b71211b4c3
|
format code
|
2023-04-25 22:36:28 +08:00 |
|
PanQiWei
|
b7b0eee0cc
|
release v0.0.4
|
2023-04-25 21:35:31 +08:00 |
|
PanQiWei
|
062b34f31a
|
add inference_mode and autocast context manager to generate function
|
2023-04-25 20:47:33 +08:00 |
|
PanQiWei
|
7915278e5f
|
bug fix
|
2023-04-25 20:43:40 +08:00 |
|
PanQiWei
|
8f93e97137
|
update example code
|
2023-04-25 20:41:27 +08:00 |
|
PanQiWei
|
31d683f85b
|
add option to choose whether autotune warmup or not after quantization
|
2023-04-25 20:29:05 +08:00 |
|
PanQiWei
|
7ce3659451
|
release v0.0.4
|
2023-04-25 20:24:32 +08:00 |
|
PanQiWei
|
0a7ee423b8
|
update example code
|
2023-04-25 20:24:00 +08:00 |
|
PanQiWei
|
c6af495da2
|
add --use_triton flag
|
2023-04-25 20:23:52 +08:00 |
|
PanQiWei
|
8183f6cde5
|
update README.md
|
2023-04-25 20:20:06 +08:00 |
|
PanQiWei
|
eeec304de5
|
update README.md
|
2023-04-25 20:12:19 +08:00 |
|
PanQiWei
|
9c405b1628
|
add triton support
|
2023-04-25 20:05:22 +08:00 |
|
PanQiWei
|
d69eb227e6
|
update setup.py
|
2023-04-25 19:35:35 +08:00 |
|
PanQiWei
|
832dc4a7a1
|
refactor file structure
|
2023-04-25 18:58:20 +08:00 |
|
PanQiWei
|
0bb84053a2
|
update setup.py
|
2023-04-25 18:50:21 +08:00 |
|
潘其威(William)
|
1c98811623
|
Merge pull request #15 from PanQiWei/support_moss
Support MOSS model
|
2023-04-25 12:59:05 +08:00 |
|
PanQiWei
|
419160b733
|
always trust remote code
|
2023-04-25 12:52:49 +08:00 |
|
PanQiWei
|
cfcba7d116
|
update README.md
|
2023-04-25 12:34:04 +08:00 |
|
PanQiWei
|
d78685aade
|
update README.md
|
2023-04-25 12:31:00 +08:00 |
|
PanQiWei
|
262416e7ff
|
set package version to v0.0.4-dev
|
2023-04-25 12:16:05 +08:00 |
|
PanQiWei
|
6b6dd3e1e3
|
always trust remote code
|
2023-04-25 12:15:32 +08:00 |
|
PanQiWei
|
f748dad2e1
|
always trust remote code
|
2023-04-25 12:13:46 +08:00 |
|
PanQiWei
|
a259fb06bb
|
add support to MOSS model
|
2023-04-25 11:54:29 +08:00 |
|
PanQiWei
|
73606a3a16
|
release v0.0.3
|
2023-04-25 01:09:30 +08:00 |
|
PanQiWei
|
7d3a625cee
|
fix mismatch GPTNeoxForCausalLM's lm_head
|
2023-04-24 20:51:56 +08:00 |
|
PanQiWei
|
1a8c460262
|
fix problem that some models required more positional arguments in transformer layer's forward function
|
2023-04-24 14:46:21 +08:00 |
|
PanQiWei
|
5657bd2db7
|
set package version to v0.0.3-dev
|
2023-04-24 14:24:52 +08:00 |
|
PanQiWei
|
8b487af045
|
Merge remote-tracking branch 'origin/main'
|
2023-04-24 14:24:28 +08:00 |
|
PanQiWei
|
37c0a80092
|
fix problem that some models can't get seqlen from model.config.max_position_embeddings
|
2023-04-24 14:24:00 +08:00 |
|
潘其威(William)
|
9279602cea
|
fix typo
|
2023-04-24 13:49:39 +08:00 |
|
潘其威(William)
|
a19f58a870
|
Merge pull request #10 from eltociear/patch-1
Update README.md
|
2023-04-24 10:14:12 +08:00 |
|