whybeyoung
/
chatglm-6b-int4
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Commit Graph

  • 02a065cf27 Upload pytorch_model.bin main Zhengxiao Du 2023-05-15 12:41:28 +0000
  • e214c5b71d Update slack link Zhengxiao Du 2023-05-12 13:49:56 +0000
  • d8a6cfc6cb Update decode method in tokenizer duzx16 2023-05-09 11:32:40 +0800
  • f6b88da8c1 Add support for parallel quantization on Mac duzx16 2023-05-04 21:45:31 +0200
  • 63d66b0572 Remove assert in load_cpu_kernel duzx16 2023-04-29 10:34:45 +0800
  • f55a1089a2 Sync with chatglm-6b v0.1.0 duzx16 2023-04-28 20:17:25 +0800
  • ce1d7b24b1 Adding `safetensors` variant of this model 葉佐俊 2023-04-26 03:31:23 +0000
  • e02ba894cf Remove pytorch_model.bin.index.json duzx16 2023-04-17 21:34:20 +0800
  • 6498797e79 Update slack link duzx16 2023-04-17 16:08:53 +0800
  • 1e40d965fe Add pytorch_model.bin.index.json duzx16 2023-04-16 21:04:18 +0800
  • 630d0efd8b Add assertion when loading cpu and cuda kernel fails songxxzp 2023-04-14 20:00:41 +0800
  • bcc35f08b4 Add assertion when loading cpu and cuda kernel fails songxxzp 2023-04-14 19:58:42 +0800
  • fe0674f86d Merge branch 'dev' songxxzp 2023-04-14 19:01:28 +0800
  • c7d8998bb3 Update CPU kernel loading method dev songxxzp 2023-04-14 18:52:35 +0800
  • 3485994337 Fix gmask duzx16 2023-04-14 15:57:11 +0800
  • 9333486c30 Add empty_init option duzx16 2023-04-13 20:35:45 +0800
  • 6466cdcff5 Update README.md duzx16 2023-04-13 15:44:48 +0800
  • 9163f7e6d9 Fix eos token in tokenizer duzx16 2023-04-11 13:25:12 +0800
  • 649466f2d7 Update dependency duzx16 2023-04-09 20:34:34 +0800
  • 41fda88421 Fix attention score on mps duzx16 2023-04-09 20:30:23 +0800
  • a7272d4c93 Fix logit processor Fix tokenizer config saving duzx16 2023-04-08 12:07:06 +0800
  • 96de7a2fb3 Merge branch 'slim' of https://huggingface.co/THUDM/chatglm-6b-int4 into slim slim duzx16 2023-04-07 23:36:57 +0800
  • 5fc46d22f7 Fix embedding quantization duzx16 2023-04-07 23:34:41 +0800
  • 7edbdfecad Upload pytorch_model.bin Zhengxiao Du 2023-04-07 15:20:38 +0000
  • bfb1a8f2b6 Slim embedding duzx16 2023-04-07 23:14:10 +0800
  • 68873da921 Fix bugs when compiling cpu kernels songxxzp 2023-04-06 20:09:56 +0800
  • 1f34060390 Drop icetk dependency duzx16 2023-04-06 19:24:30 +0800
  • 0275597b4f Update README.md GanymedeNil 2023-04-05 14:41:09 +0000
  • 19685a5a7e Fix position ids expand duzx16 2023-04-03 14:16:48 +0800
  • 7aaf3fe491 Synchronize with chatglm 6b repo songxxzp 2023-04-03 09:20:14 +0800
  • 7458231b5a Fix parallel cpu kernel songxxzp 2023-04-01 21:15:30 +0800
  • b0c66a1229
         use float() Wen Sun 2023-03-30 02:28:59 +0900
  • f7a66d7523
         Add requirements.txt Wen Sun 2023-03-29 23:24:51 +0900
  • 0f1c288530 Create handler.py Wen 2023-03-29 14:21:13 +0000
  • dac03c3ac8 Fix bugs in quantization when loading kernels songxxzp 2023-03-22 05:18:51 -0400
  • debaf0032c Fix Chinese punctuation duzx16 2023-03-22 14:49:29 +0800
  • 3ba9437241 Update README.md Zeng Aohan 2023-03-20 06:51:58 +0000
  • 0d0e8067f8 Update README.md Zeng Aohan 2023-03-20 06:43:49 +0000
  • 7ad727c89f Update README.md Zeng Aohan 2023-03-20 06:43:29 +0000
  • a93efa90f5 init commmit Sengxian 2023-03-19 21:15:20 +0800
  • 62a9758691 initial commit Zhengxiao Du 2023-03-19 12:01:56 +0000