Commit Graph

  • e1e56a625b Fix benchmark (#200) bofeng huang 2023-12-28 20:29:39 +01:00
  • 78d207fe27 Fix generate example in README (#197) Sunbir Gill 2023-12-27 16:11:10 -05:00
  • 50fceb1a28 fix: Add numpy to CIFAR's requirements.txt (#192) Jiří Moravčík 2023-12-27 00:18:59 +01:00
  • a516f4635d Fixed the return type for the __call__ method in Attention (#190) Sushant 2023-12-26 23:02:43 +05:30
  • 2bd20ef0e0 shard llama model after conversion and unshard on loading (#174) Daniel Strobusch 2023-12-25 20:19:43 +01:00
  • 738448c2d4 QWEN: Fix unsupported ScalarType BFloat16 (#187) Yifan 2023-12-25 22:10:01 +08:00
  • 647e48870a updated README (#184) Vidyasagar Bhargava 2023-12-24 19:49:53 +05:30
  • 939086e6a3 Mixtral: Stop at EOS token (#183) devonthomas35 2023-12-23 21:25:42 -08:00
  • 0371d90ccb fashion-mnist example (#180) Kashif Rasul 2023-12-23 16:34:45 +01:00
  • 848f118ac5 use non-zero exit code on error (#177) Daniel Strobusch 2023-12-23 16:10:13 +01:00
  • 092e87211e fix bad convert parameter (#178) Daniel Strobusch 2023-12-23 16:09:49 +01:00
  • f4709cb807 Align CLI args and some smaller fixes (#167) Alvaro Bartolome 2023-12-22 23:34:32 +01:00
  • 0eaa323c10 Fix conversion + inference errors. - Mistral (#176) Vaibhav Srivastav 2023-12-23 03:40:25 +05:30
  • 7ae445f6c7 feat: add mistral tps (#173) Todsaporn Banjerdkit 2023-12-22 22:55:57 +07:00
  • 188a91074b fix typo (#169) Daniel Strobusch 2023-12-21 23:17:11 +01:00
  • 3cf436b529 Quantize example (#162) Awni Hannun 2023-12-21 12:59:37 -08:00
  • 4c9db80ed2 Add support for byt5 models (#161) Juarez Bochi 2023-12-21 11:46:36 -05:00
  • 6c574dbecf update path to load weights (#164) Deven Mistry 2023-12-21 09:31:17 -05:00
  • 4addd02988 updated results (#165) Sarthak Yadav 2023-12-21 15:30:17 +01:00
  • 22620de3ee 1. Add user warning for sequences over 2048 tokens in iterate_batches. (#166) wyanzhao 2023-12-21 06:29:31 -08:00
  • 43b6522af2 rename --model_path to --model-path (#151) Daniel Strobusch 2023-12-21 15:28:57 +01:00
  • 3efb1cc2cc fix typo in readme (#163) Deven Mistry 2023-12-20 22:47:41 -05:00
  • ce30cc3d8f Use config.json in llama (#159) Pedro Cuenca 2023-12-20 19:34:44 +01:00
  • 27c0a8c002 Add llms subdir + update README (#145) Awni Hannun 2023-12-20 10:22:25 -08:00
  • aed14618ca Add config.json to Mixtral. (#158) Vaibhav Srivastav 2023-12-20 23:17:23 +05:30
  • 730c50d00a Use config.json, add model_type (#157) Pedro Cuenca 2023-12-20 17:39:37 +01:00
  • 4b7e11bd31 Add URLs to HF MLX-Community org. (#153) Vaibhav Srivastav 2023-12-20 20:27:13 +05:30
  • d8e14c858e Add --model_path to phi-2 example script (#152) Pedro Cuenca 2023-12-20 15:14:35 +01:00
  • b6e62caf2e Added Keyword Spotting Transformer + SpeechCommands example (#123) Sarthak Yadav 2023-12-19 23:17:48 +01:00
  • ebbb7083cc T5: Change default dtype to bfloat16 (#147) Juarez Bochi 2023-12-19 16:44:36 -05:00
  • 62b455f801 Add Qwen example (#134) Junyi Mei 2023-12-20 05:06:19 +08:00
  • 10a7b99e83 Add T5 and Flan-T5 example (#113) Juarez Bochi 2023-12-18 23:25:34 -05:00
  • 1e7f4a5921 fix use for llama 2 from meta (#144) Awni Hannun 2023-12-18 19:33:17 -08:00
  • 1d62b3ecc1 Pass few shot file name to --few-shot arg(#141) Daniel Strobusch 2023-12-18 22:30:04 +01:00
  • 517f5808fc Citation + contributor acknowledgments section (#136) Awni Hannun 2023-12-18 10:12:35 -08:00
  • f0e14b6341 fix renamed arg (#140) Daniel Strobusch 2023-12-18 19:11:51 +01:00
  • 44b546d446 support for tiny llama (#129) Awni Hannun 2023-12-18 07:47:55 -08:00
  • 08e862336a Rope theta to support Coda Llama (#121) Awni Hannun 2023-12-15 19:51:51 -08:00
  • db134d976d Merge pull request #115 from ml-explore/lora_custom Awni Hannun 2023-12-15 13:54:58 -08:00
  • 8df211869e minimum version Awni Hannun 2023-12-15 13:54:31 -08:00
  • fc1495abaa Stable diffusion - check model weights shape and support int for "attention_head_dim" (#85) Pawel Kowalski 2023-12-15 22:01:02 +01:00
  • 86cae9ba57 Merge pull request #116 from idoru/fix-phi-2-temp-arg Awni Hannun 2023-12-15 12:29:19 -08:00
  • ff0f172363 32 GB example Awni Hannun 2023-12-15 12:20:15 -08:00
  • ee2ee0f8e5 32 GB example Awni Hannun 2023-12-15 12:18:29 -08:00
  • 877f88dfea Pass along temp argument to generate() Sam Coward 2023-12-15 15:16:41 -05:00
  • 8c8f9d6440 keep base weights in fp16 Awni Hannun 2023-12-15 10:42:18 -08:00
  • 84f02ef58b use lower precision base weights Awni Hannun 2023-12-15 10:29:42 -08:00
  • d108c558fc more nits Awni Hannun 2023-12-15 10:06:14 -08:00
  • fa51553f09 fix readme Awni Hannun 2023-12-15 09:59:07 -08:00
  • 985f413f99 custom data with lora Awni Hannun 2023-12-15 09:56:10 -08:00
  • 126b99d8be Merge pull request #112 from ml-explore/fix_mixtral Awni Hannun 2023-12-15 08:39:02 -08:00
  • 71b40c474c Merge pull request #108 from devonthomas35/phi2_eos Awni Hannun 2023-12-15 07:34:11 -08:00
  • ec11763527 fix RoPE bug + minor updates Awni Hannun 2023-12-14 21:45:25 -08:00
  • d74d9453dd Refactor EOS check devonthomas35 2023-12-14 21:11:23 -08:00
  • a3ecda22fe Merge pull request #107 from ml-explore/hf_mixtral Awni Hannun 2023-12-14 16:57:19 -08:00
  • b863e7cca0 format Awni Hannun 2023-12-14 16:56:50 -08:00
  • d7d7aabded Remove unnecessary return devonthomas35 2023-12-14 15:52:22 -08:00
  • 4549dcbbd0 Stop generating at eos token devonthomas35 2023-12-14 15:50:59 -08:00
  • e434e7e5c2 incude instruct option Awni Hannun 2023-12-14 15:40:38 -08:00
  • 078fed3d8d use official HF for mixtral Awni Hannun 2023-12-14 15:30:32 -08:00
  • 67a208b13e Merge pull request #106 from fahnub/main Awni Hannun 2023-12-14 14:15:19 -08:00
  • 9b887cef08 minor dep fix in phi Fahad Nadeem 2023-12-15 03:09:33 +05:00
  • 09fff84a85 Merge pull request #77 from SarthakYadav/main Awni Hannun 2023-12-14 12:19:40 -08:00
  • b9439ce74e typo / nits Awni Hannun 2023-12-14 12:14:01 -08:00
  • b1b9b11801 updates + format Awni Hannun 2023-12-14 12:09:10 -08:00
  • 0e88a6afa1 Merge pull request #103 from arpitingle/patch-1 Awni Hannun 2023-12-14 10:19:40 -08:00
  • 5b08da2395 Update README.md arpit 2023-12-14 23:40:50 +05:30
  • 92efa32060 Merge pull request #97 from jbarrow/main Awni Hannun 2023-12-14 09:21:26 -08:00
  • 8f60d60814 cleanup conversion to use single qkv matrix Awni Hannun 2023-12-14 09:19:44 -08:00
  • 0c1c500714 update readme Awni Hannun 2023-12-14 08:37:34 -08:00
  • 3d2a23184a change file name for consistency, update readme. Awni Hannun 2023-12-14 08:34:24 -08:00
  • 840c0c36c2 don't drop last tokens Awni Hannun 2023-12-14 08:27:44 -08:00
  • 1613e608a9 fix args, update README, remove extra files Awni Hannun 2023-12-14 08:18:01 -08:00
  • a8d4149147 fix fp16 + nits Awni Hannun 2023-12-14 08:08:28 -08:00
  • 29b7a97342 updated header Sarthak Yadav 2023-12-14 16:28:00 +01:00
  • b11997122d Merge pull request #98 from finnless/patch-1 Awni Hannun 2023-12-14 07:13:19 -08:00
  • 363108d7b3 Merge pull request #102 from burakbudanur/main Awni Hannun 2023-12-14 07:12:20 -08:00
  • f691e00e5a Corrected the typo in 'ffn_dim_multiplier' in and added 'rope_theta' to the list unused. Without these, llama examples did not run. Burak Budanur 2023-12-14 14:02:11 +01:00
  • 15a6c155a8 simplified ResNet, expanded README with throughput and performance Sarthak Yadav 2023-12-14 09:05:04 +01:00
  • 88d7b67e6e add cache + generation, clean up some stuff Awni Hannun 2023-12-13 22:26:33 -08:00
  • 0ce7618bc9 Fix typo in stable_diffusion README Nolan 2023-12-13 20:51:39 -08:00
  • a466cc5191 phi-2 draft Joe Barrow 2023-12-13 22:22:56 -05:00
  • af2e2b40f9 Merge pull request #96 from Stv-X/typo-fix Awni Hannun 2023-12-13 16:28:03 -08:00
  • cbae83e011 Corrected spelling of terms in whisper/README.md Stv.X 2023-12-14 08:15:26 +08:00
  • 9c7e996ff0 Merge pull request #51 from jbarrow/main Awni Hannun 2023-12-13 15:20:29 -08:00
  • 9f4e63acbf Update to mlx>=0.0.5 Joe Barrow 2023-12-13 17:48:07 -05:00
  • c88468755b Merge pull request #94 from jbax3/patch-1 Awni Hannun 2023-12-13 14:19:14 -08:00
  • 1505e49a62 Update README.md to fix git-lfs command jbax3 2023-12-13 15:51:27 -06:00
  • 8d83960a55 Merge pull request #93 from jbochi/patch-1 Awni Hannun 2023-12-13 08:47:52 -08:00
  • 03fe6896de Fix convert.py instructions for Bert model Juarez Bochi 2023-12-13 11:37:02 -05:00
  • 700b67fa3a Merge pull request #90 from bofenghuang/fix-fp16 Awni Hannun 2023-12-13 07:29:10 -08:00
  • 3b7cfeb8ed Merge pull request #88 from dastrobu/meta-form-url Awni Hannun 2023-12-13 07:20:51 -08:00
  • 4b1a06c0cb Fix fp16 bofenghuang 2023-12-13 11:07:47 +01:00
  • 5515c2a75b fix "request access" form url for Llama models Daniel Strobusch 2023-12-13 10:12:10 +01:00
  • 74c4ed40d2 Merge pull request #76 from bofenghuang/add-whisper-large-v3 Awni Hannun 2023-12-12 20:22:31 -08:00
  • a614e951c4 Merge pull request #82 from ml-explore/llamav2 Awni Hannun 2023-12-12 17:08:24 -08:00
  • a99e9d551e hf correction Awni Hannun 2023-12-12 17:08:04 -08:00
  • d3bd2e5d68 Merge pull request #79 from ml-explore/whisper_fp16 Awni Hannun 2023-12-12 17:05:21 -08:00
  • 66253a324c Merge pull request #84 from iammerrick/patch-1 Awni Hannun 2023-12-12 17:02:21 -08:00
  • b7081feb62 Merge pull request #86 from 1-ashraful-islam/patch-2 Awni Hannun 2023-12-12 17:01:02 -08:00