zhangyiss/mlx-examples
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-10-31 19:18:09 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity
624 Commits 10 Branches 0 Tags
65b792d7c08628b37ca61ca6a4768508c5ea1cdf
Commit Graph

624 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
vb
1727959a27 Add mentions of MLX-my-repo. (#1129) 
* Add mentions of MLX-my-repo.

* simplify

* move

* move

---------

Co-authored-by: Awni Hannun <awni@apple.com>
 2024-12-03 19:21:39 -08:00
Awni Hannun
1963df8565 Allow prompt callback to generate_step (#1133) 
* allow prompt callback and use in cache_prompt

* nit

* comments

* bump version
 2024-12-03 16:17:14 -08:00
sakares saengkaew
0ca162cfb2 Fix data_iter in prepare_dataset from speechcommands example (#1113) 2024-12-02 23:56:07 -08:00
Angelos Katharopoulos
eb9277f574 Allow loading from diffusers ckpt (#1117) 2024-12-02 13:15:50 -08:00
hehua2008
2a9294a5f0 Fix bug in FluxSampler.timesteps method (#1131) 2024-12-02 13:15:19 -08:00
Awni Hannun
8801beb66f Add olmo2 (#1128) 
* add olmo2

* add olmo2
 2024-12-02 11:42:58 -08:00
Neil Mehta
cefe793ae0 Accept mx.array type for prompt argument for stream_generate (#1125) 
* Accept mx.array type for prompt argument for stream_generate

* Fix formatting
 2024-11-26 16:51:55 -08:00
Awni Hannun
cfc29c29f4 Put prompt processing in same stream (#1122) 
* put prompt processing in same stream

* patch
 2024-11-25 09:47:00 -08:00
madroid
a5e173802e docs: update stream_generate return type annotation (#1121) 
Improve documentation clarity by:
1. Fix return type annotation to correctly reflect GenerationResponse
2. Simplify docstring by referencing GenerationResponse class
3. Remove redundant field descriptions
 2024-11-25 08:10:14 -08:00
Remixer Dec
adaab81029 Allow converting models from local directories (#1118) 2024-11-24 16:41:06 -08:00
Kevin Conner
0ffdb6dd20 Fix object property value in mlx_lm.server chat completions response to match OpenAI spec (#1119) 
These were "chat.completions" and "chat.completions.chunk"
but should be "chat.completion" and "chat.completion.chunk"
for compatibility with clients expecting an OpenAI API.

In particular, this solves a problem in which aider 0.64.1 reports
hitting a token limit on any completion request, no matter how small,
despite apparently correct counts in the usage property.

Refer to:

https://platform.openai.com/docs/api-reference/chat/object

> object string
> The object type, which is always chat.completion.

https://platform.openai.com/docs/api-reference/chat/streaming

> object string
> The object type, which is always chat.completion.chunk.
 2024-11-24 16:37:37 -08:00
Awni Hannun
0f135396ae Generation refactor: part 2 (#1099) 
* unify with stream_generate

* fixes

* nit

* some cleanup, warnings, tests

* fix test + faster min p + test

* version
 2024-11-23 11:47:06 -08:00
Awni Hannun
004eb4cc9d Tencent HunYuan MOE model (#1100) 
* hunyuan

* fix

* format str

* default trust remote code for tokenizer, allow system prompt to be configurable
 2024-11-23 11:06:26 -08:00
Angelos Katharopoulos
042280ce50 Fix format (#1115) 2024-11-20 16:15:53 -08:00
Valentin Roussellet
60c7b80350 Pass seed to sd img2img (#1114) 2024-11-20 15:21:52 -08:00
Alban Lecocq
bd6d910ca3 [MLX LM] Fix f-string formatting in memory warning message (#1105) 
* Fix missing f-prefix for string interpolation in model size warning
* Ensures proper display of memory values in MB for model and max size
 2024-11-13 06:14:03 -08:00
madroid
1e07660184 FLUX: save train config (#1049) 2024-11-08 17:15:19 -08:00
Awni Hannun
657b4cc0aa [MLX LM] Sampler refactor + a few improvements (#1094) 
* starting

* refactor sampler/processor and a few improvements

* fix stream

* fix stream generate

* fix eos handling in stream generate
 2024-11-07 16:15:24 -08:00
Angelos Katharopoulos
ed9e81dd58 Fix rotating kv cache size (#1093) 2024-11-05 10:24:24 -08:00
Awni Hannun
6fd1f70f73 fix spm decoder multi-byte (#1092) 2024-11-05 06:06:26 -08:00
Anthony Wu
4394633ce0 mlx_whisper: add support for audio input from stdin (#1012) 
* add support for audio and input name from stdin

* refactored to stdin - arg, and output-name template

* fix bugs, add test coverage

* fix doc to match arg rename

* some nits

---------

Co-authored-by: Awni Hannun <awni@apple.com>
 2024-11-04 14:02:13 -08:00
ilyasch2
3b526f0aa1 Add support for falcon-mamba (#1074) 
* Add support for falcon-mamba

* nits

* nit

---------

Co-authored-by: Awni Hannun <awni@apple.com>
 2024-11-04 12:23:30 -08:00
Anchen
82e3338987 chore(mlx-lm): add max token arg for mlx_lm.chat (#1089) 
* chore(mlx-lm): add max token arg for mlx_lm.chat

* chore: update the default max token value
 2024-11-04 06:06:34 -08:00
Angelos Katharopoulos
331148d8ec Enable distributed LoRA training (#821) 2024-11-02 18:02:31 -07:00
Awni Hannun
29c954f4cb fix (#1082) 2024-11-02 13:51:38 -07:00
Awni Hannun
0f799947d0 fix (#1079) 2024-11-01 16:30:32 -07:00
Awni Hannun
e510987870 Clear cache every now and then (#1081) 
* clear cache every now and then

* don't need user arg anymore
 2024-11-01 14:15:32 -07:00
Awni Hannun
8160e0c4e5 Whisper improvements (#1080) 
* use safetensors in whisper

* speed up decoder

* version
 2024-11-01 10:52:28 -07:00
Alex Barron
85ffd2c96a Quantized KV Cache (#1075) 
* add QuantizedKVCache

* simplify

* add tests

* single sdpa function

* fix sed

* in place

* fix tests

* support different k and v head dims
 2024-10-31 16:59:52 -07:00
Awni Hannun
9f34fdbda4 Wire models in MLX LM (#1069) 
* wired in MLX LM

* fix synch

* comment + nit

* version

* mlx lm version

* bump to 0.19.2
 2024-10-31 08:17:14 -07:00
Awni Hannun
8fe9539af7 Fix detokenizer space match for quote (#1072) 
* fix + test

* remove transformer flax/torch warning

* format
 2024-10-27 15:06:07 -07:00
hschaeufler
ab4bf05c6e Update lora_config.yaml with new param: num_layers (#1068) 2024-10-26 09:34:46 -07:00
Saurav Maheshkar
4971462bf0 feat(clip): add linear probe evaluation script (#960) 2024-10-24 21:56:17 -07:00
Awni Hannun
9000e280ae fix mamba models conversion (#1065) 2024-10-22 15:44:08 -07:00
madroid
d1d480867b LoRA: update tools datasets docs (#1063) 
* LoRA: update tools datasets docs

* nits

* nits

---------

Co-authored-by: Awni Hannun <awni@apple.com>
 2024-10-22 12:19:11 -07:00
Awni Hannun
66e7bcb886 override dtype with quant (#1062) 2024-10-22 09:56:45 -07:00
aronson
743763bc2e Handle empty string case in maybe_trim_space (#1055) 
* Handle empty string case in maybe_trim_space

* nit

---------

Co-authored-by: Awni Hannun <awni@apple.com>
 2024-10-20 20:46:43 -07:00
madroid
f491d473a3 FLUX: Optimize dataset loading logic (#1038) 2024-10-15 10:37:45 -07:00
Zak B. Elep
3d62b058a4 fix: typo on flux model preloading (#1050) 2024-10-15 09:13:01 -07:00
madroid
bbd2003047 FLUX: update README.md (#1036) 2024-10-14 11:21:41 -07:00
Awni Hannun
605c4854f1 Prompt caching in mlx_lm.server (#1026) 
* caching in server

* nits

* fix tests

* don't throw if no metal

* comments
 2024-10-14 10:57:22 -07:00
Awni Hannun
8dca1a2f60 Tokenizer updates + tests (#1024) 
* tokenizer updates + tests

* nit

* add can_trim_prompt_cache

* nits
 2024-10-14 10:48:46 -07:00
Awni Hannun
6c368f2124 bump mac tests to use py39 (#1047) 2024-10-14 10:40:36 -07:00
Awni Hannun
c799133998 Make llm async eval less brittle (#1040) 
* Make llm async eval less brittle

* nit
 2024-10-14 10:25:24 -07:00
Seitaro Sugawara
1e0cda68c6 Update README.md (#1045) 
* Update README.md

A small typo was fixed in the musicgen README.md.

* Update musicgen/README.md

---------

Co-authored-by: Awni Hannun <awni.hannun@gmail.com>
 2024-10-14 06:21:25 -07:00
Shunta Saito
7612c646f3 Fix PLaMo model to support Grouped Query Attention (#1037) 2024-10-12 15:26:50 -07:00
Ivan Fioravanti
d8611dd69f Small typo fixed in flux README.md (#1035) 2024-10-12 06:14:01 -07:00
Angelos Katharopoulos
a5f2bab070 Add FLUX finetuning (#1028) 2024-10-11 21:17:41 -07:00
Alex Barron
d72fdeb4ee MusicGen (#1020) 
* Add MusicGen model

* add benchmarks

* change to from_pretrained

* symlinks

* add readme and requirements

* fix readme

* readme
 2024-10-11 10:16:20 -07:00
Awni Hannun
4360e7ccec clear cache during prompt processing (#1027) 2024-10-09 16:48:32 -07:00