Commit Graph

60 Commits

Author SHA1 Message Date
Anchen
362e88a744
feat: move lora into mlx-lm (#337)
* feat: Add lora and qlora training to mlx-lm


---------

Co-authored-by: Awni Hannun <awni@apple.com>
2024-01-23 08:44:37 -08:00
Shunta Saito
85c1ff8fd6
Add PLaMo-13B model as an LLM example (#303)
* Convert HF weights of PLaMo and load it to a plamo model in mlx

* Fix model inference part

* Add bos at the beginning of the prompt

* Fix convert.py to copy tokenizer.model into the converted dir

* Use the required insturction format in generate.py when "--instruct" option is specified

* Change filenames and update existing scripts

* Add README

* Add requirements.txt

* Fix plamo.py to stop generation when EOS appears

* Add quantization to convert.py

* Use mlx>=0.0.9 for mx.core.outer() in PLaMo model

* Update acknowledgements.md

* Fix card text in upload_to_hub()

* Not use prompt template when --instruct is not specified

* Ask if you trust_remote_code for loading tokenizer of PLaMo

* Check the user trusts the remote code when converting

* Remove plamo directory

* Update README

* Add PLaMo model file

* Fix the handling of cache in PLaMo and update README

* Ask if trust_remote_code only when the model is PLaMo

* Remove resolve_trust_remote_code from convert.py and use the latest transformers

* Remove code not to add EOS

* Update README to fix an example not to use noncommercial version of the model

* Remove unused imports

* Remove unnecessary description about the instruct model of PLaMo from README

* format, nits in README

* typo

---------

Co-authored-by: Shunta Saito <shunta@mitmul-mbp.local>
Co-authored-by: Awni Hannun <awni@apple.com>
2024-01-23 07:17:24 -08:00
Ivan Fioravanti
c45c2311bd
Add colorized output option to generate script (#347)
* Add colorized output option to generate script

Two new functions were added to the script that allow output to be colorized based on the T[0] probability. Changes were made to the `generate_step` function in utils.py to permit colorization. Additionally, an argument for colorization was introduced to the command-line parser.

* Rename 'colorize' parameter with 'return_probability' in generate_step
2024-01-23 05:25:44 -08:00
Anchen
30be4c4734
refactor(qwen): moving qwen into mlx-lm (#312)
* refactor(qwen): moving qwen into mlx-lm

* chore: update doc

* chore: fix type hint

* add qwen model support in convert

* chore: fix doc

* chore: only load model in quantize_model

* chore: make the convert script only copy tokenizer files instead of load it and save

* chore: update docstring

* chore: remove unnecessary try catch

* chore: clean up for tokenizer and update  transformers 4.37

* nits in README

---------

Co-authored-by: Awni Hannun <awni@apple.com>
2024-01-22 15:00:07 -08:00
Anchen
527cea4027
chore: fix the convert.py script for weights are not sanitized and support quant for non-32 dimensions (#340)
* chore: fix convert script for weights not sanitized and suport quant for non 32 dim

* Update llms/mlx_lm/utils.py

Co-authored-by: Awni Hannun <awni.hannun@gmail.com>

* chore: fix typo

---------

Co-authored-by: Awni Hannun <awni.hannun@gmail.com>
2024-01-19 21:07:21 -08:00
Awni Hannun
bcc9fc3581
two minor fixes (#335) 2024-01-18 14:18:13 -08:00
someone
2287294723
fix mlx_lm generator for chinese (#321)
* fix generator for chinese

* add REPLACEMENT_CHAR

---------

Co-authored-by: cg <cg@qq.com>
2024-01-16 07:13:33 -08:00
Awni Hannun
b0870ed679
fix response + bump version (#319) 2024-01-15 11:51:21 -08:00
Anchen
195bec2fa3
feat(mlx_lm): add mixtral support in mlx_lm (#318)
* feat: add mixtral support in mlx_lm

* chore: update doc
2024-01-15 07:18:14 -08:00
Awni Hannun
c6440416a2
Mlx llm package (#301)
* fix converter

* add recursive files

* remove gitignore

* remove gitignore

* add packages properly

* read me update

* remove dup readme

* relative

* fix convert

* fix community name

* fix url

* version
2024-01-12 10:25:56 -08:00