Commit Graph

325 Commits

Author SHA1 Message Date
Goekdeniz-Guelmez
3a499f9735 fixed inference slowness but it cant handle multible Token inputs and is generateing gibberish 2024-11-10 16:35:07 +01:00
Goekdeniz-Guelmez
800b60239c save checkpoint 2024-11-10 14:36:26 +01:00
Goekdeniz-Guelmez
906f972d36 save push 2024-11-06 16:35:46 +01:00
Goekdeniz-Guelmez
58b448dc0b updates 2024-10-30 21:23:13 +01:00
Gökdeniz Gülmez
ffc7ab06a0
Merge branch 'ml-explore:main' into adding-support-for-mamba2 2024-10-30 17:04:38 +01:00
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
Gökdeniz Gülmez
3b70708201
Merge branch 'ml-explore:main' into adding-support-for-mamba2 2024-10-25 08:57:37 +02:00
Goekdeniz-Guelmez
7c8849e795 update 2024-10-24 16:16:42 +02:00
Awni Hannun
9000e280ae
fix mamba models conversion (#1065) 2024-10-22 15:44:08 -07:00
Goekdeniz-Guelmez
a677638c4b inference works but is hella slow 2024-10-22 23:06:06 +02:00
Goekdeniz-Guelmez
9ab581d678 notes 2024-10-22 22:10:53 +02:00
Goekdeniz-Guelmez
e43a2ab229 not working, incorrect handling with cache probably 2024-10-22 22:04:25 +02:00
Goekdeniz-Guelmez
55485b98e8 update 2024-10-22 21:23:47 +02:00
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
Goekdeniz-Guelmez
758597eaa8 adding multi token input and correct cache handling in ssm step 2024-10-22 20:44:23 +02:00
Awni Hannun
66e7bcb886
override dtype with quant (#1062) 2024-10-22 09:56:45 -07:00
Goekdeniz-Guelmez
5326d9373a Merge branch 'adding-support-for-mamba2' of https://github.com/Goekdeniz-Guelmez/mlx-examples into adding-support-for-mamba2 2024-10-22 18:26:05 +02:00
Goekdeniz-Guelmez
b9c57cd429 generation works! trying training now 2024-10-22 18:25:59 +02:00
Gökdeniz Gülmez
0ef73f3a2d
Merge branch 'ml-explore:main' into adding-support-for-mamba2 2024-10-21 15:14:19 +02:00
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
Goekdeniz-Guelmez
c1634ce81b still generating gibberish 2024-10-20 18:41:28 +02:00
Goekdeniz-Guelmez
ab4cf1d1cf generation works but outputs gibberish 2024-10-20 18:04:34 +02:00
Goekdeniz-Guelmez
4ab5139c05 quick save 2024-10-20 16:11:39 +02:00
Goekdeniz-Guelmez
cd036ccfb5 fix generation works too (almost) 2024-10-16 21:13:36 +02:00
Goekdeniz-Guelmez
181d6abedc Merge branch 'adding-support-for-mamba2' of https://github.com/Goekdeniz-Guelmez/mlx-examples into adding-support-for-mamba2 2024-10-16 21:09:42 +02:00
Goekdeniz-Guelmez
8073cb486c adding debug statements (somehiw generating only goes through the fist MambaMixer block pass) 2024-10-16 21:09:30 +02:00
Gökdeniz Gülmez
855fcc4327
Merge branch 'ml-explore:main' into adding-support-for-mamba2 2024-10-16 18:57:55 +02:00
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
c799133998
Make llm async eval less brittle (#1040)
* Make llm async eval less brittle

* nit
2024-10-14 10:25:24 -07:00
Gökdeniz Gülmez
3f1c1dde6a
Merge branch 'ml-explore:main' into adding-support-for-mamba2 2024-10-14 16:32:00 +02:00
Shunta Saito
7612c646f3
Fix PLaMo model to support Grouped Query Attention (#1037) 2024-10-12 15:26:50 -07:00
Goekdeniz-Guelmez
00ba27fe6c adding debug statements 2024-10-11 21:36:41 +02:00
Goekdeniz-Guelmez
6f88dd59d7 quick clean up and fix 2024-10-11 21:08:13 +02:00
Goekdeniz-Guelmez
9c075a71f8 Merge branch 'adding-support-for-mamba2' of https://github.com/Goekdeniz-Guelmez/mlx-examples into adding-support-for-mamba2 2024-10-11 20:54:35 +02:00
Goekdeniz-Guelmez
4e1236cbf6 fixing loading the model 2024-10-11 20:53:29 +02:00
Awni Hannun
4360e7ccec
clear cache during prompt processing (#1027) 2024-10-09 16:48:32 -07:00
Awni Hannun
b7373cb44f
fix long prompt generations (#1023) 2024-10-09 11:09:36 -07:00
Awni Hannun
fca087be49
More cache improvements (#1015)
* fix rotating kv cache for chat use case

* reorg + fixes to caching, unify prompt caching across types and use cases for e.g. caching during a chat

* nit in chat

* fix tests

* fix tests

* fix tests

* docs

* chat command

* comments + docs

* Define meta_state on all Cache implementations

* fixes + trim_prompt_cache api

* fix default model

---------

Co-authored-by: Angelos Katharopoulos <a_katharopoulos@apple.com>
2024-10-07 20:45:51 -07:00
Gökdeniz Gülmez
52d6ca0ad0
Merge branch 'ml-explore:main' into adding-support-for-mamba2 2024-10-04 22:25:31 +02:00
madroid
36c1d8e8dc
Server: support function calling (#1003) 2024-10-02 12:36:07 -07:00
Goekdeniz-Guelmez
264ba43707 update trainer/lora.py and adding DepthWiseConv1d because mlx 0.18.0 doesnt axepts groups parameter 2024-10-02 19:19:32 +02:00
Gökdeniz Gülmez
49b9fc1a4c
Create mamba2.py 2024-10-02 12:48:15 +02:00
nathan
0866e23a67
repetiton_penalty and logits_bias just using logits_processors (#1004)
* refactor of repetition_penalty and logits_bias to use logits_processor

* nits

---------

Co-authored-by: Awni Hannun <awni@apple.com>
2024-09-30 08:49:03 -07:00
Zai Thottakath
418d9a5511
Feature: QDoRA (#891)
* feat: QDoRA with tests and a small bug fix for recalculation of self.m

* some simplifications and fixes

---------

Co-authored-by: Awni Hannun <awni@apple.com>
2024-09-30 08:01:11 -07:00
madroid
aa1c8abdc6
LoRA: Support HuggingFace dataset via data parameter (#996)
* LoRA: support huggingface dataset via `data` argument

* LoRA: Extract the load_custom_hf_dataset function

* LoRA: split small functions

* fix spelling errors

* handle load hf dataset error

* fix pre-commit lint

* update data argument help

* nits and doc

---------

Co-authored-by: Awni Hannun <awni@apple.com>
2024-09-30 07:36:21 -07:00
Gökdeniz Gülmez
50e5ca81a8
Adding full finetuning (#903)
* Adding full model weights finetuning

* Updating the LORA.md and ACKNOWLEDGMENTS.md files.

* removing --use-dora and --fulll-training and adding --fine-tune-type

* some clean up

* reformating and fixing dora training

* updated CONFIG_DEFAULTS

* update config example

* update in the config example fie

* Update LORA.md

* merge and commit

* adding argument for dora linear layer

* clean up

* clean up in the example yaml file

* fix

* final fix before sending

* small addition to re md file

* fix for loading the fully trained model by saving all the files and configs correctly

* clean up

* removing the unnesesairy files

* changing lora layers back to 16

* removed max file size

* nits

* resolve merge

* some consistency changes

---------

Co-authored-by: Awni Hannun <awni@apple.com>
2024-09-29 17:12:47 -07:00
madroid
7ec2021bb9
LoRA: support tools(function calling) format datasets (#995)
* LoRA: support fine-tuning tools datasets

* LoRA: Split small function

* LoRA: add tools format to lora docs

* LoRA: pre-commit fix

* Revert "LoRA: pre-commit fix"

This reverts commit b94b7e0fe7.

* Revert "LoRA: Split small function"

This reverts commit 3f6a5f19fd.

* LoRA: remove ToolsDataset

In a JSONL file, not all data is required to include the tools value.

* nit in readme

* nit in readme

* nit in readme

---------

Co-authored-by: Awni Hannun <awni@apple.com>
2024-09-28 10:41:36 -07:00
nathan
ace2bb5890
Add logits_processor option to generate_step function (#983)
* Add logits_processor option for the generation as in huggingface transformers library

* concatenation correction

* Rename the tokens variable for clarity

* remove the logit_bias argument from generate_step method

* fix the variable name

* nits + test

* test

* add back logit bias + test

---------

Co-authored-by: Awni Hannun <awni@apple.com>
2024-09-28 10:08:49 -07:00