zhangyiss/mlx-examples
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-06-25 18:11:17 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity
397 Commits 10 Branches 0 Tags 80 MiB
d3f8e4aee9
Commit Graph

3 Commits

Author SHA1 Message Date
Awni Hannun
b8a348c1b8
Switch to fast RMS/LN Norm (#603) 
* use nn.RMSNorm, use sdpa, cleanup

* bump mlx versions

* minor update

* use fast layer norm

* version bump

* update requirement for whisper

* update requirement for gguf
 2024-03-23 07:13:51 -07:00
Angelos Katharopoulos
f71e965d57
Change gqa to use repeat instead of concatenate (#443) 2024-02-14 17:40:11 -08:00
Juarez Bochi
f5b80c95fb
Example reading directly from gguf file (#222) 
* Draft of tiny llama from gguf

* Transpose all

* No transposition with new layout

* Read config from gguf

* Create tokenizer from gguf

* move gguf and update to be similar to hf_llm

* change model to HF style + updates to REAMDE

* nits in REAMDE

* nit readme

* only use mlx for metadata

* fix eos/bos tokenizer

* fix tokenization

* quantization runs

* 8-bit works

* tokenizer fix

* bump mlx version

---------

Co-authored-by: Juarez Bochi <juarez.bochi@grammarly.com>
Co-authored-by: Awni Hannun <awni@apple.com>
 2024-01-23 15:41:54 -08:00