Prince Canuma c012eb173f Add support for OpenELM (#719) ...

* add openELM

* update splitting logic

* update qkv logic and, transformer and MLP block

* code formatting and fix args

* fix array slicing and remove unused var :)

* add to tuner

* use mx.split for slicing qkv

* merge with phi3

* remove rope scaling logic

* code formatting

2024-04-25 16:49:28 -07:00

..

__init__.py

Mlx llm package (#301)

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

base.py

Mlx llm package (#301)

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

cohere.py

Quantize embedding / Update quantize API (#680)

2024-04-18 18:16:10 -07:00

dbrx.py

- Removed unused Python imports (#683)

2024-04-16 07:50:32 -07:00

gemma.py

Quantize embedding / Update quantize API (#680)

2024-04-18 18:16:10 -07:00

llama.py

Switch to fast RMS/LN Norm (#603)

2024-03-23 07:13:51 -07:00

minicpm.py

MiniCPM implementation (#685)

2024-04-25 15:29:28 -07:00

mixtral.py

Fix argpartition call in Mixtral and other MOES (#676)

2024-04-12 11:00:56 -07:00

olmo.py

Quantize embedding / Update quantize API (#680)

2024-04-18 18:16:10 -07:00

openelm.py

Add support for OpenELM (#719)

2024-04-25 16:49:28 -07:00

phi3.py

Add support for phi-3 (#712)

2024-04-23 09:20:00 -07:00

phi.py

Switch to fast RMS/LN Norm (#603)

2024-03-23 07:13:51 -07:00

phixtral.py

Fix argpartition call in Mixtral and other MOES (#676)

2024-04-12 11:00:56 -07:00

plamo.py

Configurable LR schedulers (#604)

2024-03-29 13:41:10 -07:00

qwen2_moe.py

Add support for qwen2moe (#640)

2024-04-02 11:33:29 -07:00

qwen2.py

Quantize embedding / Update quantize API (#680)

2024-04-18 18:16:10 -07:00

qwen.py

Switch to fast RMS/LN Norm (#603)

2024-03-23 07:13:51 -07:00

stablelm.py

Stable lm 2 (#666)

2024-04-08 14:18:55 -07:00

starcoder2.py

Quantize embedding / Update quantize API (#680)

2024-04-18 18:16:10 -07:00