|
@@ -5,10 +5,11 @@ Inference of [Facebook's LLaMA](https://github.com/facebookresearch/llama) model
|
|
|
**Hot topics**
|
|
**Hot topics**
|
|
|
|
|
|
|
|
- Running on Windows: https://github.com/ggerganov/llama.cpp/issues/22
|
|
- Running on Windows: https://github.com/ggerganov/llama.cpp/issues/22
|
|
|
|
|
+- Fix Tokenizer / Unicode support: https://github.com/ggerganov/llama.cpp/issues/11
|
|
|
|
|
|
|
|
## Description
|
|
## Description
|
|
|
|
|
|
|
|
-The main goal is to run the model using 4-bit quantization on a MacBook.
|
|
|
|
|
|
|
+The main goal is to run the model using 4-bit quantization on a MacBook
|
|
|
|
|
|
|
|
- Plain C/C++ implementation without dependencies
|
|
- Plain C/C++ implementation without dependencies
|
|
|
- Apple silicon first-class citizen - optimized via Arm Neon and Accelerate framework
|
|
- Apple silicon first-class citizen - optimized via Arm Neon and Accelerate framework
|
|
@@ -22,6 +23,12 @@ Please do not make conclusions about the models based on the results from this i
|
|
|
For all I know, it can be completely wrong. This project is for educational purposes and is not going to be maintained properly.
|
|
For all I know, it can be completely wrong. This project is for educational purposes and is not going to be maintained properly.
|
|
|
New features will probably be added mostly through community contributions, if any.
|
|
New features will probably be added mostly through community contributions, if any.
|
|
|
|
|
|
|
|
|
|
+Supported platformst:
|
|
|
|
|
+
|
|
|
|
|
+- [X] Mac OS
|
|
|
|
|
+- [X] Linux
|
|
|
|
|
+- [ ] Windows (soon)
|
|
|
|
|
+
|
|
|
---
|
|
---
|
|
|
|
|
|
|
|
Here is a typical run using LLaMA-7B:
|
|
Here is a typical run using LLaMA-7B:
|
Georgi Gerganov