Update README.md

README.md

@@ -8,20 +8,14 @@ tags:
 
 # vicuna-13b-4bit
 Converted `vicuna-13b` to GPTQ 4bit using `true-sequentual` and `groupsize 128` in `safetensors` for best possible model performance.
-This does **not** support `llama.cpp` or any other cpp implemetations, only `cuda` or `triton`. These implementations require a different format to use.
+This does **not** support `llama.cpp` or any other cpp implemetations, only `cuda` is supported. These implementations require a different format to use.
 
 Vicuna is a high coherence model based on Llama that is comparable to ChatGPT. Read more here https://vicuna.lmsys.org/
 
-GPTQ - https://github.com/qwopqwop200/GPTQ-for-LLaMa
+# Important - Update 2023-04-05
+Recent GPTQ commits have introduced breaking changes to model loading and you should this fork for a stable experience https://github.com/oobabooga/GPTQ-for-LLaMa
 
-# Important - Update 2023-04-03
-Recent GPTQ commits have introduced breaking changes to model loading and you should use commit `a6f363e3f93b9fb5c26064b5ac7ed58d22e3f773` in the `cuda` branch. 
-
-If you're not familiar with the Git process
-1. `git checkout a6f363e3f93b9fb5c26064b5ac7ed58d22e3f773`
-2. `git switch -c cuda-stable`
-
-This creates and switches to a `cuda-stable` branch to continue using the quantized models.
+Curently only cuda is supported.
 
 # Usage
 1. Run manually through GPTQ