Update README.md

New quantizations s00n tm

README.md

@@ -2,7 +2,7 @@
 license: gpl-3.0
 metrics:
 - perplexity
-pipeline_tag: conversational
+pipeline_tag: text-generation
 tags:
 - LLaMa
 - text-generation-inference
@@ -11,4 +11,8 @@ tags:
 
 LLaMa 65B converted to ggml via LLaMa.cpp, then quantized to 4bit.
 
-I recommend the following settings when running as a good starting point: ```main.exe -m ggml-LLaMa-65B-q4_0.bin -n -1 -t 42 -c 2048 --temp 0.35 --interactive-first --repeat_penalty 1.2 --instruct --color```
+Note: If you previously used the q4_0 model before April 26th, 2023, you are using an outdated model. I suggest redownloading for a better experience.
+Check https://github.com/ggerganov/llama.cpp#quantization for details on the different quantization types.
+
+I recommend the following settings when running as a good starting point: ```main.exe -m ggml-LLaMa-65B-q4_0.bin -n -1 -t 42 -c 2048 --temp 0.4 --interactive-first --repeat_penalty 1.2 --color```
+Be aware that LLaMa is a text generation model, not a conversational one, and as such you will have to prompt it differently than, for example, Vicuna or ChatGPT.