Update README

README.md

@@ -10,18 +10,15 @@ language:
 - en
 ---
 ## General
-Vicuna 1.1 13B finetune incorporating various datasets in addition to the unfiltered ShareGPT. This is an experiment attempting to enhance the creativity of the Vicuna 1.1, while also reducing censorship as much as possible.
-All datasets have been cleaned. Additionally, only the "instruct" portion of GPTeacher has been used.
+Vicuna 1.1 13B finetune incorporating various datasets in addition to the unfiltered ShareGPT. This is an experiment attempting to enhance the creativity of the Vicuna 1.1, while also reducing censorship as much as possible. All datasets have been cleaned. Additionally, only the "instruct" portion of GPTeacher has been used.
 
 ## Models
-*GGML 4-bit for llama.cpp:*<br/>
+*GGML quant for llama.cpp:*<br/>
 ggml-vicuna-13b-cocktail-v1-q5_0.bin<br/>
 
 *GPTQ 4-bit CUDA:*<br/>
 vicuna-13b-cocktail-v1-4bit-128g.safetensors<br/>
 
-Tokenizer and configs can be found in `hf-output`.
-
 ## Remarks
 This model has been trained with a modified prompt:<br/>
 ```
@@ -30,4 +27,4 @@ USER: [user message]
 ASSOCIATE: [model reply]</s>
 ```
 
-The training roles are USER and ASSOCIATE.
+The training roles are USER and ASSOCIATE.