Update README.md

README.md

@@ -9,7 +9,6 @@ language:
 - en
 tags:
 - mistral
-- ehartford/dolphin
 - spanish
 - lora
 - int8
@@ -18,13 +17,12 @@ tags:
 
 # ecastera-eva-westlake-7b-spanish
 
-Mistral 7b-based model fine-tuned in Spanish to add high quality Spanish text generation.
-
-* Refined version of my previous models, with new training data and methodology. This should produce more natural reponses in Spanish.
+* Refined version of my previous models, with new training data and methodology, cleaned corpus.
+* This should produce more natural reponses in Spanish.
+* Fine tuned with high quality literature, books and philosophy, with high level reasoning capabilities.
 * Base model Mistral-7b
 * Based on the excelent job of senseable/WestLake-7B-v2 and Eric Hartford's cognitivecomputations/WestLake-7B-v2-laser
-* Fine-tuned in Spanish with a collection of poetry, books, wikipedia articles, phylosophy texts and alpaca-es datasets.
-* Trained using Lora and PEFT and INT8 quantization on 2 GPUs for several days.
+* Trained using Lora and PEFT and INT8 quantization.
 
 ## Usage: