phanerozoic commited on
Commit
a91365d
1 Parent(s): b8c8809

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -2
README.md CHANGED
@@ -49,7 +49,7 @@ Custom stopping strings employed for output quality:
49
  - "\nUser:"
50
 
51
  ### Training Data
52
- Trained on a vast dataset in ChatML format, ensuring diverse and rich inputs.
53
 
54
  ### Preprocessing
55
  Advanced preprocessing into ChatML format.
@@ -87,7 +87,11 @@ Primary metric: Perplexity. Qualitative assessments of dialect authenticity and
87
  Marked improvement in sophisticated output with authentic pirate tone. Lower perplexity score demonstrates enhanced language modeling.
88
 
89
  ### Summary
90
- Represents a significant advancement in domain-specific language modeling, excelling in complex, authentic pirate-themed content.
 
 
 
 
91
 
92
  ### Model Architecture and Objective
93
  Based on Mistral Instruct v0.2, fine-tuned for high coherence and technical accuracy in pirate-themed content.
 
49
  - "\nUser:"
50
 
51
  ### Training Data
52
+ Trained on a vast pirate themed dataset in ChatML format much larger than the previous version, ensuring diverse and rich inputs. This dataset was similarly derived from "Moby Dick".
53
 
54
  ### Preprocessing
55
  Advanced preprocessing into ChatML format.
 
87
  Marked improvement in sophisticated output with authentic pirate tone. Lower perplexity score demonstrates enhanced language modeling.
88
 
89
  ### Summary
90
+ MistralPirate-7b-v0.3 represents a significant leap in domain-specific language modeling, particularly in the realm of pirate-themed content generation. This version not only corrects the version control nomenclature but also marks a substantial advancement in the model's capabilities. It blends the charm and authenticity of pirate vernacular with the precision of modern language modeling techniques.
91
+
92
+ The model has been meticulously fine-tuned to capture the nuances of pirate dialect while maintaining a high degree of language coherence and technical accuracy. This makes it an unparalleled tool in scenarios where an immersive pirate theme is desired, be it in storytelling, gaming, or educational settings. The enhanced perplexity scores and technical refinements reflect its ability to handle complex, multi-faceted queries with a flair unique to pirate lore.
93
+
94
+ Designed to navigate the challenging waters of thematic content generation, MistralPirate-7b-v0.3 stands as a testament to the possibilities of domain-specific language models. It showcases the seamless integration of thematic accuracy with advanced AI capabilities, ensuring that users can enjoy an authentic and engaging pirate experience.
95
 
96
  ### Model Architecture and Objective
97
  Based on Mistral Instruct v0.2, fine-tuned for high coherence and technical accuracy in pirate-themed content.