elinas commited on
Commit
e2c934d
1 Parent(s): 185a5c9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -2
README.md CHANGED
@@ -15,13 +15,14 @@ library_name: transformers
15
  ![image/webp](https://cdn-uploads.huggingface.co/production/uploads/630417380907b9a115c6aa9f/3hc8zt8fzKdO3qHK1p1mW.webp)
16
 
17
  Chronos Gold 12B 1.0 is a very unique model that applies to domains areas such as
18
- geneal chatbot functionatliy, *roleplay*, and storywriting. The model has been observed to write up to 2250 tokens in a single sequence.
 
19
 
20
  The base model is `mistralai/Mistral-Nemo-Base-2407` which was heavily modified to produce a more coherent model, comparable to much larger models.
21
 
22
  **Chronos Gold 12B-1.0** re-creates the uniqueness of the original Chronos with significiantly enhanced prompt adherence (following), coherence, a modern dataset, as well as supporting a majority of "character card" formats in applications like SillyTavern.
23
 
24
- It went through an intelligent merge process as my previous models and was further finetuned on a dataset curated for it.
25
 
26
  The specifics of the model will not be disclosed at the time due to dataset ownership.
27
 
 
15
  ![image/webp](https://cdn-uploads.huggingface.co/production/uploads/630417380907b9a115c6aa9f/3hc8zt8fzKdO3qHK1p1mW.webp)
16
 
17
  Chronos Gold 12B 1.0 is a very unique model that applies to domains areas such as
18
+ geneal chatbot functionatliy, *roleplay*, and storywriting. The model has been observed to write up to 2250 tokens in a single sequence. The model was trained at a
19
+ sequence length of 16384 (16k) and will still retain the *apparent* 128k context length from Mistral-Nemo.
20
 
21
  The base model is `mistralai/Mistral-Nemo-Base-2407` which was heavily modified to produce a more coherent model, comparable to much larger models.
22
 
23
  **Chronos Gold 12B-1.0** re-creates the uniqueness of the original Chronos with significiantly enhanced prompt adherence (following), coherence, a modern dataset, as well as supporting a majority of "character card" formats in applications like SillyTavern.
24
 
25
+ It went through an iterative and objective merge process as my previous models and was further finetuned on a dataset curated for it.
26
 
27
  The specifics of the model will not be disclosed at the time due to dataset ownership.
28