teknium commited on
Commit
47044a4
·
verified ·
1 Parent(s): 6ae71c2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -49,6 +49,9 @@ Chat with Hermes in Nous Chat: https://chat.nousresearch.com
49
 
50
  Training highlights include a newly synthesized post-training corpus emphasizing verified reasoning traces, massive improvements in math, code, STEM, logic, creativity, and format-faithful outputs, while preserving general assistant quality and broadly neutral alignment.
51
 
 
 
 
52
  ## What’s new vs Hermes 3
53
 
54
  - **Post-training corpus**: Massively increased dataset size from 1M samples and 1.2B tokens to **~5M samples / ~60B tokens** blended across reasoning and non-reasoning data.
 
49
 
50
  Training highlights include a newly synthesized post-training corpus emphasizing verified reasoning traces, massive improvements in math, code, STEM, logic, creativity, and format-faithful outputs, while preserving general assistant quality and broadly neutral alignment.
51
 
52
+ **This is the FP8 version of Hermes 4, please see the <a href="https://huggingface.co/NousResearch/Hermes-4-70B"> BF16 Model </a> if looking for that.
53
+
54
+
55
  ## What’s new vs Hermes 3
56
 
57
  - **Post-training corpus**: Massively increased dataset size from 1M samples and 1.2B tokens to **~5M samples / ~60B tokens** blended across reasoning and non-reasoning data.