Deci
/

Text Generation
Transformers
Safetensors
English
Deci AI
DeciLM
custom_code
Eval Results
danaevan commited on
Commit
b66233e
1 Parent(s): 511f677

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -104,8 +104,7 @@ model-index:
104
  ---
105
  # DeciLM 6B
106
 
107
- DeciLM 6B is a 5.7 billion parameter decoder-only text generation model. With a context window of 4096 tokens, the highly efficient model uses variable Grouped-Query Attention (GQA) to achieve an optimal balance between performance and computational efficiency. The model's architecture was generated using Deci's proprietary Neural Architecture Search-based technology, AutoNAC. DeciLM 6B underwent training utilizing the SlimPajamas dataset, leveraging advanced proprietary methodologies allowing for fast training.
108
-
109
  ## Model Details
110
 
111
  ### Model Description
 
104
  ---
105
  # DeciLM 6B
106
 
107
+ DeciLM 6B is a 5.7 billion parameter decoder-only text generation model. With a context window of 4096 tokens, the highly efficient model uses variable Grouped-Query Attention (GQA) to achieve an optimal balance between performance and computational efficiency. The model's architecture was generated using Deci's proprietary Neural Architecture Search-based technology, AutoNAC.
 
108
  ## Model Details
109
 
110
  ### Model Description