MihaiPopa-1 commited on
Commit
19544bb
·
verified ·
1 Parent(s): 4b69c5c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -20,7 +20,9 @@ CinnabarLM is a tiny, 4M-parameter LLM trained for ~33 minutes on a T4 GPU (on C
20
  # Why?
21
  Because it's a good idea to make tiny LLMs. Some people already did with [MicroLM](https://huggingface.co/CromIA/MicroLM-1M), [Spark 4 5M](https://huggingface.co/LH-Tech-AI/Spark-5M-Base-v4) and [Tenete 8M](https://huggingface.co/Harley-ml/Tenete-8M), but not myself!
22
 
23
- # Differences
 
 
24
 
25
  # Model Configurations
26
  | Parameter | Value |
 
20
  # Why?
21
  Because it's a good idea to make tiny LLMs. Some people already did with [MicroLM](https://huggingface.co/CromIA/MicroLM-1M), [Spark 4 5M](https://huggingface.co/LH-Tech-AI/Spark-5M-Base-v4) and [Tenete 8M](https://huggingface.co/Harley-ml/Tenete-8M), but not myself!
22
 
23
+ # Differences from Preview
24
+ * Now it's Llama-based, Preview was a custom model
25
+ * And of course, it's stable now (it doesn't generate gibberish / mess of words anymore)!
26
 
27
  # Model Configurations
28
  | Parameter | Value |