MihaiPopa-1 commited on
Commit
14dc63b
·
verified ·
1 Parent(s): 1388ba8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -47,6 +47,7 @@ Because it's a good idea to make tiny LLMs. Some people already did with [MicroL
47
  * **Not Instruction-Tuned:** It's only a base model, so it only completes text.
48
  * **English-Only:** It's trained on English data (FineWeb), it's NOT multilingual.
49
  * **Not a Standard Model:** It's NOT a Qwen/Llama/GPT model. Standard Transformers can't recognize this!
 
50
 
51
  # Some other details
52
  * It's trained on 80 million tokens of [FineWeb](https://huggingface.co/datasets/HuggingFaceFW/fineweb) (CC-MAIN-2025-26 snapshot), and the knowledge cutoff is June 2025.
 
47
  * **Not Instruction-Tuned:** It's only a base model, so it only completes text.
48
  * **English-Only:** It's trained on English data (FineWeb), it's NOT multilingual.
49
  * **Not a Standard Model:** It's NOT a Qwen/Llama/GPT model. Standard Transformers can't recognize this!
50
+ * **Preview:** This is a preview version, it generates gibberish often. CinnabarLM 1 will solve this with Llama.
51
 
52
  # Some other details
53
  * It's trained on 80 million tokens of [FineWeb](https://huggingface.co/datasets/HuggingFaceFW/fineweb) (CC-MAIN-2025-26 snapshot), and the knowledge cutoff is June 2025.