LH-Tech-AI commited on
Commit
6ea3d43
·
verified ·
1 Parent(s): f995611

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -27,8 +27,10 @@ Today, we are introducing Spark v4, a 5M parameter Llama base model trained on 0
27
  - LAMBADA (PPL): 588.26
28
  - HellaSwag: 0.2695
29
 
 
 
30
  ## Usage
31
- You can use the model with `use.py`.
32
 
33
  ## Example output
34
  **Input:** The main concept of physics<br>
 
27
  - LAMBADA (PPL): 588.26
28
  - HellaSwag: 0.2695
29
 
30
+ More information about the Spark Sub-5M research: https://lh-tech.de/ai/sub-5m-research.html
31
+
32
  ## Usage
33
+ You can use the model with `use.py`. But first you'll need to download `config.json`, `tokenizer.json`, `tokenizer_config.json`, `model.safetensors` and `generation_config.json` and put these files into a subfolder `spark_v4_fp16_final`.
34
 
35
  ## Example output
36
  **Input:** The main concept of physics<br>