dranger003 commited on
Commit
e67b83f
1 Parent(s): a137779

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -6,6 +6,9 @@ pipeline_tag: text-generation
6
  GGUF importance matrix (imatrix) quants for https://huggingface.co/codellama/CodeLlama-70b-Instruct-hf
7
  The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using wiki.train.raw.
8
 
 
 
 
9
  | Layers | Context | Template |
10
  | --- | --- | --- |
11
  | <pre>0</pre> | <pre>4096</pre> | <pre>\<s\> Source: system<br><br> {instructions}\<step\> Source: user<br><br> {prompt}\<step\> Source: assistant<br>Destination: user<br><br> {response}</pre> |
 
6
  GGUF importance matrix (imatrix) quants for https://huggingface.co/codellama/CodeLlama-70b-Instruct-hf
7
  The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using wiki.train.raw.
8
 
9
+ The template for this model is very sensitive and must be set very precisely.
10
+ All whitespace are intended, and special tokens `<s>` and `<step>` must be encodded properly.
11
+
12
  | Layers | Context | Template |
13
  | --- | --- | --- |
14
  | <pre>0</pre> | <pre>4096</pre> | <pre>\<s\> Source: system<br><br> {instructions}\<step\> Source: user<br><br> {prompt}\<step\> Source: assistant<br>Destination: user<br><br> {response}</pre> |