PEFT
Safetensors
Transformers
English
text-generation-inference
unsloth
llama
trl
Not-For-All-Audiences
mpasila commited on
Commit
2d1cc78
1 Parent(s): 61b2451

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -23,6 +23,8 @@ Dataset used is [a modified](https://huggingface.co/datasets/mpasila/LimaRP-augm
23
 
24
  ### Prompt format: Llama 3 Instruct
25
 
 
 
26
  # Uploaded model
27
 
28
  - **Developed by:** mpasila
 
23
 
24
  ### Prompt format: Llama 3 Instruct
25
 
26
+ There might be a slight issue with the prompt formatting since Unsloth decided to leave "gpt" and "user" to the prompts which seem to not be handled correctly all the time.
27
+
28
  # Uploaded model
29
 
30
  - **Developed by:** mpasila