Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -27,9 +27,9 @@ datasets:
27
  <img src="./llama-3-merges.webp" alt="Llama-3 DPO Logo" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
28
 
29
 
30
- # Llama-3-8B-Instruct-DPO-v0.3
31
 
32
- This model is a fine-tune (DPO) of `meta-llama/Meta-Llama-3-8B-Instruct` model.
33
 
34
  # How to use
35
 
@@ -86,7 +86,7 @@ terminators = [
86
 
87
  outputs = pipeline(
88
  prompt,
89
- max_new_tokens=256,
90
  eos_token_id=terminators,
91
  do_sample=True,
92
  temperature=0.6,
 
27
  <img src="./llama-3-merges.webp" alt="Llama-3 DPO Logo" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
28
 
29
 
30
+ # Llama-3-8B-Instruct-DPO-v0.3 (32k)
31
 
32
+ This model is a fine-tune (DPO) of `meta-llama/Meta-Llama-3-8B-Instruct` model. I have used `rope_theta` to extend the context length up to 32K safely.
33
 
34
  # How to use
35
 
 
86
 
87
  outputs = pipeline(
88
  prompt,
89
+ max_new_tokens=8192,
90
  eos_token_id=terminators,
91
  do_sample=True,
92
  temperature=0.6,