Update README.md
#5
by
MaziyarPanahi
- opened
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=
|
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,
|