Commit
•
9ad4ea4
1
Parent(s):
fd221c8
Update README.md
Browse files
README.md
CHANGED
|
@@ -86,8 +86,6 @@ license: llama3
|
|
| 86 |
</ul>
|
| 87 |
<p><a href="https://huggingface.co/turboderp/Cat-Llama-3-70B-instruct">70b variant of the model</a> (Trained by Dr. Kal'tsit, Posted by Turboderp), Please check it out!</p>
|
| 88 |
<h2>About:</h2>
|
| 89 |
-
<p>Issues known:
|
| 90 |
-
the model spits out < /s> out at the end of every sequence due to a tokenizer/model error in the training config. Will be fixed in a later version. -Steel </p>
|
| 91 |
<p>Cat-llama3-instruct is a llama 3 8b finetuned model focusing on system prompt fidelity, helpfulness and character engagement. The model aims to respect system prompt to an extreme degree, provide helpful information regardless of situations, and offer maximum character immersion (Role Play) in given scenes.</p>
|
| 92 |
<h2>Specific Aims:</h2>
|
| 93 |
<ul>
|
|
|
|
| 86 |
</ul>
|
| 87 |
<p><a href="https://huggingface.co/turboderp/Cat-Llama-3-70B-instruct">70b variant of the model</a> (Trained by Dr. Kal'tsit, Posted by Turboderp), Please check it out!</p>
|
| 88 |
<h2>About:</h2>
|
|
|
|
|
|
|
| 89 |
<p>Cat-llama3-instruct is a llama 3 8b finetuned model focusing on system prompt fidelity, helpfulness and character engagement. The model aims to respect system prompt to an extreme degree, provide helpful information regardless of situations, and offer maximum character immersion (Role Play) in given scenes.</p>
|
| 90 |
<h2>Specific Aims:</h2>
|
| 91 |
<ul>
|