AuriAetherwiing
commited on
Commit
•
28e06c0
1
Parent(s):
8237ceb
Update README.md
Browse files
README.md
CHANGED
@@ -21,6 +21,7 @@ base_model:
|
|
21 |
<li><a href=https://huggingface.co/mradermacher/EVA-Yi-1.5-9B-32K-V1-GGUF>Static GGUF by Mradermacher</a></li>
|
22 |
<li><a href=https://huggingface.co/bartowski/EVA-Yi-1.5-9B-32K-V1-exl2>EXL2 by bartowski</a></li>
|
23 |
</ul>
|
|
|
24 |
</p>
|
25 |
<p>
|
26 |
Prompt format is ChatML.<br>
|
|
|
21 |
<li><a href=https://huggingface.co/mradermacher/EVA-Yi-1.5-9B-32K-V1-GGUF>Static GGUF by Mradermacher</a></li>
|
22 |
<li><a href=https://huggingface.co/bartowski/EVA-Yi-1.5-9B-32K-V1-exl2>EXL2 by bartowski</a></li>
|
23 |
</ul>
|
24 |
+
We recommend using original BFloat16 weights, quantization seems to affect Yi significantly more than other model architectures.
|
25 |
</p>
|
26 |
<p>
|
27 |
Prompt format is ChatML.<br>
|