Text Generation
Transformers
Safetensors
llama
Not-For-All-Audiences
nsfw
text-generation-inference
Inference Endpoints
Commit
•
fca2891
1
Parent(s):
501240a
Update README.md
Browse files
README.md
CHANGED
|
@@ -13,9 +13,13 @@ Requires ExllamaV2, which is being developed by turboderp https://github.com/tur
|
|
| 13 |
|
| 14 |
Main branch is 4.6bpw 8h (req ??gb)
|
| 15 |
|
|
|
|
|
|
|
| 16 |
5.0b8h branch is 5.0bpw 8h (req ??gb)
|
| 17 |
|
| 18 |
-
|
|
|
|
|
|
|
| 19 |
|
| 20 |
--------
|
| 21 |
<center>[<a href="https://huggingface.co/Undi95/Dawn-v2-70B">fp16</a> - <a href="https://huggingface.co/Undi95/Dawn-v2-70B-GGUF">gguf</a> - exl2 : <a href="https://huggingface.co/Undi95/Dawn-v2-70B-2.4bpw-h6-exl2">2.40bpw</a> - <a href="https://huggingface.co/Undi95/Dawn-v2-70B-2.55bpw-h6-exl2">2.55bpw</a>]</center>
|
|
|
|
| 13 |
|
| 14 |
Main branch is 4.6bpw 8h (req ??gb)
|
| 15 |
|
| 16 |
+
2.5b8h branch is 2.55bpw 8h (req 24gb and the 8b cache setting) - Add BOS token must be unchecked at this weight or output is nonsense.
|
| 17 |
+
|
| 18 |
5.0b8h branch is 5.0bpw 8h (req ??gb)
|
| 19 |
|
| 20 |
+
6b8h branch is coming soon
|
| 21 |
+
|
| 22 |
+
|
| 23 |
|
| 24 |
--------
|
| 25 |
<center>[<a href="https://huggingface.co/Undi95/Dawn-v2-70B">fp16</a> - <a href="https://huggingface.co/Undi95/Dawn-v2-70B-GGUF">gguf</a> - exl2 : <a href="https://huggingface.co/Undi95/Dawn-v2-70B-2.4bpw-h6-exl2">2.40bpw</a> - <a href="https://huggingface.co/Undi95/Dawn-v2-70B-2.55bpw-h6-exl2">2.55bpw</a>]</center>
|