Update README.md
Browse files
README.md
CHANGED
@@ -14,7 +14,14 @@ inference: false
|
|
14 |
### This repository contains quantized conversions of the current Pygmalion 6B checkpoints.
|
15 |
*For use with frontends that support GGML quantized GPT-J models, such as KoboldCpp and Oobabooga (with the CTransformers loader).*
|
16 |
|
17 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
|
19 |
The original model card can be found below.
|
20 |
|
|
|
14 |
### This repository contains quantized conversions of the current Pygmalion 6B checkpoints.
|
15 |
*For use with frontends that support GGML quantized GPT-J models, such as KoboldCpp and Oobabooga (with the CTransformers loader).*
|
16 |
|
17 |
+
Model | Startup RAM usage (KoboldCpp) | Startup RAM usage (Oobabooga)
|
18 |
+
:--:|:--:|:--:
|
19 |
+
pygmalion-6b-main.q4_0.bin | Placeholder | Placeholder
|
20 |
+
pygmalion-6b-main.q4_1.bin | Placeholder | Placeholder
|
21 |
+
pygmalion-6b-main.q5_0.bin | Placeholder | Placeholder
|
22 |
+
pygmalion-6b-main.q5_1.bin | Placeholder | Placeholder
|
23 |
+
pygmalion-6b-main.q8_0.bin | Placeholder | Placeholder
|
24 |
+
pygmalion-6b-main.f16.bin | Placeholder | Placeholder
|
25 |
|
26 |
The original model card can be found below.
|
27 |
|