add model
Browse files- README.md +17 -0
- ggml-model-q8_0.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
thumbnail:
|
| 6 |
+
tags:
|
| 7 |
+
- text generation
|
| 8 |
+
- conversational
|
| 9 |
+
inference: false
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Pygmalion 7B (q8_0 ggml version)
|
| 13 |
+
|
| 14 |
+
Converted from the XORed weights from [PygmalionAI](https://huggingface.co/PygmalionAI/pygmalion-7b) (i.e. ready for use).
|
| 15 |
+
Additionally, converted from bfloat16 to float16.
|
| 16 |
+
Additionally, converted from float16 to ggml float16.
|
| 17 |
+
Additionally, quantized from ggml float16 to ggml q8_0.
|
ggml-model-q8_0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81abd7b8d04a08f9cf2b2c79e72513b0cb5fc016e3ea630bf30409b1bca8768a
|
| 3 |
+
size 7581934208
|