Update README.md
Browse files
README.md
CHANGED
|
@@ -2,4 +2,18 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
|
| 5 |
-
Converted using ggerganov/ggml's "stablelm" conversion script and quantization code as of [commit 05f3079](https://github.com/ggerganov/ggml/tree/05f307971862b83df12fada0c42ee027ba5a82b5/examples/stablelm) (2023-04-20). Should be compatible with KoboldCpp.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
|
| 5 |
+
Converted using ggerganov/ggml's "stablelm" conversion script and quantization code as of [commit 05f3079](https://github.com/ggerganov/ggml/tree/05f307971862b83df12fada0c42ee027ba5a82b5/examples/stablelm) (2023-04-20). Should be compatible with KoboldCpp.
|
| 6 |
+
|
| 7 |
+
NOTES: pythia-70m-deduped gave garbage output in my testing. The models are still being uploaded.
|
| 8 |
+
|
| 9 |
+
# RAM USAGE (koboldcpp):
|
| 10 |
+
Model | RAM
|
| 11 |
+
:--:|:--:
|
| 12 |
+
ggml-pythia-70m-deduped-q4_3.bin | 121.2 MiB
|
| 13 |
+
ggml-pythia-160m-deduped-q4_3.bin | 225.2 MiB
|
| 14 |
+
ggml-pythia-410m-deduped-q4_3.bin | 498.1 MiB
|
| 15 |
+
ggml-pythia-1b-deduped-q4_3.bin | 951.5 MiB
|
| 16 |
+
ggml-pythia-1.4b-deduped-q4_3.bin | 1.3 GiB
|
| 17 |
+
ggml-pythia-2.8b-deduped-q4_3.bin | 2.4 GiB
|
| 18 |
+
ggml-pythia-6.9b-deduped-q4_3.bin | 5.4 GiB
|
| 19 |
+
ggml-pythia-12b-deduped-q4_3.bin | Still being converted
|