Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,14 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
+
# Open Llama 7b GGML Models
|
| 5 |
+
|
| 6 |
+
This repository contains the GGML models for the latest 700 billion token (700bt) preview of the Open Llama 7b model.
|
| 7 |
+
|
| 8 |
+
The following files can be used with `llama.cpp` or `kobold.cpp`:
|
| 9 |
+
|
| 10 |
+
- `ggml-model-q4_0.bin`: Quantized model, 3.79 GB
|
| 11 |
+
- `ggml-model-q4_1.bin`: Quantized model, 4.21 GB
|
| 12 |
+
- `ggml-model-q5_0.bin`: Quantized model, 4.63 GB
|
| 13 |
+
- `ggml-model-q5_1.bin`: Quantized model, 5.06 GB
|
| 14 |
+
- `ggml-model-q8_0.bin`: Quantized model, 7.16 GB
|