Commit
•
bef64c8
1
Parent(s):
12a9f58
Update README.md
Browse files
README.md
CHANGED
|
@@ -3,3 +3,16 @@ license: other
|
|
| 3 |
license_name: gemma-terms-of-use
|
| 4 |
license_link: https://ai.google.dev/gemma/terms
|
| 5 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
license_name: gemma-terms-of-use
|
| 4 |
license_link: https://ai.google.dev/gemma/terms
|
| 5 |
---
|
| 6 |
+
|
| 7 |
+
This repository contains gemma 2B models quantized using llama.cpp.
|
| 8 |
+
|
| 9 |
+
For details of the model see https://huggingface.co/google/gemma-2b-it.
|
| 10 |
+
|
| 11 |
+
Details of the k-quants can be found here: https://github.com/ggerganov/llama.cpp/pull/1684
|
| 12 |
+
|
| 13 |
+
## Provided files
|
| 14 |
+
|
| 15 |
+
| Name | Quant method | Bits | Size |
|
| 16 |
+
| ---- | ---- | ---- | ---- |
|
| 17 |
+
| [gemma-2b-it-Q4_K_M.gguf](https://huggingface.co/operablepattern/gemma-2b-it-Q/blob/main/gemma-2b-it-Q4_K_M.gguf) | Q4_K_M | 4 | 1.63 GB|
|
| 18 |
+
| [gemma-2b-it-Q5_K_M.gguf](https://huggingface.co/operablepattern/gemma-2b-it-Q/blob/main/gemma-2b-it-Q5_K_M.gguf) | Q5_K_M | 5 | 1.84 GB|
|