Update README.md
Browse files
README.md
CHANGED
|
@@ -7,6 +7,12 @@ This is an HF format unquantised model of [CarterAI's StableVicuna 13B](https://
|
|
| 7 |
|
| 8 |
It is the result of merging the deltas from the above repository with the original Llama 13B weights.
|
| 9 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
# Original StableVicuna-13B model card
|
| 11 |
|
| 12 |
## Model Description
|
|
|
|
| 7 |
|
| 8 |
It is the result of merging the deltas from the above repository with the original Llama 13B weights.
|
| 9 |
|
| 10 |
+
## Repositories available
|
| 11 |
+
|
| 12 |
+
* [4bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/stable-vicuna-13B-GPTQ).
|
| 13 |
+
* [4bit and 5bit GGML models for CPU inference](https://huggingface.co/TheBloke/stable-vicuna-13B-GGML).
|
| 14 |
+
* [Unquantised 16bit model in HF format](https://huggingface.co/TheBloke/stable-vicuna-13B-HF).
|
| 15 |
+
|
| 16 |
# Original StableVicuna-13B model card
|
| 17 |
|
| 18 |
## Model Description
|