Update README.md
Browse files
README.md
CHANGED
@@ -29,7 +29,10 @@ Created by: [upstage](https://huggingface.co/upstage)
|
|
29 |
[Q6_K](https://huggingface.co/cgus/SOLAR-10.7B-Instruct-v1.0-128k-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-128k-Q6_K.gguf?download=true)
|
30 |
[Q8_0](https://huggingface.co/cgus/SOLAR-10.7B-Instruct-v1.0-128k-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-128k-Q8_0.gguf?download=true)
|
31 |
[FP16](https://huggingface.co/cgus/SOLAR-10.7B-Instruct-v1.0-128k-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-128k-FP16.gguf?download=true)
|
32 |
-
|
|
|
|
|
|
|
33 |
## My notes about this model:
|
34 |
Honestly, I have no idea how YARN models supposed to work out of the box.
|
35 |
Llama.cpp should have proper YARN support but I haven't seen good enough information about real life application of this feature.
|
|
|
29 |
[Q6_K](https://huggingface.co/cgus/SOLAR-10.7B-Instruct-v1.0-128k-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-128k-Q6_K.gguf?download=true)
|
30 |
[Q8_0](https://huggingface.co/cgus/SOLAR-10.7B-Instruct-v1.0-128k-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-128k-Q8_0.gguf?download=true)
|
31 |
[FP16](https://huggingface.co/cgus/SOLAR-10.7B-Instruct-v1.0-128k-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-128k-FP16.gguf?download=true)
|
32 |
+
|
33 |
+
There's also an alternative repo with iMatrix calibration:
|
34 |
+
[SOLAR-10.7B-Instruct-v1.0-128k-iMat-GGUF](https://huggingface.co/cgus/SOLAR-10.7B-Instruct-v1.0-128k-iMat-GGUF)
|
35 |
+
|
36 |
## My notes about this model:
|
37 |
Honestly, I have no idea how YARN models supposed to work out of the box.
|
38 |
Llama.cpp should have proper YARN support but I haven't seen good enough information about real life application of this feature.
|