Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,7 @@
|
|
| 1 |
|
| 2 |
|
|
|
|
|
|
|
| 3 |
This model is a GGUF quantization of Dolphin-2.6-Mixtral. Original model @ cognitivecomputations/dolphin-2.6-mixtral-8x7b
|
| 4 |
|
| 5 |
For now I am only providing the 4 bit Q_K_M which has a very impressive performance, retaining the main reasoning and logic capabilities, but still enabling anyone to run it on a 24GB consumer grade hardware with GGML + 26/33 layers being offloaded to the GPU.
|
|
|
|
| 1 |
|
| 2 |
|
| 3 |
+
Discord https://discord.gg/SmbBewAM
|
| 4 |
+
|
| 5 |
This model is a GGUF quantization of Dolphin-2.6-Mixtral. Original model @ cognitivecomputations/dolphin-2.6-mixtral-8x7b
|
| 6 |
|
| 7 |
For now I am only providing the 4 bit Q_K_M which has a very impressive performance, retaining the main reasoning and logic capabilities, but still enabling anyone to run it on a 24GB consumer grade hardware with GGML + 26/33 layers being offloaded to the GPU.
|