Update README.md
Browse files
README.md
CHANGED
|
@@ -48,6 +48,7 @@ Support me on Github Sponsors: https://github.com/sponsors/teknium1
|
|
| 48 |
- [BigBench](#bigbench)
|
| 49 |
- [Averages Compared](#averages-compared)
|
| 50 |
3. [Prompt Format](#prompt-format)
|
|
|
|
| 51 |
|
| 52 |
|
| 53 |
## Example Outputs
|
|
@@ -213,6 +214,9 @@ In LM-Studio, simply select the ChatML Prefix on the settings side pane:
|
|
| 213 |
|
| 214 |
# Quantized Models:
|
| 215 |
|
| 216 |
-
|
|
|
|
|
|
|
|
|
|
| 217 |
|
| 218 |
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
|
|
|
| 48 |
- [BigBench](#bigbench)
|
| 49 |
- [Averages Compared](#averages-compared)
|
| 50 |
3. [Prompt Format](#prompt-format)
|
| 51 |
+
4. [Quantized Models](#quantized-models)
|
| 52 |
|
| 53 |
|
| 54 |
## Example Outputs
|
|
|
|
| 214 |
|
| 215 |
# Quantized Models:
|
| 216 |
|
| 217 |
+
The Bloke has quantized Open Hermes 2 in GPTQ, GGUF, and AWQ! Avialable here:
|
| 218 |
+
https://huggingface.co/TheBloke/OpenHermes-2-Mistral-7B-GPTQ
|
| 219 |
+
https://huggingface.co/TheBloke/OpenHermes-2-Mistral-7B-GGUF
|
| 220 |
+
https://huggingface.co/TheBloke/OpenHermes-2-Mistral-7B-AWQ
|
| 221 |
|
| 222 |
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|