Update README.md
Browse files
README.md
CHANGED
|
@@ -25,9 +25,10 @@ It is the result of quantising to 4bit using [AutoGPTQ](https://github.com/PanQi
|
|
| 25 |
|
| 26 |
## Repositories available
|
| 27 |
|
| 28 |
-
* [
|
| 29 |
-
* [
|
| 30 |
-
* [
|
|
|
|
| 31 |
|
| 32 |
### Prompt template
|
| 33 |
|
|
|
|
| 25 |
|
| 26 |
## Repositories available
|
| 27 |
|
| 28 |
+
* [4-bit GPTQ model for GPU inference](https://huggingface.co/TheBloke/WizardLM-Uncensored-Falcon-40B-GPTQ)
|
| 29 |
+
* [3-bit GPTQ model for GPU inference](https://huggingface.co/TheBloke/WizardLM-Uncensored-Falcon-40B-3bit-GPTQ).
|
| 30 |
+
* [4, and 5-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/WizardLM-Uncensored-Falcon-40B-GGML)
|
| 31 |
+
* [Eric's unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/WizardLM-Uncensored-Falcon-40b)
|
| 32 |
|
| 33 |
### Prompt template
|
| 34 |
|