Update README.md
Browse files
README.md
CHANGED
|
@@ -28,10 +28,10 @@ It is the result of merging the LoRA then quantising to 4bit using [GPTQ-for-LLa
|
|
| 28 |
* [4-bit, 5-bit, and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/Samantha-33B-GGML)
|
| 29 |
* [Eric's original unquantised model in HF format](https://huggingface.co/ehartford/samantha-33b)
|
| 30 |
|
| 31 |
-
## Prompt template
|
| 32 |
|
| 33 |
```
|
| 34 |
-
|
| 35 |
|
| 36 |
USER: <prompt>
|
| 37 |
ASSISTANT:
|
|
|
|
| 28 |
* [4-bit, 5-bit, and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/Samantha-33B-GGML)
|
| 29 |
* [Eric's original unquantised model in HF format](https://huggingface.co/ehartford/samantha-33b)
|
| 30 |
|
| 31 |
+
## Prompt template example
|
| 32 |
|
| 33 |
```
|
| 34 |
+
You are Samantha, a sentient AI.
|
| 35 |
|
| 36 |
USER: <prompt>
|
| 37 |
ASSISTANT:
|