Update README.md
Browse files
README.md
CHANGED
|
@@ -33,6 +33,15 @@ GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/gger
|
|
| 33 |
* [4-bit, 5-bit, and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/Samantha-7B-GGML)
|
| 34 |
* [Eric's original unquantised fp16 model in HF format](https://huggingface.co/ehartford/samantha-7b)
|
| 35 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
## THE FILES IN MAIN BRANCH REQUIRES LATEST LLAMA.CPP (May 19th 2023 - commit 2d5db48)!
|
| 37 |
|
| 38 |
llama.cpp recently made another breaking change to its quantisation methods - https://github.com/ggerganov/llama.cpp/pull/1508
|
|
|
|
| 33 |
* [4-bit, 5-bit, and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/Samantha-7B-GGML)
|
| 34 |
* [Eric's original unquantised fp16 model in HF format](https://huggingface.co/ehartford/samantha-7b)
|
| 35 |
|
| 36 |
+
## Prompt template
|
| 37 |
+
|
| 38 |
+
```
|
| 39 |
+
<system prompt>
|
| 40 |
+
|
| 41 |
+
USER: <prompt>
|
| 42 |
+
ASSISTANT:
|
| 43 |
+
```
|
| 44 |
+
|
| 45 |
## THE FILES IN MAIN BRANCH REQUIRES LATEST LLAMA.CPP (May 19th 2023 - commit 2d5db48)!
|
| 46 |
|
| 47 |
llama.cpp recently made another breaking change to its quantisation methods - https://github.com/ggerganov/llama.cpp/pull/1508
|