Update README.md
Browse files
README.md
CHANGED
@@ -34,6 +34,13 @@ GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/gger
|
|
34 |
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/baichuan-vicuna-7B-GGML)
|
35 |
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/fireballoon/baichuan-vicuna-7b)
|
36 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
37 |
<!-- compatibility_ggml start -->
|
38 |
## Compatibility
|
39 |
|
@@ -87,7 +94,7 @@ Refer to the Provided Files table below to see what files use which methods, and
|
|
87 |
I use the following command line; adjust for your tastes and needs:
|
88 |
|
89 |
```
|
90 |
-
./main -t 10 -ngl 32 -m baichuan-vicuna-7b.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "
|
91 |
```
|
92 |
If you're able to use full GPU offloading, you should use `-t 1` to get best performance.
|
93 |
|
|
|
34 |
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/baichuan-vicuna-7B-GGML)
|
35 |
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/fireballoon/baichuan-vicuna-7b)
|
36 |
|
37 |
+
## Prompt template: Vicuna 1.1
|
38 |
+
```
|
39 |
+
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
|
40 |
+
USER: prompt
|
41 |
+
ASSISTANT:
|
42 |
+
```
|
43 |
+
|
44 |
<!-- compatibility_ggml start -->
|
45 |
## Compatibility
|
46 |
|
|
|
94 |
I use the following command line; adjust for your tastes and needs:
|
95 |
|
96 |
```
|
97 |
+
./main -t 10 -ngl 32 -m baichuan-vicuna-7b.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "USER: Write a story about llamas\nASSISTANT:"
|
98 |
```
|
99 |
If you're able to use full GPU offloading, you should use `-t 1` to get best performance.
|
100 |
|