Upload README.md
Browse files
README.md
CHANGED
@@ -10,8 +10,9 @@ model_creator: VAGO solutions
|
|
10 |
model_name: SauerkrautLM 70B v1
|
11 |
model_type: llama
|
12 |
pipeline_tag: text-generation
|
13 |
-
prompt_template: "
|
14 |
-
\ gibt hilfreiche, detaillierte und h\xF6fliche Antworten
|
|
|
15 |
quantized_by: TheBloke
|
16 |
---
|
17 |
<!-- markdownlint-disable MD041 -->
|
@@ -73,12 +74,13 @@ Here is an incomplate list of clients and libraries that are known to support GG
|
|
73 |
<!-- repositories-available end -->
|
74 |
|
75 |
<!-- prompt-template start -->
|
76 |
-
## Prompt template: Sauerkraut
|
77 |
|
78 |
```
|
79 |
-
|
80 |
-
|
81 |
-
|
|
|
82 |
|
83 |
```
|
84 |
|
@@ -229,7 +231,7 @@ Windows Command Line users: You can set the environment variable by running `set
|
|
229 |
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
|
230 |
|
231 |
```shell
|
232 |
-
./main -ngl 32 -m sauerkrautlm-70b-v1.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "
|
233 |
```
|
234 |
|
235 |
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
|
|
|
10 |
model_name: SauerkrautLM 70B v1
|
11 |
model_type: llama
|
12 |
pipeline_tag: text-generation
|
13 |
+
prompt_template: "[INST] <<SYS>>\nEin Chat zwischen einem Benutzer und einem KI-Assistenten.\
|
14 |
+
\ Der KI-Assistent gibt hilfreiche, detaillierte und h\xF6fliche Antworten.\n<</SYS>>\n\
|
15 |
+
{prompt}[/INST]\n"
|
16 |
quantized_by: TheBloke
|
17 |
---
|
18 |
<!-- markdownlint-disable MD041 -->
|
|
|
74 |
<!-- repositories-available end -->
|
75 |
|
76 |
<!-- prompt-template start -->
|
77 |
+
## Prompt template: Sauerkraut-Llama-2-Chat
|
78 |
|
79 |
```
|
80 |
+
[INST] <<SYS>>
|
81 |
+
Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten.
|
82 |
+
<</SYS>>
|
83 |
+
{prompt}[/INST]
|
84 |
|
85 |
```
|
86 |
|
|
|
231 |
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
|
232 |
|
233 |
```shell
|
234 |
+
./main -ngl 32 -m sauerkrautlm-70b-v1.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "[INST] <<SYS>>\nEin Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten.\n<</SYS>>\n{prompt}[/INST]"
|
235 |
```
|
236 |
|
237 |
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
|