Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,64 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
inference: false
|
3 |
+
license: apache-2.0
|
4 |
+
tags:
|
5 |
+
- code
|
6 |
+
language:
|
7 |
+
- de
|
8 |
+
- en
|
9 |
+
quantized_by: VAGOsolutions
|
10 |
+
pipeline_tag: text-generation
|
11 |
+
base_model: VAGOsolutions/SauerkrautLM-1.5b
|
12 |
+
---
|
13 |
+
|
14 |
+
## Llamacpp GGUF Quantizations of SauerkrautLM-1.5b
|
15 |
+
|
16 |
+
|
17 |
+
Original model: https://huggingface.co/VAGOsolutions/SauerkrautLM-1.5b
|
18 |
+
|
19 |
+
|
20 |
+
|
21 |
+
## Prompt format
|
22 |
+
|
23 |
+
```
|
24 |
+
<|im_start|>system
|
25 |
+
You are SauerkrautLM, a helpful AI assistant.<|im_end|>
|
26 |
+
<|im_start|>user
|
27 |
+
{prompt}<|im_end|>
|
28 |
+
<|im_start|>assistant
|
29 |
+
```
|
30 |
+
|
31 |
+
```
|
32 |
+
<|im_start|>system
|
33 |
+
Du bist SauerkrautLM, ein hilfreicher KI-Assistent.<|im_end|>
|
34 |
+
<|im_start|>user
|
35 |
+
{prompt}<|im_end|>
|
36 |
+
<|im_start|>assistant
|
37 |
+
```
|
38 |
+
|
39 |
+
## Download a file (not the whole branch) from below:
|
40 |
+
|
41 |
+
| Filename | Quant type | File Size | Description |
|
42 |
+
| -------- | ---------- | --------- | ----------- |
|
43 |
+
| [SauerkrautLM-1.5b-Q8_0.gguf](https://huggingface.co/VAGOsolutions/SauerkrautLM-1.5b.GGUF/blob/main/SauerkrautLM-1.5b-Q8_0.gguf) | f16 | 3.1GB | Highest quality (no quant) |
|
44 |
+
| [SauerkrautLM-1.5b-Q8_0.gguf](https://huggingface.co/VAGOsolutions/SauerkrautLM-1.5b.GGUF/blob/main/SauerkrautLM-1.5b-Q8_0.gguf) | Q8_0 | 1.6GB | Extremely high quality, generally unneeded but max available quant. |
|
45 |
+
| [SauerkrautLM-1.5b-Q6_K.gguf](https://huggingface.co/VAGOsolutions/SauerkrautLM-1.5b.GGUF/blob/main/SauerkrautLM-1.5b-Q6_K.gguf) | Q6_K | 1.3GB | Very high quality, near perfect, *recommended*. |
|
46 |
+
| [SauerkrautLM-1.5b-Q5_K_M.gguf](https://huggingface.co/VAGOsolutions/SauerkrautLM-1.5b.GGUF/blob/main/SauerkrautLM-1.5b-Q5_K_M.gguf) | Q5_K_M | 1.1GB | High quality, *recommended*. |
|
47 |
+
| [SauerkrautLM-1.5b-Q5_K_S.gguf](https://huggingface.co/VAGOsolutions/SauerkrautLM-1.5b.GGUF/blob/main/SauerkrautLM-1.5b-Q5_K_S.gguf) | Q5_K_S | 1.1GB | High quality, *recommended*. |
|
48 |
+
| [SauerkrautLM-1.5b-Q4_K_M.gguf](https://huggingface.co/VAGOsolutions/SauerkrautLM-1.5b.GGUF/blob/main/SauerkrautLM-1.5b-Q4_K_M.gguf) | Q4_K_M | 0.98GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
|
49 |
+
| [SauerkrautLM-1.5b-Q4_K_S.gguf](https://huggingface.co/VAGOsolutions/SauerkrautLM-1.5b.GGUF/blob/main/SauerkrautLM-1.5b-Q4_K_S.gguf) | Q4_K_S | 0.94GB | Slightly lower quality with more space savings, *recommended*. |
|
50 |
+
|
51 |
+
## Downloading using huggingface-cli
|
52 |
+
|
53 |
+
First, make sure you have hugginface-cli installed:
|
54 |
+
|
55 |
+
```
|
56 |
+
pip install -U "huggingface_hub[cli]"
|
57 |
+
```
|
58 |
+
|
59 |
+
Then, you can target the specific file you want:
|
60 |
+
|
61 |
+
```
|
62 |
+
huggingface-cli download VAGOsolutions/SauerkrautLM-1.5b.GGUF --include "SauerkrautLM-1.5b-Q4_K_M.gguf" --local-dir ./
|
63 |
+
```
|
64 |
+
|