Update README.md
Browse files
README.md
CHANGED
@@ -16,7 +16,7 @@ language:
|
|
16 |
<img src="SambaLingo_Logo.png" width="340" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
17 |
|
18 |
<!-- Provide a quick summary of what the model is/does. -->
|
19 |
-
SambaLingo-Slovenian-Chat is a human aligned chat model trained in Slovenian and English. It is trained using direct preference optimization on top the base model [SambaLingo-Slovenian-Base](https://huggingface.co/sambanovasystems/SambaLingo-Slovenian-Base). The base model adapts [Llama-2-7b](https://huggingface.co/meta-llama/Llama-2-7b-hf) to Slovenian by training on 17 billion tokens from the Slovenian split of the [Cultura-X](https://huggingface.co/datasets/uonlp/CulturaX) dataset.
|
20 |
|
21 |
## Model Description
|
22 |
<!-- Provide a longer summary of what this model is. -->
|
@@ -25,6 +25,7 @@ SambaLingo-Slovenian-Chat is a human aligned chat model trained in Slovenian and
|
|
25 |
- **Model type:** Language Model
|
26 |
- **Language(s):** Slovenian, English
|
27 |
- **Finetuned from model:** [Llama-2-7b](https://huggingface.co/meta-llama/Llama-2-7b-hf)
|
|
|
28 |
- **Blog Post**: Will be released soon!
|
29 |
|
30 |
## Getting Started
|
@@ -59,14 +60,14 @@ outputs = outputs["generated_text"]
|
|
59 |
### Prompting Guidelines
|
60 |
To prompt this model, please use the following chat template:
|
61 |
```
|
62 |
-
<|user
|
63 |
```
|
64 |
|
65 |
### Example Prompts and Generations
|
66 |
```
|
67 |
-
<|user
|
68 |
Kdaj je bil ustvarjen google? Zakaj je prevladoval nad drugimi iskalniki?</s>
|
69 |
-
<|assistant
|
70 |
Google je bil ustanovljen septembra 1998 v garaži Larryja Pagea in Sergeya Brina v Mountain Viewu v Kaliforniji.
|
71 |
|
72 |
Google je prevladoval nad drugimi iskalniki zaradi več dejavnikov:
|
|
|
16 |
<img src="SambaLingo_Logo.png" width="340" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
17 |
|
18 |
<!-- Provide a quick summary of what the model is/does. -->
|
19 |
+
SambaLingo-Slovenian-Chat is a human aligned chat model trained in Slovenian and English. It is trained using direct preference optimization on top the base model [SambaLingo-Slovenian-Base](https://huggingface.co/sambanovasystems/SambaLingo-Slovenian-Base). The base model adapts [Llama-2-7b](https://huggingface.co/meta-llama/Llama-2-7b-hf) to Slovenian by training on 17 billion tokens from the Slovenian split of the [Cultura-X](https://huggingface.co/datasets/uonlp/CulturaX) dataset. Try this model at [SambaLingo-chat-space](https://huggingface.co/spaces/sambanovasystems/SambaLingo-chat-space).
|
20 |
|
21 |
## Model Description
|
22 |
<!-- Provide a longer summary of what this model is. -->
|
|
|
25 |
- **Model type:** Language Model
|
26 |
- **Language(s):** Slovenian, English
|
27 |
- **Finetuned from model:** [Llama-2-7b](https://huggingface.co/meta-llama/Llama-2-7b-hf)
|
28 |
+
- **Try this model:** [SambaLingo-chat-space](https://huggingface.co/spaces/sambanovasystems/SambaLingo-chat-space)
|
29 |
- **Blog Post**: Will be released soon!
|
30 |
|
31 |
## Getting Started
|
|
|
60 |
### Prompting Guidelines
|
61 |
To prompt this model, please use the following chat template:
|
62 |
```
|
63 |
+
<|user|>\n{question}</s>\n<|assistant|>\n
|
64 |
```
|
65 |
|
66 |
### Example Prompts and Generations
|
67 |
```
|
68 |
+
<|user|>
|
69 |
Kdaj je bil ustvarjen google? Zakaj je prevladoval nad drugimi iskalniki?</s>
|
70 |
+
<|assistant|>
|
71 |
Google je bil ustanovljen septembra 1998 v garaži Larryja Pagea in Sergeya Brina v Mountain Viewu v Kaliforniji.
|
72 |
|
73 |
Google je prevladoval nad drugimi iskalniki zaradi več dejavnikov:
|