Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- norygano/TRACHI
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
---
|
8 |
+
|
9 |
+
# dolphin-mistral-TRACHI-7b
|
10 |
+
|
11 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
12 |
+
|
13 |
+
Quantized versions of the fine-tuned [
|
14 |
+
dolphin-2.2.1-mistral-7b ](https://huggingface.co/cognitivecomputations/dolphin-2.2.1-mistral-7b) on TRACHI datasets.
|
15 |
+
|
16 |
+
## Model Details
|
17 |
+
This is a model that aims to facilitate conversation with TRACHI characters. Its used by [Discord Bots](https://discord.gg/mcRke7vB7X) running on a local Ollama server.
|
18 |
+
|
19 |
+
### Model Description
|
20 |
+
Characters can be prompted by including their name in the system role within the prompt:
|
21 |
+
|
22 |
+
```plaintext
|
23 |
+
<|im_start|>system
|
24 |
+
{character}<|im_end|>
|
25 |
+
<|im_start|>user
|
26 |
+
{prompt}<|im_end|>
|
27 |
+
<|im_start|>assistant
|
28 |
+
```
|
29 |
+
|
30 |
+
## Bias, Risks, and Limitations
|
31 |
+
|
32 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
33 |
+
Like the base model ([
|
34 |
+
dolphin-2.2.1-mistral-7b ](https://huggingface.co/cognitivecomputations/dolphin-2.2.1-mistral-7b)), this fine-tune is unbiased and uncensored.
|