Commit
•
8e9d7c6
1
Parent(s):
c2f6184
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,53 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
4 |
+
datasets:
|
5 |
+
- NeuralNovel/Neural-Story-v1
|
6 |
+
library_name: transformers
|
7 |
+
inference: false
|
8 |
---
|
9 |
+
![Neural-Story](https://i.ibb.co/SdLF3bL/OIG-49.jpg)
|
10 |
+
|
11 |
+
# NeuralNovel/Tanuki-7B-v0.2
|
12 |
+
|
13 |
+
The **NeuralNovel/Tanuki-7B-v0.2**
|
14 |
+
|
15 |
+
Designed to generate instructive and narrative text, with a specific focus on storytelling.
|
16 |
+
This fine-tune has been tailored to provide detailed and creative responses in the context of narrative and optimised for short story telling.
|
17 |
+
|
18 |
+
Based on mistralAI, with apache-2.0 license, suitable for commercial or non-commercial use.
|
19 |
+
|
20 |
+
### Data-set
|
21 |
+
The model was finetuned using the Neural-Story-v1 dataset.
|
22 |
+
|
23 |
+
|
24 |
+
### Summary
|
25 |
+
|
26 |
+
Fine-tuned with the intention of generating creative and narrative text, making it more suitable for creative writing prompts and storytelling.
|
27 |
+
|
28 |
+
#### Out-of-Scope Use
|
29 |
+
|
30 |
+
The model may not perform well in scenarios unrelated to instructive and narrative text generation. Misuse or applications outside its designed scope may result in suboptimal outcomes.
|
31 |
+
|
32 |
+
### Bias, Risks, and Limitations
|
33 |
+
|
34 |
+
The model may exhibit biases or limitations inherent in the training data. It is essential to consider these factors when deploying the model to avoid unintended consequences.
|
35 |
+
|
36 |
+
While the Neural-Story-v0.1 dataset serves as an excellent starting point for testing language models, users are advised to exercise caution, as there might be some inherent genre or writing bias.
|
37 |
+
|
38 |
+
### Hardware and Training
|
39 |
+
|
40 |
+
Trained using NVIDIA Tesla T40 24 GB.
|
41 |
+
|
42 |
+
```
|
43 |
+
|
44 |
+
n_epochs = 3,
|
45 |
+
n_checkpoints = 3,
|
46 |
+
batch_size = 12,
|
47 |
+
learning_rate = 1e-5,
|
48 |
+
|
49 |
+
|
50 |
+
|
51 |
+
```
|
52 |
+
|
53 |
+
*Sincere appreciation to Techmind for their generous sponsorship.*
|