Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,43 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
library_name: peft
|
6 |
+
base_model: unsloth/mistral-7b-v0.2-bnb-4bit
|
7 |
+
datasets:
|
8 |
+
- molbal/dramallama-novels
|
9 |
+
pipeline_tag: text-generation
|
10 |
+
tags:
|
11 |
+
- art
|
12 |
---
|
13 |
+
|
14 |
+
|
15 |
+
|
16 |
+
# Model Card for molbal/drama-mistral
|
17 |
+
|
18 |
+
Text completion model trained on public domain novels.
|
19 |
+
|
20 |
+
|
21 |
+
## Model Details
|
22 |
+
|
23 |
+
### Model Description
|
24 |
+
|
25 |
+
This model is trained on a large corpus of novels from various drama categories, including detective fiction, crime nonfiction,
|
26 |
+
mystery fiction, gothic fiction, horror, romantic fiction, short stories, and western. The model is able to generate text that
|
27 |
+
is similar in style and tone to the novels in the dataset.
|
28 |
+
|
29 |
+
|
30 |
+
|
31 |
+
- **Developed by:** Bálint Molnár-Kaló https://huggingface.co/molbal
|
32 |
+
- **Model type:** TText completion model
|
33 |
+
- **Language(s) (NLP):** English only
|
34 |
+
- **License:** Apache license 2.0
|
35 |
+
- **Finetuned from model [optional]:** unsloth/mistral-7b-v0.2-bnb-4bit
|
36 |
+
|
37 |
+
### Model Sources
|
38 |
+
|
39 |
+
- **Repository:** https://huggingface.co/datasets/molbal/dramallama-novels
|
40 |
+
- **Demo:** https://huggingface.co/datasets/molbal/dramallama-novels/viewer/default/train
|
41 |
+
|
42 |
+
### Training details
|
43 |
+
Trained for ~19 hours on a RTX 4090 using Unsloth and its wrapper scripts found in https://github.com/molbal/llm-text-completion-finetune uing the cloud provider vast.ai
|