Update README.md
Browse files
README.md
CHANGED
@@ -10,15 +10,15 @@ tags:
|
|
10 |
- Storywriter
|
11 |
---
|
12 |
|
13 |
-
# GOAT-70B-
|
14 |
|
15 |
-
![GOAT-70B-
|
16 |
|
17 |
GOAT-70B-Storytelling model developed by GOAT.AI lab for autonomous story-writing.
|
18 |
|
19 |
|
20 |
-
# GOAT-
|
21 |
-
The GOAT-70B-
|
22 |
|
23 |
Generated examples can be accessed [here](https://huggingface.co/datasets/GOAT-AI/generated-novels)
|
24 |
# Model description
|
@@ -29,10 +29,10 @@ Generated examples can be accessed [here](https://huggingface.co/datasets/GOAT-A
|
|
29 |
### Learn more
|
30 |
|
31 |
- **Blog:** TBA
|
32 |
-
- **
|
33 |
## Uses
|
34 |
|
35 |
-
The main purpose of GOAT-70B-
|
36 |
|
37 |
## Usage
|
38 |
|
@@ -44,7 +44,7 @@ import torch
|
|
44 |
|
45 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
46 |
|
47 |
-
model_name = "GOAT-AI/GOAT-70B-
|
48 |
|
49 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
50 |
model = AutoModelForCausalLM.from_pretrained(
|
@@ -52,11 +52,11 @@ model = AutoModelForCausalLM.from_pretrained(
|
|
52 |
torch_dtype=torch.bfloat16
|
53 |
)
|
54 |
```
|
55 |
-
Currently, we support LLM endpoint generation, where you need to send a post request to generation endpoint (we recommend using Text Generation Inference by HuggingFace)
|
56 |
|
57 |
First, modify config.py and add your generation endpoint.
|
58 |
|
59 |
-
Then you can use it inside via GOAT-
|
60 |
|
61 |
```python
|
62 |
from goat_storytelling_agent.story_processor.prompt_manager import generate_story
|
@@ -65,10 +65,10 @@ novel_scenes = generate_story('never too much coffee', form='novel')
|
|
65 |
```
|
66 |
## License
|
67 |
|
68 |
-
GOAT-70B-
|
69 |
|
70 |
-
GOAT-70B-
|
71 |
|
72 |
### Risks and Biases
|
73 |
|
74 |
-
GOAT-70B-
|
|
|
10 |
- Storywriter
|
11 |
---
|
12 |
|
13 |
+
# GOAT-70B-Storytelling model
|
14 |
|
15 |
+
![GOAT-70B-Storytelling](https://assets.adapt.ws/files/20231117_ehznrqludevtapck.png)
|
16 |
|
17 |
GOAT-70B-Storytelling model developed by GOAT.AI lab for autonomous story-writing.
|
18 |
|
19 |
|
20 |
+
# GOAT-Storytelling-Agent
|
21 |
+
The GOAT-70B-Storytelling model has been developed as an integral component within the GOAT-Storytelling-Agent. This agent facilitates the generation of high-quality, cohesive, and captivating narratives, including stories and books. It achieves this by utilizing inputs such as plot outlines, character profiles, their interrelationships, and other relevant details. Example is provided below.
|
22 |
|
23 |
Generated examples can be accessed [here](https://huggingface.co/datasets/GOAT-AI/generated-novels)
|
24 |
# Model description
|
|
|
29 |
### Learn more
|
30 |
|
31 |
- **Blog:** TBA
|
32 |
+
- **GitHub:** github.com/GOAT-Storytelling-Agent (TBA)
|
33 |
## Uses
|
34 |
|
35 |
+
The main purpose of GOAT-70B-Storytelling is to generate books, novels, movie scripts and etc. as an agent in coping with our GOAT-Storytelling-Agent. It is specifically designed for storywriters.
|
36 |
|
37 |
## Usage
|
38 |
|
|
|
44 |
|
45 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
46 |
|
47 |
+
model_name = "GOAT-AI/GOAT-70B-Storytelling"
|
48 |
|
49 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
50 |
model = AutoModelForCausalLM.from_pretrained(
|
|
|
52 |
torch_dtype=torch.bfloat16
|
53 |
)
|
54 |
```
|
55 |
+
Currently, we support LLM endpoint generation, where you need to send a post request to the generation endpoint (we recommend using Text Generation Inference by HuggingFace)
|
56 |
|
57 |
First, modify config.py and add your generation endpoint.
|
58 |
|
59 |
+
Then you can use it inside via GOAT-Storytelling-Agent:
|
60 |
|
61 |
```python
|
62 |
from goat_storytelling_agent.story_processor.prompt_manager import generate_story
|
|
|
65 |
```
|
66 |
## License
|
67 |
|
68 |
+
GOAT-70B-Storytelling model is based on [Meta's LLaMA-2-70b-hf](https://huggingface.co/meta-llama/Llama-2-70b-hf), and using own datasets.
|
69 |
|
70 |
+
GOAT-70B-Storytelling model weights are available under LLAMA-2 license. Note that the GOAT-70B-Storytelling model weights require access to the LLaMA-2 model weighs. The GOAT-70B-Storytelling model is based on LLaMA-2 and should be used according to the LLaMA-2 license.
|
71 |
|
72 |
### Risks and Biases
|
73 |
|
74 |
+
GOAT-70B-Storytelling model can produce factually incorrect output and should not be relied on to deliver factually accurate information. Therefore, the GOAT-70B-Storytelling model could possibly generate wrong, biased, or otherwise offensive outputs.
|