passing2961
commited on
Commit
β’
d37f41d
1
Parent(s):
fcf82f5
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,45 @@
|
|
1 |
-
---
|
2 |
-
license: cc-by-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-3.0
|
3 |
+
datasets:
|
4 |
+
- passing2961/multifaceted-skill-of-mind
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
base_model:
|
8 |
+
- meta-llama/Llama-3.2-1B-Instruct
|
9 |
+
tags:
|
10 |
+
- conversational ai
|
11 |
+
- conversational skill
|
12 |
+
---
|
13 |
+
|
14 |
+
# Thanos-1B Model Card
|
15 |
+
|
16 |
+
[π§ Multifaceted Skill-of-Mind](https://huggingface.co/datasets/passing2961/multifaceted-skill-of-mind) | [π€ Thanos-3B](https://huggingface.co/passing2961/Thanos-3B) | [π€ Thanos-8B](https://huggingface.co/passing2961/Thanos-8B) | [π» Github](https://github.com/passing2961/Thanos) | [π Arxiv]() | [π PDF]()
|
17 |
+
|
18 |
+
|
19 |
+
## Model Description
|
20 |
+
- **Repository:** [Code](https://github.com/passing2961/Thanos)
|
21 |
+
- **Paper:** Thanos: Enhancing Conversational Agents with Skill-of-Mind-Infused Large Language Model
|
22 |
+
- **Point of Contact:** [Young-Jun Lee](mailto:[email protected])
|
23 |
+
|
24 |
+
## Model Details
|
25 |
+
- **Model**: Thanos-series is a fully open-source skill-of-mind-infused LLM to help the general LLM-based conversational agent to respond human-like way.
|
26 |
+
- **Date**: Thanos-series was trained in 2024.
|
27 |
+
- **Training Dataset**: [100K Multifaceted Skill-of-Mind](https://huggingface.co/datasets/passing2961/multifaceted-skill-of-mind)
|
28 |
+
- **Architecture**: Thanos-1B was trained on top of [LLaMA-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct).
|
29 |
+
|
30 |
+
## How to Use
|
31 |
+
|
32 |
+
## License and Recommendations
|
33 |
+
|
34 |
+
The Thanos-1B is intended to be used for research purposes only.
|
35 |
+
|
36 |
+
## Acknowledgement
|
37 |
+
|
38 |
+
This work was supported by a grant of the KAIST-KT joint research project through AI Tech Lab, Institute of convergence Technology, funded by KT [Project No. G01230605, Development of Task-oriented Persona-based Dialogue Generation Combining Multi-modal Interaction and Knowledge Modeling].
|
39 |
+
|
40 |
+
## Citation
|
41 |
+
|
42 |
+
If you find the resources in this repository useful, please cite our work:
|
43 |
+
|
44 |
+
```
|
45 |
+
TBD
|