Chen Zheng commited on
Commit ·
2ecd103
1
Parent(s): f349811
write readme
Browse files
README.md
CHANGED
|
@@ -1,3 +1,21 @@
|
|
| 1 |
-
-
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# ICE-GRT Model Card
|
| 2 |
+
|
| 3 |
+
## Model Details
|
| 4 |
+
|
| 5 |
+
ICE-GRT is a chat assistant trained by Reinforcement Learning from Human Feedback (RLHF) by Vicuna model.
|
| 6 |
+
|
| 7 |
+
- Model type: An auto-regressive language model based on the transformer architecture
|
| 8 |
+
- License: The same as lmsys/vicuna-13b-v1.5
|
| 9 |
+
- Finetuned from model: lmsys/vicuna-13b-v1.5
|
| 10 |
+
|
| 11 |
+
## Model Sources
|
| 12 |
+
|
| 13 |
+
Paper 1 (SFT): https://arxiv.org/abs/2310.04945
|
| 14 |
+
|
| 15 |
+
Paper 2 (RLHF): Publish soon!
|
| 16 |
+
|
| 17 |
+
## Uses
|
| 18 |
+
|
| 19 |
+
The primary use of Vicuna is research on large language models and chatbots. The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
|
| 20 |
+
|
| 21 |
+
|