Commit
•
b18ed0e
1
Parent(s):
7d08956
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,30 @@
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-sa-4.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-sa-4.0
|
| 3 |
+
datasets:
|
| 4 |
+
- Dahoas/rm-static
|
| 5 |
+
- Dahoas/synthetic-instruct-gptj-pairwise
|
| 6 |
+
- Anthropic/hh-rlhf
|
| 7 |
+
language:
|
| 8 |
+
- en
|
| 9 |
---
|
| 10 |
+
|
| 11 |
+
# Model Card for Model ID
|
| 12 |
+
|
| 13 |
+
This a model is a fine-tuned with SFT using DeepSpeed Chat.
|
| 14 |
+
It is based on OPT-1.3M.B
|
| 15 |
+
|
| 16 |
+
## Model Details
|
| 17 |
+
|
| 18 |
+
### Model Description
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [The Kaitchup](https://kaitchup.substack.com/)
|
| 21 |
+
- **Model type:** Causal
|
| 22 |
+
- **Language(s) (NLP):** English
|
| 23 |
+
- **License:** cc-by-nc-sa-4.0
|
| 24 |
+
- **Finetuned from model:** [facebook/opt-1.3b](https://huggingface.co/facebook/opt-1.3b)
|
| 25 |
+
|
| 26 |
+
### Model Sources
|
| 27 |
+
|
| 28 |
+
The model has been trained with the procedure described in this article:
|
| 29 |
+
|
| 30 |
+
[Train Instruct LLMs On Your GPU with DeepSpeed Chat — Step #1: Supervised Fine-tuning](https://kaitchup.substack.com/p/train-instruct-llms-on-your-gpu-with)
|