Commit ·
60ff639
1
Parent(s): 565db01
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,18 @@
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-4.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-4.0
|
| 3 |
+
datasets:
|
| 4 |
+
- tatsu-lab/alpaca
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
metrics:
|
| 8 |
+
- vicuna benchmark
|
| 9 |
+
- wikitext2
|
| 10 |
+
pipeline_tag: question-answering
|
| 11 |
---
|
| 12 |
+
# Eluwa: A Conversational LoRA for Facebook's OPT 2.7b Architecture
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
Eluwa is a fine-tuned LoRA model based on Facebook's OPT 2.7b architecture and trained on the Stanford Alpaca dataset. Eluwa is designed to provide a more conversational and creative experience in question-answering mode compared to the default OPT model. The idea was that OPT was too curt (and frankly, a bit of an asshole) for a model of its size, and that we could finetune it like Alpaca did to Llama.
|
| 17 |
+
|
| 18 |
+
It worked! Based on very limited testing, it's about halfway to GPT 3.5. Response times are fast: on my GTX 1080ti + Ryzen 3600,it generates between 1.14 tokens/s and 3.77 tokens/s.
|