Update README.md
Browse files
README.md
CHANGED
|
@@ -8,13 +8,20 @@ base_model:
|
|
| 8 |
- google/gemma-2-2b-it
|
| 9 |
pipeline_tag: question-answering
|
| 10 |
library_name: peft
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
# Game of Thrones Q&A Model (PEFT / QLoRA fine-tuned)
|
| 14 |
|
| 15 |
## 馃 Model Overview
|
| 16 |
|
| 17 |
-
**Model name:**
|
| 18 |
**Base model:** `google/gemma-2-2b-it`
|
| 19 |
**Fine-tuning method:** QLoRA (via PEFT)
|
| 20 |
**Task:** Contextual Question Answering on *Game of Thrones*
|
|
|
|
| 8 |
- google/gemma-2-2b-it
|
| 9 |
pipeline_tag: question-answering
|
| 10 |
library_name: peft
|
| 11 |
+
tags:
|
| 12 |
+
- got
|
| 13 |
+
- q&a
|
| 14 |
+
- RAG
|
| 15 |
+
- transformers
|
| 16 |
+
- peft
|
| 17 |
+
- bitsandbytes
|
| 18 |
---
|
| 19 |
|
| 20 |
# Game of Thrones Q&A Model (PEFT / QLoRA fine-tuned)
|
| 21 |
|
| 22 |
## 馃 Model Overview
|
| 23 |
|
| 24 |
+
**Model name:** hash-map/got_model
|
| 25 |
**Base model:** `google/gemma-2-2b-it`
|
| 26 |
**Fine-tuning method:** QLoRA (via PEFT)
|
| 27 |
**Task:** Contextual Question Answering on *Game of Thrones*
|