Text Generation
PEFT
Safetensors
English
llama
llama-3
lora
qlora
adapters
question-answering
document-qa
scientific-text
dissertation
phd-abstract
conversational
Instructions to use nvikou/llama3-phd-abstract-qa-en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use nvikou/llama3-phd-abstract-qa-en with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3-8b-Instruct-bnb-4bit") model = PeftModel.from_pretrained(base_model, "nvikou/llama3-phd-abstract-qa-en") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -136,10 +136,7 @@ print(answer)
|
|
| 136 |
|
| 137 |
- Supervised instruction-tuning pairs derived from a **PhD abstract** (English branch).
|
| 138 |
- Training set size: **219** question–answer pairs.
|
| 139 |
-
|
| 140 |
-
|
| 141 |
-
The raw QA dataset is **not** published with this repository.
|
| 142 |
-
|
| 143 |
---
|
| 144 |
|
| 145 |
## Citation
|
|
|
|
| 136 |
|
| 137 |
- Supervised instruction-tuning pairs derived from a **PhD abstract** (English branch).
|
| 138 |
- Training set size: **219** question–answer pairs.
|
| 139 |
+
|
|
|
|
|
|
|
|
|
|
| 140 |
---
|
| 141 |
|
| 142 |
## Citation
|