Instructions to use heegyu/ko-prometheus-8b-lora-0708 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use heegyu/ko-prometheus-8b-lora-0708 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("MLP-KTLim/llama-3-Korean-Bllossom-8B") model = PeftModel.from_pretrained(base_model, "heegyu/ko-prometheus-8b-lora-0708") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -8,7 +8,7 @@ language:
|
|
| 8 |
- ko
|
| 9 |
---
|
| 10 |
|
| 11 |
-
# νκ΅μ΄ Prometheus λͺ¨λΈ (
|
| 12 |
|
| 13 |
LoRA νμ΅ν λ€, [LogicKor](https://github.com/instructkr/LogicKor)μ 곡κ°λ GPT-4μ judgementμ λΉκ΅ν΄λ³΄μμ΅λλ€.
|
| 14 |
μμ μ μλ ν둬ννΈλ‘ νκ° ν μκ΄κ³μλ₯Ό λΆμνμμΌλ (Spearman), μκ΄κ³μλ 0.3647λ‘ λμ§ μμμ΅λλ€.
|
|
|
|
| 8 |
- ko
|
| 9 |
---
|
| 10 |
|
| 11 |
+
# νκ΅μ΄ Prometheus λͺ¨λΈ (Test Model)
|
| 12 |
|
| 13 |
LoRA νμ΅ν λ€, [LogicKor](https://github.com/instructkr/LogicKor)μ 곡κ°λ GPT-4μ judgementμ λΉκ΅ν΄λ³΄μμ΅λλ€.
|
| 14 |
μμ μ μλ ν둬ννΈλ‘ νκ° ν μκ΄κ³μλ₯Ό λΆμνμμΌλ (Spearman), μκ΄κ³μλ 0.3647λ‘ λμ§ μμμ΅λλ€.
|