Hugging Face's logo

daekeun-ml
/
Llama-2-ko-DPO-13B

Text Generation
Transformers
Safetensors
Korean
llama
llama-2
dpo
text-generation-inference
Model card Files Community
daekeun-ml commited on
Commit
5b94b67
·
1 Parent(s): 39a9873

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -28,8 +28,8 @@ I think the potential of the base LLM model is enormous, seeing how much halluci
28
 
29
  | Model | Average |Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
30
  | --- | --- | --- | --- | --- | --- | --- |
31
- | **daekeun/Llama-2-ko-DPO-13B (Ours)** | **51.03** | 47.53 | 58.28 | 43.59 | 51.91 | 53.84 |
32
- | [daekeun/Llama-2-ko-instruct-13B](https://huggingface.co/daekeun-ml/Llama-2-ko-instruct-13B) | 49.52 | 46.5 | 56.9 | 43.76 | 42 | 58.44 |
33
  | [kyujinpy/Korean-OpenOrca-13B](https://huggingface.co/kyujinpy/KO-Platypus2-13B) | 48.79 | 43.09 | 54.13 | 40.24 | 45.22 | 61.28 |
34
 
35
 
 
28
 
29
  | Model | Average |Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
30
  | --- | --- | --- | --- | --- | --- | --- |
31
+ | **daekeun-ml/Llama-2-ko-DPO-13B (Ours)** | **51.03** | 47.53 | 58.28 | 43.59 | 51.91 | 53.84 |
32
+ | [daekeun-ml/Llama-2-ko-instruct-13B](https://huggingface.co/daekeun-ml/Llama-2-ko-instruct-13B) | 49.52 | 46.5 | 56.9 | 43.76 | 42 | 58.44 |
33
  | [kyujinpy/Korean-OpenOrca-13B](https://huggingface.co/kyujinpy/KO-Platypus2-13B) | 48.79 | 43.09 | 54.13 | 40.24 | 45.22 | 61.28 |
34
 
35