Upload folder using huggingface_hub

README.md

@@ -54,8 +54,7 @@ import json
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-# model_id = "yanolja/YanoljaNEXT-Rosetta-4B"
-model_id = "/data/nas-2/seungduk/eeve2/babel/datasets/gemma-3-4b-rosetta-revision4-stage2"
+model_id = "yanolja/YanoljaNEXT-Rosetta-4B"
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     dtype=torch.bfloat16,
@@ -154,10 +153,11 @@ The model was fine-tuned on multilingual translation data to optimize performanc
 
 ### Translation Quality Benchmarks
 
-The following CHrF++ scores demonstrate the model's competitive performance compared to other state-of-the-art translation models on English to Korean translation:
+The following CHrF++ scores (WMT24++) demonstrate the model's competitive performance compared to other state-of-the-art translation models on English to Korean translation:
 
-| Model                              | CHrF++ Score |
+| Model                              | CHrF++ Score (WMT24++) |
 |------------------------------------|--------------|
+| yanolja/YanoljaNEXT-Rosetta-12B    | 34.75 |
 | yanolja/YanoljaNEXT-Rosetta-20B    | 33.87        |
 | google/gemini-2.0-flash-001        | 33.81        |
 | openai/gpt-oss-120b                | 31.51        |