Update README.md

README.md

@@ -202,7 +202,7 @@ The evaluation code for this can be found [here](https://drive.google.com/file/d
 
 ```yaml
 ### model
-model_name_or_path: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+model_name_or_path: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
 
 ### method
 stage: sft
@@ -219,7 +219,7 @@ preprocessing_num_workers: 16
 packing: true
 
 ### output
-output_dir: /root/train_outputs/DeepSeek-R1-Distill-Qwen-7B/reasoning-multilingual-R1-Llama-70B-train
+output_dir: /root/train_outputs/DeepSeek-R1-Distill-Qwen-1.5B/reasoning-multilingual-R1-Llama-70B-train
 logging_steps: 1
 save_steps: 0.99999
 plot_loss: true
@@ -250,11 +250,10 @@ echo '{
   }
 }' > /root/LLaMA-Factory/data/dataset_info.json
 
-# 7B Qwen
-cd /root/LLaMA-Factory && llamafactory-cli train /root/reasoning_multilingual_train_7B.yaml
-rm -r /root/train_outputs/DeepSeek-R1-Distill-Qwen-7B/reasoning-multilingual-R1-Llama-70B-train/checkpoint*
-huggingface-cli upload lightblue/DeepSeek-R1-Distill-Qwen-7B-Multilingual /root/train_outputs/DeepSeek-R1-Distill-Qwen-7B/reasoning-multilingual-R1-Llama-70B-train
-
+# # 1.5B Llama
+cd /root/LLaMA-Factory && llamafactory-cli train /root/reasoning_multilingual_train_1.5B.yaml
+rm -r /root/train_outputs/DeepSeek-R1-Distill-Qwen-1.5B/reasoning-multilingual-R1-Llama-70B-train/checkpoint*
+huggingface-cli upload lightblue/DeepSeek-R1-Distill-Qwen-1.5B-Multilingual /root/train_outputs/DeepSeek-R1-Distill-Qwen-1.5B/reasoning-multilingual-R1-Llama-70B-train
 ```
 
 # License