Hugging Face's logo

MonteXiaofeng
/
Tranport-llama3_1_8B_instruct

Safetensors
llama
交通运输
语言模型
chatmodel
Model card Files Community
MonteXiaofeng commited on
Commit
3169f32
·
verified ·
1 Parent(s): 609acac

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -27,4 +27,5 @@ select best ckpt by the evaluation loss
27
  Since I only found an instruction dataset [DUOMO-Lab/Transgpt_sft_v2](https://huggingface.co/datasets/DUOMO-Lab/Transgpt_sft_v2) in the field of traffic, in order to remove the influence of the base model, I used the data in llama3.1-8b-instruc for fine-tuning and compared and evaluated our model.
28
  The evaluation method is: use GPT4 on the validation set of each dataset to compare good, tie, and loss. The evaluation results are as follows
29
 
30
- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/642f6c64f945a8a5c9ee5b5d/MoX6n0dVfXx80FsR5-va-.png)
 
 
27
  Since I only found an instruction dataset [DUOMO-Lab/Transgpt_sft_v2](https://huggingface.co/datasets/DUOMO-Lab/Transgpt_sft_v2) in the field of traffic, in order to remove the influence of the base model, I used the data in llama3.1-8b-instruc for fine-tuning and compared and evaluated our model.
28
  The evaluation method is: use GPT4 on the validation set of each dataset to compare good, tie, and loss. The evaluation results are as follows
29
 
30
+
31
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/642f6c64f945a8a5c9ee5b5d/hvLm7eK0YImjWYbQE4ZCd.png)