Update README.md

README.md

@@ -7,22 +7,10 @@ base_model:
 datasets:
 - ChatTSRepo/ChatTS-Training-Dataset
 language:
-- zho
 - eng
-- fra
-- spa
-- por
-- deu
-- ita
-- rus
-- jpn
-- kor
-- vie
-- tha
-- ara
 ---
 
-# [VLDB' 25] ChatTS-14B Model
+# [VLDB' 25] ChatTS-14B-0801 Model
 
 <div style="display:flex;justify-content: center">
 <a href="https://github.com/NetmanAIOps/ChatTS"><img alt="github" src="https://img.shields.io/badge/Code-GitHub-blue"></a>
@@ -35,7 +23,7 @@ language:
 This repo provides code, datasets and model for `ChatTS`: [ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoning](https://arxiv.org/pdf/2412.03104).
 
 ## Web Demo
-The Web Demo of ChatTS-14B is available at HuggingFace Spaces: [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20ChatTS-Web%20Demo-blue)](https://huggingface.co/spaces/xiezhe22/ChatTS)
+The Web Demo of ChatTS-14B-0801 is available at HuggingFace Spaces: [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20ChatTS-Web%20Demo-blue)](https://huggingface.co/spaces/xiezhe22/ChatTS)
 
 ## Key Features
 ChatTS is a Multimodal LLM built natively for time series as a core modality：
@@ -85,6 +73,9 @@ outputs = model.generate(**inputs, max_new_tokens=300)
 print(tokenizer.decode(outputs[0][len(inputs['input_ids'][0]):], skip_special_tokens=True))
 ```
 
+## Reproduction of Paper Results
+Please download the [legacy ChatTS-14B model](https://huggingface.co/bytedance-research/ChatTS-14B/tree/fea24f221dd13ad310b68cc5470f575647b838c6) to reproduce the results in the paper.
+
 ## Reference
 - QWen2.5-14B-Instruct (https://huggingface.co/Qwen/Qwen2.5-14B-Instruct)
 - transformers (https://github.com/huggingface/transformers.git)