tingyuansen commited on
Commit
47adcb8
·
verified ·
1 Parent(s): 7f89965

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -38,7 +38,7 @@ AstroLLaMA-3-8B-Chat_Summary is a specialized chat model for astronomy, develope
38
  - Warmup ratio: 0.03
39
  - Cosine decay schedule for learning rate reduction
40
  - **Primary Use**: Instruction-following and chat-based interactions for astronomy-related queries
41
- - **Reference**: Pan et al. 2024 [Link to be added]
42
 
43
  ## Using the model for chat
44
 
@@ -85,7 +85,7 @@ print(f"Assistant: {response}")
85
 
86
  This model used the summarized content for training, which has led to improved performance compared to the AIC (Abstract, Introduction, Conclusion) version. The summarization process allows for the inclusion of more comprehensive information from each paper while maintaining a manageable token count.
87
 
88
- Here's a performance comparison chart based upon the astronomical benchmarking Q&A as described in [Ting et al. 2024](https://arxiv.org/abs/2407.11194), and Pan et al. 2024:
89
 
90
  | Model | Score (%) |
91
  |-------|-----------|
 
38
  - Warmup ratio: 0.03
39
  - Cosine decay schedule for learning rate reduction
40
  - **Primary Use**: Instruction-following and chat-based interactions for astronomy-related queries
41
+ - **Reference**: [Pan et al. 2024](https://arxiv.org/abs/2409.19750)
42
 
43
  ## Using the model for chat
44
 
 
85
 
86
  This model used the summarized content for training, which has led to improved performance compared to the AIC (Abstract, Introduction, Conclusion) version. The summarization process allows for the inclusion of more comprehensive information from each paper while maintaining a manageable token count.
87
 
88
+ Here's a performance comparison chart based upon the astronomical benchmarking Q&A as described in [Ting et al. 2024](https://arxiv.org/abs/2407.11194):
89
 
90
  | Model | Score (%) |
91
  |-------|-----------|