ShengnanAn commited on
Commit
c2889d8
β€’
1 Parent(s): 4750622

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -12,7 +12,7 @@ language:
12
  πŸ’» <a href="https://github.com/microsoft/FILM/" target="_blank">[Github Repo]</a> β€’ πŸ“ƒ <a href="https://arxiv.org/abs/xxx" target="_blank">[Paper]</a> β€’ πŸ€— <a href="https://huggingface.co/datasets/In2Training/VaLProbing-32K" target="_blank">[VaLProbing-32K] </a>
13
  </p>
14
 
15
- **FILM-7B** is a 32K-context LLM that overcomes the lost-in-the-middle problem.
16
  It is trained from Mistral-7B-Instruct-v0.2 by applying Information-Intensie (In2) Training.
17
  FILM-7B achieves near-perfect performance on probing tasks, SOTA-level performance on real-world long-context tasks among ~7B size LLMs, and does not compromise the short-context performance.
18
 
 
12
  πŸ’» <a href="https://github.com/microsoft/FILM/" target="_blank">[Github Repo]</a> β€’ πŸ“ƒ <a href="https://arxiv.org/abs/xxx" target="_blank">[Paper]</a> β€’ πŸ€— <a href="https://huggingface.co/datasets/In2Training/VaLProbing-32K" target="_blank">[VaLProbing-32K] </a>
13
  </p>
14
 
15
+ **FILM-7B is a 32K-context LLM that overcomes the lost-in-the-middle problem.**
16
  It is trained from Mistral-7B-Instruct-v0.2 by applying Information-Intensie (In2) Training.
17
  FILM-7B achieves near-perfect performance on probing tasks, SOTA-level performance on real-world long-context tasks among ~7B size LLMs, and does not compromise the short-context performance.
18