|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- In2Training/VaLProbing-32K |
|
language: |
|
- en |
|
--- |
|
|
|
# FILM-7B |
|
|
|
<p align="center"> |
|
💻 <a href="https://github.com/microsoft/FILM/" target="_blank">[Github Repo]</a> • 📃 <a href="https://arxiv.org/abs/xxx" target="_blank">[LongAlign Paper]</a> • 🤗 <a href="https://huggingface.co/datasets/In2Training/VaLProbing-32K" target="_blank">[VaL Probing] </a> |
|
</p> |
|
|
|
**FILM-7B** is a 32K-context LLM that overcomes the lost-in-the-middle problem on [VaLProbing-32K](https://huggingface.co/datasets/In2Training/VaLProbing-32K/). |
|
It is trained from Mistral-7B-Instruct-v0.2 by applying Information-Intensie (In2) Training. |
|
FILM-7B achieves SOTA-level performance on real-world long-context tasks among ~7B size LLMs and does not compromise the short-context performance. |
|
|
|
## Model Usage |
|
|
|
The system tempelate for FILM-7B: |
|
```text |
|
[INST] Below is a context and an instruction. Based on the information provided in the context, write a response for the instruction. |
|
|
|
### Context: |
|
{YOUR LONG CONTEXT} |
|
|
|
### Instruction: |
|
{YOUR QUESTION & INSTRUCTION} [/INST] |
|
``` |
|
|
|
## Probing Results |
|
|
|
|
|
|
|
|
|
|
|
|
