|
--- |
|
language: |
|
- en |
|
library_name: transformers |
|
pipeline_tag: question-answering |
|
license: apache-2.0 |
|
datasets: |
|
- togethercomputer/RedPajama-Data-1T |
|
- allenai/qasper |
|
- DataHammer/paper_ground_dialog |
|
metrics: |
|
- bleu |
|
- rouge |
|
- f1 |
|
- bertscore |
|
--- |
|
|
|
## Model Details |
|
|
|
### Model Description |
|
|
|
<!-- Provide a longer summary of what this model is. --> |
|
Dense Passage Retrieval (DPR) is a set of tools and models for state-of-the-art open-domain Q&A research. scidpr-question-encoder is the Question Encoder trained using the Scientific Question Answer (QA) dataset (Pradeep et al., 2021). |
|
|
|
|
|
- **Developed by:** See [GitHub repo](https://github.com/gmftbyGMFTBY/science-llm) for model developers |
|
- **Model date:** LLaMA was trained In May. 2023. |
|
- **Model version:** This is version 1 of the model. |
|
- **Model type:** mozi_llama is an auto-regressive language model, based on the transformer architecture. The model comes in different sizes: 7B parameters. |
|
- **Language(s) (NLP):** [Apache 2.0](https://github.com/gmftbyGMFTBY/science-llm/blob/main/LICENSE) |
|
- **License:** English |
|
|
|
### Model Sources [optional] |
|
|
|
<!-- Provide the basic links for the model. --> |
|
|
|
- **Repository:** [Girhub Repo](https://github.com/gmftbyGMFTBY/science-llm) |
|
- **Paper [optional]:** [Paper Repo]() |
