---
title: OPI-Llama-3.1-8B-Instruct
canonical_url: "https://www.modelscope.cn/models/BAAI/OPI-Llama-3.1-8B-Instruct"
md_url: "https://www.modelscope.cn/models/BAAI/OPI-Llama-3.1-8B-Instruct.md"
repository: BAAI/OPI-Llama-3.1-8B-Instruct
last_updated: 2025-03-12
license: llama3.1
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llama
architectures:
  - LlamaForCausalLM
base_model:
  - meta-llama/Meta-Llama-3.1-8B-Instruct
base_model_relation: finetune
parameters: 8.0B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 1845
stars: 1
tags:
  - "Life Science"
  - AI4Science
  - Biology
  - Protein
  - LLM
  - Instruction
---

# OPI-Llama-3.1-8B-Instruct

> OPI-Llama-3.1-8B-Instruct - BAAI 在 ModelScope 开源的模型。Github: https://github.com/baaihealth/opi Paper: OPI: An Open Instruction Dataset for Adapting Large Language Models to Protein-Related Tasks has been accepted by NeurIPS 2024 Workshop: Foundation Models…

BAAI/OPI-Llama-3.1-8B-Instruct 是 ModelScope 魔搭社区上的 8.0B 参数text-generation模型，采用 llama3.1 许可，基于 meta-llama/Meta-Llama-3.1-8B-Instruct 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: BAAI/OPI-Llama-3.1-8B-Instruct
- **License**: llama3.1
- **Tasks**: text-generation
- **Parameters**: 8.0B
- **Base model**: meta-llama/Meta-Llama-3.1-8B-Instruct
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: Life Science, AI4Science, Biology, Protein, LLM, Instruction
- **Downloads**: 1845
- **Stars**: 1
- **Last updated**: 2025-03-12

Source: https://www.modelscope.cn/models/BAAI/OPI-Llama-3.1-8B-Instruct

---

![OPI_logo](demo_figures/OPI_logo.png)

# Github: 
  https://github.com/baaihealth/opi
# Paper: 
  [OPI: An Open Instruction Dataset for Adapting Large Language Models to Protein-Related Tasks](https://neurips.cc/virtual/2024/105921) has been accepted by [NeurIPS 2024 Workshop: Foundation Models for Science: Progress, Opportunities, and Challenges](https://neurips.cc/virtual/2024/workshop/84714).

# Model Card of OPI-Llama-3.1-8B-Instruct
OPI-Llama-3.1-8B-Instruct was fine-tuned from the Meta-Llama-3.1-8B-Instruct model using the complete OPI training set (i.e.,[OPI_full_1.61M_train.json](https://huggingface.co/datasets/BAAI/OPI/blob/main/OPI_DATA/OPI_full_1.61M_train.json)).
For more details of training and testing, please visit [https://github.com/baaihealth/opi](https://github.com/baaihealth/opi).

![Overview](demo_figures/OPI_experiment_outline.png)

# Evaluation of OPI-Llama-3.1-8B-Instruct on 9 tasks 
Each testing result is derived from the Meta-Llama-3.1-8B-Instruct model that has been fine-tuned using [OPI_full_1.61M.json](https://huggingface.co/datasets/BAAI/OPI/blob/main/OPI_DATA/OPI_full_1.61M_train.json) and subsequently evaluated on the respective testing set for each specific task.

<table border="1" style="text-align:center; border-collapse:collapse; width: 100%;">
  <thead>
    <tr>
      <th style="text-align:center;">Task Type</th>
      <th style="text-align:center;">Task Name</th>
      <th style="text-align:center;">Testing file</th>
      <th style="text-align:center;">Accuracy</th>
      <th style="text-align:center;">Precision</th>
      <th style="text-align:center;">Recall</th>
      <th style="text-align:center;">F1</th>
      <th style="text-align:center;">Rouge-L</th>
    </tr>
  </thead>
  <tbody>
    <tr>
      <td rowspan="6">Sequence Understanding</td>
      <td rowspan="2">EC Number Prediction (split100)</td>
      <td>CLEAN_EC_number_new_test</td>
      <td>-</td>
      <td>0.3724</td>
      <td>0.3374</td>
      <td>0.3468</td>
      <td>-</td>
    </tr>
    <tr>
      <td>CLEAN_EC_number_price_test</td>
      <td>-</td>
      <td>0.0738</td>
      <td>0.0738</td>
      <td>0.0738</td>
      <td>-</td>
    </tr>
    <tr>
      <td rowspan="3">Fold Type Prediction</td>
      <td>fold_type_test_Fold_Holdout</td>
      <td>0.1045</td>
      <td>-</td>
      <td>-</td>
      <td>-</td>
      <td>-</td>
    </tr>
    <tr>
      <td>fold_type_test_Superfamily_Holdout</td>
      <td>0.1507</td>
      <td>-</td>
      <td>-</td>
      <td>-</td>
      <td>-</td>
    </tr>
    <tr>
      <td>fold_type_test_Family_Holdout</td>
      <td>0.6145</td>
      <td>-</td>
      <td>-</td>
      <td>-</td>
      <td>-</td>
    </tr>
    <tr>
      <td>Subcellular Localization Prediction</td>
      <td>subcell_loc_test</td>
      <td>0.4214</td>
      <td>-</td>
      <td>-</td>
      <td>-</td>
      <td>-</td>
    </tr>
    <tr>
      <td rowspan="9">Annotation Prediction</td>
      <td rowspan="3">Function Keywords Prediction</td>
      <td>CASPSimilarSeq_keywords_test</td>
      <td>-</td>
      <td>0.4202</td>
      <td>0.5057</td>
      <td>0.4385</td>
      <td>-</td>
    </tr>
    <tr>
      <td>IDFilterSeq_keywords_test</td>
      <td>-</td>
      <td>0.6762</td>
      <td>0.6905</td>
      <td>0.6650</td>
      <td>-</td>
    </tr>
    <tr>
      <td>UniProtSeq_keywords_test</td>
      <td>-</td>
      <td>0.7606</td>
      <td>0.7489</td>
      <td>0.7374</td>
      <td>-</td>
    </tr>
    <tr>
      <td rowspan="3">Gene Ontology(GO) Terms Prediction</td>
      <td>CASPSimilarSeq_go_terms_test</td>
      <td>-</td>
      <td>0.1113</td>
      <td>0.0936</td>
      <td>0.099</td>
      <td>-</td>
    </tr>
    <tr>
      <td>IDFilterSeq_go_terms_test</td>
      <td>-</td>
      <td>0.6686</td>
      <td>0.6287</td>
      <td>0.6304</td>
      <td>-</td>
    </tr>
    <tr>
      <td>UniProtSeq_go_terms_test</td>
      <td>-</td>
      <td>0.7150</td>
      <td>0.6897</td>
      <td>0.6849</td>
      <td>-</td>
    </tr>
    <tr>
      <td rowspan="3">Function Description Prediction</td>
      <td>CASPSimilarSeq_function_test</td>
      <td>-</td>
      <td>-</td>
      <td>-</td>
      <td>-</td>
      <td>0.7524</td>
    </tr>
    <tr>
      <td>IDFilterSeq_function_test</td>
      <td>-</td>
      <td>-</td>
      <td>-</td>
      <td>-</td>
      <td>0.4786</td>
    </tr>
    <tr>
      <td>UniProtSeq_function_test</td>
      <td>-</td>
      <td>-</td>
      <td>-</td>
      <td>-</td>
      <td>0.5144</td>
    </tr>
    <tr>
      <td rowspan="3">Knowledge Mining</td>
      <td>Tissue Location Prediction from Gene Symbol</td>
      <td>gene_symbol_to_tissue_test</td>
      <td>-</td>
      <td>0.4002</td>
      <td>0.9356</td>
      <td>0.5466</td>
      <td>-</td>
    </tr>
    <tr>
      <td>Cancer Prediction from Gene Symbol</td>
      <td>gene_symbol_to_cancer_test</td>
      <td>-</td>
      <td>0.2890</td>
      <td>0.2701</td>
      <td>0.2664</td>
      <td>-</td>
    </tr>
    <tr>
      <td>Cancer Prediction from Gene Name</td>
      <td>gene_name_to_cancer_test</td>
      <td>-</td>
      <td>0.2786</td>
      <td>0.2707</td>
      <td>0.2659</td>
      <td>-</td>
    </tr>
  </tbody>
</table>

# Prediction comparison with SOTA mdoels

![model_compare](model_compare/task1_EC_number.png)
![model_compare](model_compare/task2_fold_type.png)
![model_compare](model_compare/task3_subcell_loc.png)
![model_compare](model_compare/task4_keywords.png)
![model_compare](model_compare/task5_GO.png)
![model_compare](model_compare/task6_function.png)
![model_compare](model_compare/task7_gsymbol2tissue.png)
![model_compare](model_compare/task8_gsymbol2cancer.png)
![model_compare](model_compare/task9_gname2cancer.png)