metadata

license: llama2
datasets:
  - wyt2000/InverseCoder-CL-7B-Evol-Instruct-90K
  - ise-uiuc/Magicoder-Evol-Instruct-110K
library_name: transformers
pipeline_tag: text-generation
tags:
  - code
model-index:
  - name: InverseCoder-CL-7B
    results:
      - task:
          type: text-generation
        dataset:
          type: openai_humaneval
          name: HumanEval
        metrics:
          - name: pass@1
            type: pass@1
            value: 0.762
            verified: false
      - task:
          type: text-generation
        dataset:
          type: openai_humaneval
          name: HumanEval(+)
        metrics:
          - name: pass@1
            type: pass@1
            value: 0.72
            verified: false
      - task:
          type: text-generation
        dataset:
          type: mbpp
          name: MBPP
        metrics:
          - name: pass@1
            type: pass@1
            value: 0.706
            verified: false
      - task:
          type: text-generation
        dataset:
          type: mbpp
          name: MBPP(+)
        metrics:
          - name: pass@1
            type: pass@1
            value: 0.601
            verified: false
      - task:
          type: text-generation
        dataset:
          type: ds1000
          name: DS-1000 (Overall Completion)
        metrics:
          - name: pass@1
            type: pass@1
            value: 0.399
            verified: false
      - task:
          type: text-generation
        dataset:
          type: nuprl/MultiPL-E
          name: MultiPL-HumanEval (Java)
        metrics:
          - name: pass@1
            type: pass@1
            value: 0.487
            verified: false
      - task:
          type: text-generation
        dataset:
          type: nuprl/MultiPL-E
          name: MultiPL-HumanEval (JavaScript)
        metrics:
          - name: pass@1
            type: pass@1
            value: 0.619
            verified: false
      - task:
          type: text-generation
        dataset:
          type: nuprl/MultiPL-E
          name: MultiPL-HumanEval (C++)
        metrics:
          - name: pass@1
            type: pass@1
            value: 0.526
            verified: false
      - task:
          type: text-generation
        dataset:
          type: nuprl/MultiPL-E
          name: MultiPL-HumanEval (PHP)
        metrics:
          - name: pass@1
            type: pass@1
            value: 0.552
            verified: false
      - task:
          type: text-generation
        dataset:
          type: nuprl/MultiPL-E
          name: MultiPL-HumanEval (Swift)
        metrics:
          - name: pass@1
            type: pass@1
            value: 0.53
            verified: false
      - task:
          type: text-generation
        dataset:
          type: nuprl/MultiPL-E
          name: MultiPL-HumanEval (Rust)
        metrics:
          - name: pass@1
            type: pass@1
            value: 0.461
            verified: false
      - task:
          type: text-generation
        dataset:
          type: nuprl/MultiPL-E
          name: MultiPL-HumanEval (Average for non-python languages)
        metrics:
          - name: pass@1
            type: pass@1
            value: 0.529
            verified: false

InverseCoder: Unleashing the Power of Instruction-Tuned Code LLMs with Inverse-Instruct

InverseCoder is a series of code LLMs instruction-tuned by generating data from itself through Inverse-Instruct.

Models and Datasets

	Base Model	InverseCoder	Dataset
6.7B	deepseek-ai/deepseek-coder-6.7b-base	wyt2000/InverseCoder-DS-6.7B	wyt2000/InverseCoder-DS-6.7B-Evol-Instruct-90K
7B	codellama/CodeLlama-7b-Python-hf	wyt2000/InverseCoder-CL-7B <= You are here	wyt2000/InverseCoder-CL-7B-Evol-Instruct-90K
13B	codellama/CodeLlama-13b-Python-hf	wyt2000/InverseCoder-CL-13B	wyt2000/InverseCoder-CL-13B-Evol-Instruct-90K

Usage

Similar to Magicoder-S-DS-6.7B, use the code below to get started with the model. Make sure you installed the transformers library.

from transformers import pipeline
import torch
INVERSECODER_PROMPT = """You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions.
@@ Instruction
{instruction}
@@ Response
"""
instruction = <Your code instruction here>
prompt = INVERSECODER_PROMPT.format(instruction=instruction)
generator = pipeline(
    model="wyt2000/InverseCoder-CL-7B",
    task="text-generation",
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
result = generator(prompt, max_length=1024, num_return_sequences=1, temperature=0.0)
print(result[0]["generated_text"])

Paper

Arxiv: https://arxiv.org/abs/2407.05700

Please cite the paper if you use the models or datasets from InverseCoder.

@misc{wu2024inversecoderunleashingpowerinstructiontuned,
      title={InverseCoder: Unleashing the Power of Instruction-Tuned Code LLMs with Inverse-Instruct}, 
      author={Yutong Wu and Di Huang and Wenxuan Shi and Wei Wang and Lingzhe Gao and Shihao Liu and Ziyuan Nan and Kaizhao Yuan and Rui Zhang and Xishan Zhang and Zidong Du and Qi Guo and Yewen Pu and Dawei Yin and Xing Hu and Yunji Chen},
      year={2024},
      eprint={2407.05700},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2407.05700}, 
}

Code

Official code repo for Inverse-Instruct (under development).

Acknowledgements

Magicoder: Training code, original datasets and data decontamination
DeepSeek-Coder: Base model for InverseCoder-DS
CodeLlama: Base model for InverseCoder-CL
AutoMathText: Self-evaluation and data selection method