uukuguy's picture
Update README.md
87a4d21 verified
metadata
language:
  - en
library_name: transformers
pipeline_tag: text-generation
datasets:
  - jondurbin/airoboros-2.2
  - Open-Orca/OpenOrca
  - garage-bAInd/Open-Platypus
  - WizardLM/WizardLM_evol_instruct_V2_196k
  - TokenBender/python_eval_instruct_51k
tags:
  - code
license: apache-2.0
model-index:
  - name: SpeechlessCoder
    results:
      - task:
          type: text-generation
        dataset:
          type: openai_humaneval
          name: HumanEval
        metrics:
          - name: pass@1
            type: pass@1
            value: null
            verified: false

speechless-instruct-mistral-7b-v0.2

Code: https://github.com/uukuguy/speechless

Use the following dataset to fine-tune mistralai/Mistral-7B-v0.2 in order to improve the model's reasoning and planning abilities.

Total 201,981 samples.

  • jondurbin/airoboros-2.2: Filter categories related to coding, reasoning and planning. 23,462 samples.
  • Open-Orca/OpenOrca: Filter the 'cot' category in 1M GPT4 dataset. 74,440 samples.
  • garage-bAInd/Open-Platypus: 100%, 24,926 samples.
  • WizardLM/WizardLM_evol_instruct_V2_196k: Coding coversation part. 30,185 samples
  • TokenBender/python_eval_instruct_51k: “python” in output .40,309 samples
  • Spider: 8,659 samples

How to Prompt the Model

This model accepts the Alpaca instruction format.

For example:

You are an intelligent programming assistant.

### Instruction:
Implement a linked list in C++

### Response:

HumanEval

Metric Value
humaneval-python

Big Code Models Leaderboard](https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard)

CodeLlama-34B-Python: 53.29

CodeLlama-34B-Instruct: 50.79

CodeLlama-13B-Instruct: 50.6

CodeLlama-34B: 45.11

CodeLlama-13B-Python: 42.89

CodeLlama-13B: 35.07

Open LLM Leaderboard

Metric Value
ARC 58.79
HellaSwag 81.89
MMLU 61.27
TruthfulQA 49.85
Winoground 78.22
GSM8K 56.33
Average 64.39