magicoder / README.md
justinxzhao's picture
Update README.md (#1)
58d0eed verified
metadata
library_name: peft
base_model: mistralai/Mistral-7B-v0.1
pipeline_tag: text-generation

Description: Coding tasks in multiple languages
Original dataset: https://huggingface.co/datasets/ise-uiuc/Magicoder-OSS-Instruct-75K
---
Try querying this adapter for free in Lora Land at https://predibase.com/lora-land!
The adapter_category is STEM and the name is Code Generation (magicoder)
---
Sample input: Below is a programming problem, paired with a language in which the solution should be written. Write a solution in the provided that appropriately solves the programming problem.\n\n### Problem:

def strlen(string: str) -> int: """ Return length of given string >>> strlen('') 0 >>> strlen('abc') 3 """ \n\n### Language: python\n\n### Solution:
---
Sample output: python def strlen(string: str) -> int: return len(string)
---
Try using this adapter yourself!

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "mistralai/Mistral-7B-v0.1"
peft_model_id = "predibase/magicoder"

model = AutoModelForCausalLM.from_pretrained(model_id)
model.load_adapter(peft_model_id)