Mistral_7b_fine_tune

Model Details

Model Description

• Developed by: Zidan Alfarizi
• Model type: large language model for code generation
• Language(s) (NLP): English
• Finetuned from model: lMistral 7b

Model Sources

• Repository: https://github.com/unslothai/unsloth
• Developed by: unsloth

Model parameter

• r = 16,
• target_modules = ["q_proj", "k_proj", "v_proj", "o_proj","gate_proj", "up_proj", "down_proj",],
• lora_alpha = 16,
• lora_dropout = 0,
• bias = "none",
• use_gradient_checkpointing = "unsloth",
• random_state = 3407,
• use_rslora = False,
• loftq_config = None,

Usage and limitations

This model is used to generate code based on commands given by the user. it should be noted that this model can generate many languages because it takes the initial model from llama2. However, after finetuning it is better at generating python code, because currently it is only trained with python code datasets.

How to Get Started with the Model

use link below to use model //

Training Data

https://huggingface.co/datasets/mlabonne/Evol-Instruct-Python-26k

Training Hyperparameters

• Warmup_step: 5
• lr_scheduler_type: linear
• Learning Rate: 0.0002
• Batch Size: 2
• Weigh_decay: 0.001
• Epoch: 30
• Optimizer: adamw_8bit

Testing Data

https://huggingface.co/datasets/google-research-datasets/mbpp/viewer/full

Testing Document

https://docs.google.com/spreadsheets/d/1hr8R4nixQsDC5cGGENTOLUW1jPCS_lltVRIeOzenBvA/edit?usp=sharing

Results

Berfore finetune

• Accurary : 56%
• Consistensy : 0.4%

After fine tune

• Accuracy : 59%
• Consistency : 100%