You can deploy this model and start earning money today!

suka-nlp/
Gemma_finetune

Name: Gemma_finetune
Availability: InStock

adapter-transformers

code

mlabonne/Evol-Instruct-Python-26k

Views

No views yet

Model Details

Model Description

Developed by: Maulida Suryaning Aisha
Model type: large language model for code generation
Language(s) (NLP): English
Finetuned from model: Gemma

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: 8
Activation Function: SiLU (Sigmoid Linear Unit), GeLU (Gaussian Error Linear Unit), Exact GeLU, Approximate GeLU
Weigh_decay: 0.001
Epoch: 60
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 : 17%
Consistensy : 0%

After fine tune

Accuracy : 67%
Consistency : 100%

suka-nlp/Gemma_finetune