CodeLlama-7B-Instruct-AWQ-FaVe-rank64-2epochs-v2

Ferdi/CodeLlama-7B-Instruct-AWQ-FaVe-rank64-2epochs-v2

CodeLlama-7B-Instruct-AWQ-FaVe-rank64-2epochs-v2 is a machine learning model from Ferdi. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as llama2.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

29% of all-time downloads

All-time downloads

Public

Repo size

134 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors134 MB · 99%

At a glance

Library: peft
License: llama2
Access: Public
Created: Jun 26, 2024
Updated: Jun 26, 2024
SHA: ae5ade63

Base models

TheBloke/CodeLlama-7B-Instruct-AWQ

Model card

From the Hugging Face model README

CodeLlama-7B-Instruct-AWQ-FaVe-rank64-2epochs-v2

This model is a fine-tuned version of TheBloke/CodeLlama-7B-Instruct-AWQ on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3887

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0005
train_batch_size: 1
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 10
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.2685	10	1.0714
1.4428	0.5369	20	0.6101
1.4428	0.8054	30	0.5003
0.4924	1.0738	40	0.4773
0.4924	1.3423	50	0.4364
0.3846	1.6107	60	0.4030
0.3846	1.8792	70	0.3887

Framework versions

PEFT 0.10.0
Transformers 4.40.2
Pytorch 2.2.1+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Library: peft
License: llama2
Created: Jun 26, 2024
Updated: Jun 26, 2024