Adapter-Phi-3-mini-128k-instruct-lora-hrdx-gptq

swkong/Adapter-Phi-3-mini-128k-instruct-lora-hrdx-gptq

Adapter-Phi-3-mini-128k-instruct-lora-hrdx-gptq is a machine learning model from swkong. 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 mit.

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

Downloads · 30 days

1% of all-time downloads

All-time downloads

114

Public

Repo size

529 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors75.5 MB · 95%

At a glance

Library: peft
License: mit
Access: Public
Created: Nov 18, 2024
Updated: Nov 18, 2024
SHA: 0d2f15e3

Base models

microsoft/Phi-3-mini-128k-instruct

Model card

From the Hugging Face model README

Adapter-Phi-3-mini-128k-instruct-lora-hrdx-gptq

This model is a fine-tuned version of microsoft/Phi-3-mini-128k-instruct on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.1900

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: 0.0001
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.3444	30	2.3647
No log	2.6889	60	2.1900

Framework versions

PEFT 0.13.2
Transformers 4.46.2
Pytorch 2.4.0+cu121
Datasets 3.1.0
Tokenizers 0.20.3

Library: peft
License: mit
Created: Nov 18, 2024
Updated: Nov 18, 2024