Mistral-7B-Instruct-v0.3-qlora-modular

TripleH/Mistral-7B-Instruct-v0.3-qlora-modular

Mistral-7B-Instruct-v0.3-qlora-modular is a text generation model from TripleH. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.

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

Downloads · 30 days

22% of all-time downloads

All-time downloads

Public

Repo size

672 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors168 MB · 97%

At a glance

Task: Text Generation
Library: peft
License: apache-2.0
Access: Public
Created: Jul 7, 2025
Updated: Jul 7, 2025
SHA: de7b9cc6

Try a prompt

Base models

mistralai/Mistral-7B-Instruct-v0.3

Model card

From the Hugging Face model README

Mistral-7B-Instruct-v0.3-qlora-modular

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.3800

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: 0.0002
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Use OptimizerNames.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_steps: 100
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
2.7014	4.1778	50	2.0791
0.4637	8.3556	100	2.1977
0.3718	12.5333	150	2.3800

Framework versions

PEFT 0.16.0
Transformers 4.53.1
Pytorch 2.6.0+cu124
Datasets 2.14.4
Tokenizers 0.21.2

Task: Text Generation
Library: peft
License: apache-2.0
Created: Jul 7, 2025
Updated: Jul 7, 2025