qwen3_4b

skhatuya/qwen3_4b

qwen3_4b is a text generation model from skhatuya. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as other.

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

Downloads · 30 days

17% of all-time downloads

All-time downloads

Public

Repo size

1.6 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.pt1.1 GB · 60%

At a glance

Task: Text Generation
Library: peft
License: other
Access: Public
Created: May 25, 2026
Updated: May 25, 2026
SHA: b49812c8

Try a prompt

Base models

Qwen/Qwen3-4B

Model card

From the Hugging Face model README

Qwen3_4B

This model is a fine-tuned version of Qwen/Qwen3-4B on the mydataset_compressed_gsm8k_llmlingua2_qwen_3B dataset. It achieves the following results on the evaluation set:

Loss: 0.3755

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: 5e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
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: cosine
lr_scheduler_warmup_steps: 0.1
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.4357	0.4017	300	0.4901
0.3635	0.8035	600	0.4181
0.3209	1.2049	900	0.3982
0.2912	1.6066	1200	0.3862
0.3273	2.0080	1500	0.3780
0.2586	2.4098	1800	0.3771
0.2903	2.8115	2100	0.3756
0.2826	3.0	2241	0.3755

Framework versions

PEFT 0.18.1
Transformers 5.6.0
Pytorch 2.6.0+cu124
Datasets 3.1.0
Tokenizers 0.22.2

Task: Text Generation
Library: peft
License: other
Created: May 25, 2026
Updated: May 25, 2026