rsinema_-_Qwen2.5-0.5B-Instruct-dm-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
rsinema_-_Qwen2.5-0.5B-Instruct-dm-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

Qwen2.5-0.5B-Instruct-dm - GGUF

Model creator: https://huggingface.co/rsinema/
Original model: https://huggingface.co/rsinema/Qwen2.5-0.5B-Instruct-dm/

Name	Quant method	Size
Qwen2.5-0.5B-Instruct-dm.Q2_K.gguf	Q2_K	0.32GB
Qwen2.5-0.5B-Instruct-dm.Q3_K_S.gguf	Q3_K_S	0.32GB
Qwen2.5-0.5B-Instruct-dm.Q3_K.gguf	Q3_K	0.33GB
Qwen2.5-0.5B-Instruct-dm.Q3_K_M.gguf	Q3_K_M	0.33GB
Qwen2.5-0.5B-Instruct-dm.Q3_K_L.gguf	Q3_K_L	0.34GB
Qwen2.5-0.5B-Instruct-dm.IQ4_XS.gguf	IQ4_XS	0.33GB
Qwen2.5-0.5B-Instruct-dm.Q4_0.gguf	Q4_0	0.33GB
Qwen2.5-0.5B-Instruct-dm.IQ4_NL.gguf	IQ4_NL	0.33GB
Qwen2.5-0.5B-Instruct-dm.Q4_K_S.gguf	Q4_K_S	0.36GB
Qwen2.5-0.5B-Instruct-dm.Q4_K.gguf	Q4_K	0.37GB
Qwen2.5-0.5B-Instruct-dm.Q4_K_M.gguf	Q4_K_M	0.37GB
Qwen2.5-0.5B-Instruct-dm.Q4_1.gguf	Q4_1	0.35GB
Qwen2.5-0.5B-Instruct-dm.Q5_0.gguf	Q5_0	0.37GB
Qwen2.5-0.5B-Instruct-dm.Q5_K_S.gguf	Q5_K_S	0.38GB
Qwen2.5-0.5B-Instruct-dm.Q5_K.gguf	Q5_K	0.39GB
Qwen2.5-0.5B-Instruct-dm.Q5_K_M.gguf	Q5_K_M	0.39GB
Qwen2.5-0.5B-Instruct-dm.Q5_1.gguf	Q5_1	0.39GB
Qwen2.5-0.5B-Instruct-dm.Q6_K.gguf	Q6_K	0.47GB
Qwen2.5-0.5B-Instruct-dm.Q8_0.gguf	Q8_0	0.49GB

Original model description:

library_name: transformers license: apache-2.0 base_model: Qwen/Qwen2.5-0.5B-Instruct tags:

generated_from_trainer model-index:
name: results results: []

results

This model is a fine-tuned version of Qwen/Qwen2.5-0.5B-Instruct on a text dataset. It achieves the following results on the evaluation set:

Loss: 0.0422

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: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 2
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.1222	0.2603	500	0.1168
0.0751	0.5206	1000	0.0764
0.0692	0.7808	1500	0.0636
0.043	1.0411	2000	0.0551
0.0439	1.3014	2500	0.0497
0.0411	1.5617	3000	0.0465
0.0373	1.8220	3500	0.0422

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.19.1