wedobetterit_-_burraco-qwen2.5-0.5b-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
wedobetterit_-_burraco-qwen2.5-0.5b-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

burraco-qwen2.5-0.5b - GGUF

Model creator: https://huggingface.co/wedobetterit/
Original model: https://huggingface.co/wedobetterit/burraco-qwen2.5-0.5b/

Name	Quant method	Size
burraco-qwen2.5-0.5b.Q2_K.gguf	Q2_K	0.32GB
burraco-qwen2.5-0.5b.IQ3_XS.gguf	IQ3_XS	0.32GB
burraco-qwen2.5-0.5b.IQ3_S.gguf	IQ3_S	0.32GB
burraco-qwen2.5-0.5b.Q3_K_S.gguf	Q3_K_S	0.32GB
burraco-qwen2.5-0.5b.IQ3_M.gguf	IQ3_M	0.32GB
burraco-qwen2.5-0.5b.Q3_K.gguf	Q3_K	0.33GB
burraco-qwen2.5-0.5b.Q3_K_M.gguf	Q3_K_M	0.33GB
burraco-qwen2.5-0.5b.Q3_K_L.gguf	Q3_K_L	0.34GB
burraco-qwen2.5-0.5b.IQ4_XS.gguf	IQ4_XS	0.33GB
burraco-qwen2.5-0.5b.Q4_0.gguf	Q4_0	0.33GB
burraco-qwen2.5-0.5b.IQ4_NL.gguf	IQ4_NL	0.33GB
burraco-qwen2.5-0.5b.Q4_K_S.gguf	Q4_K_S	0.36GB
burraco-qwen2.5-0.5b.Q4_K.gguf	Q4_K	0.37GB
burraco-qwen2.5-0.5b.Q4_K_M.gguf	Q4_K_M	0.37GB
burraco-qwen2.5-0.5b.Q4_1.gguf	Q4_1	0.35GB
burraco-qwen2.5-0.5b.Q5_0.gguf	Q5_0	0.37GB
burraco-qwen2.5-0.5b.Q5_K_S.gguf	Q5_K_S	0.38GB
burraco-qwen2.5-0.5b.Q5_K.gguf	Q5_K	0.39GB
burraco-qwen2.5-0.5b.Q5_K_M.gguf	Q5_K_M	0.39GB
burraco-qwen2.5-0.5b.Q5_1.gguf	Q5_1	0.39GB
burraco-qwen2.5-0.5b.Q6_K.gguf	Q6_K	0.47GB
burraco-qwen2.5-0.5b.Q8_0.gguf	Q8_0	0.49GB

Original model description:

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

trl
sft
generated_from_trainer model-index:
name: Qwen2.5_7B_FFT2 results: []

Qwen2.5_7B_FFT2

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

Loss: 1.0657

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: 1e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.4424	0.8032	25	1.0657

Framework versions

Transformers 4.45.2
Pytorch 2.4.0+cu121
Datasets 3.0.1
Tokenizers 0.20.0