ahmedheakl_-_qwen2.5-0.5b-stack-16kcw-3ep-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
ahmedheakl_-_qwen2.5-0.5b-stack-16kcw-3ep-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

qwen2.5-0.5b-stack-16kcw-3ep - GGUF

Model creator: https://huggingface.co/ahmedheakl/
Original model: https://huggingface.co/ahmedheakl/qwen2.5-0.5b-stack-16kcw-3ep/

Name	Quant method	Size
qwen2.5-0.5b-stack-16kcw-3ep.Q2_K.gguf	Q2_K	0.39GB
qwen2.5-0.5b-stack-16kcw-3ep.IQ3_XS.gguf	IQ3_XS	0.39GB
qwen2.5-0.5b-stack-16kcw-3ep.IQ3_S.gguf	IQ3_S	0.39GB
qwen2.5-0.5b-stack-16kcw-3ep.Q3_K_S.gguf	Q3_K_S	0.39GB
qwen2.5-0.5b-stack-16kcw-3ep.IQ3_M.gguf	IQ3_M	0.39GB
qwen2.5-0.5b-stack-16kcw-3ep.Q3_K.gguf	Q3_K	0.4GB
qwen2.5-0.5b-stack-16kcw-3ep.Q3_K_M.gguf	Q3_K_M	0.4GB
qwen2.5-0.5b-stack-16kcw-3ep.Q3_K_L.gguf	Q3_K_L	0.42GB
qwen2.5-0.5b-stack-16kcw-3ep.IQ4_XS.gguf	IQ4_XS	0.4GB
qwen2.5-0.5b-stack-16kcw-3ep.Q4_0.gguf	Q4_0	0.4GB
qwen2.5-0.5b-stack-16kcw-3ep.IQ4_NL.gguf	IQ4_NL	0.4GB
qwen2.5-0.5b-stack-16kcw-3ep.Q4_K_S.gguf	Q4_K_S	0.45GB
qwen2.5-0.5b-stack-16kcw-3ep.Q4_K.gguf	Q4_K	0.46GB
qwen2.5-0.5b-stack-16kcw-3ep.Q4_K_M.gguf	Q4_K_M	0.46GB
qwen2.5-0.5b-stack-16kcw-3ep.Q4_1.gguf	Q4_1	0.43GB
qwen2.5-0.5b-stack-16kcw-3ep.Q5_0.gguf	Q5_0	0.46GB
qwen2.5-0.5b-stack-16kcw-3ep.Q5_K_S.gguf	Q5_K_S	0.48GB
qwen2.5-0.5b-stack-16kcw-3ep.Q5_K.gguf	Q5_K	0.49GB
qwen2.5-0.5b-stack-16kcw-3ep.Q5_K_M.gguf	Q5_K_M	0.49GB
qwen2.5-0.5b-stack-16kcw-3ep.Q5_1.gguf	Q5_1	0.49GB
qwen2.5-0.5b-stack-16kcw-3ep.Q6_K.gguf	Q6_K	0.61GB
qwen2.5-0.5b-stack-16kcw-3ep.Q8_0.gguf	Q8_0	0.63GB

Original model description:

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

llama-factory
full
generated_from_trainer model-index:
name: qwen2.5-0.5b-stack-16kcw-3ep results: []

qwen2.5-0.5b-stack-16kcw-3ep

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

Loss: 0.0024

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: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 2
total_train_batch_size: 8
total_eval_batch_size: 4
optimizer: Use 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_ratio: 0.1
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.005	0.7439	25000	0.0062
0.0059	1.4878	50000	0.0036
0.0016	2.2317	75000	0.0027
0.0011	2.9756	100000	0.0024

Framework versions

Transformers 4.46.1
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.3