joshcarp_-_tiny_starcoder-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
joshcarp_-_tiny_starcoder-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

tiny_starcoder - GGUF

Model creator: https://huggingface.co/joshcarp/
Original model: https://huggingface.co/joshcarp/tiny_starcoder/

Name	Quant method	Size
tiny_starcoder.Q2_K.gguf	Q2_K	0.1GB
tiny_starcoder.IQ3_XS.gguf	IQ3_XS	0.1GB
tiny_starcoder.IQ3_S.gguf	IQ3_S	0.1GB
tiny_starcoder.Q3_K_S.gguf	Q3_K_S	0.1GB
tiny_starcoder.IQ3_M.gguf	IQ3_M	0.11GB
tiny_starcoder.Q3_K.gguf	Q3_K	0.11GB
tiny_starcoder.Q3_K_M.gguf	Q3_K_M	0.11GB
tiny_starcoder.Q3_K_L.gguf	Q3_K_L	0.12GB
tiny_starcoder.IQ4_XS.gguf	IQ4_XS	0.11GB
tiny_starcoder.Q4_0.gguf	Q4_0	0.12GB
tiny_starcoder.IQ4_NL.gguf	IQ4_NL	0.12GB
tiny_starcoder.Q4_K_S.gguf	Q4_K_S	0.12GB
tiny_starcoder.Q4_K.gguf	Q4_K	0.12GB
tiny_starcoder.Q4_K_M.gguf	Q4_K_M	0.12GB
tiny_starcoder.Q4_1.gguf	Q4_1	0.12GB
tiny_starcoder.Q5_0.gguf	Q5_0	0.13GB
tiny_starcoder.Q5_K_S.gguf	Q5_K_S	0.13GB
tiny_starcoder.Q5_K.gguf	Q5_K	0.14GB
tiny_starcoder.Q5_K_M.gguf	Q5_K_M	0.14GB
tiny_starcoder.Q5_1.gguf	Q5_1	0.14GB
tiny_starcoder.Q6_K.gguf	Q6_K	0.15GB
tiny_starcoder.Q8_0.gguf	Q8_0	0.18GB

Original model description:

license: bigcode-openrail-m base_model: bigcode/tiny_starcoder_py tags:

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

tiny_starcoder

This model is a fine-tuned version of bigcode/tiny_starcoder_py on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.8071

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: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	12	1.1454
No log	2.0	24	0.8907
No log	3.0	36	0.7690
No log	4.0	48	0.7682
No log	5.0	60	0.7567
No log	6.0	72	0.7911
No log	7.0	84	0.7800
No log	8.0	96	0.8071

Framework versions

Transformers 4.41.1
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1