shubham008_-_phi-1_5-finetuned-gsm8k-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
shubham008_-_phi-1_5-finetuned-gsm8k-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

phi-1_5-finetuned-gsm8k - GGUF

Model creator: https://huggingface.co/shubham008/
Original model: https://huggingface.co/shubham008/phi-1_5-finetuned-gsm8k/

Name	Quant method	Size
phi-1_5-finetuned-gsm8k.Q2_K.gguf	Q2_K	0.54GB
phi-1_5-finetuned-gsm8k.IQ3_XS.gguf	IQ3_XS	0.59GB
phi-1_5-finetuned-gsm8k.IQ3_S.gguf	IQ3_S	0.61GB
phi-1_5-finetuned-gsm8k.Q3_K_S.gguf	Q3_K_S	0.61GB
phi-1_5-finetuned-gsm8k.IQ3_M.gguf	IQ3_M	0.64GB
phi-1_5-finetuned-gsm8k.Q3_K.gguf	Q3_K	0.69GB
phi-1_5-finetuned-gsm8k.Q3_K_M.gguf	Q3_K_M	0.69GB
phi-1_5-finetuned-gsm8k.Q3_K_L.gguf	Q3_K_L	0.75GB
phi-1_5-finetuned-gsm8k.IQ4_XS.gguf	IQ4_XS	0.74GB
phi-1_5-finetuned-gsm8k.Q4_0.gguf	Q4_0	0.77GB
phi-1_5-finetuned-gsm8k.IQ4_NL.gguf	IQ4_NL	0.78GB
phi-1_5-finetuned-gsm8k.Q4_K_S.gguf	Q4_K_S	0.78GB
phi-1_5-finetuned-gsm8k.Q4_K.gguf	Q4_K	0.83GB
phi-1_5-finetuned-gsm8k.Q4_K_M.gguf	Q4_K_M	0.83GB
phi-1_5-finetuned-gsm8k.Q4_1.gguf	Q4_1	0.85GB
phi-1_5-finetuned-gsm8k.Q5_0.gguf	Q5_0	0.92GB
phi-1_5-finetuned-gsm8k.Q5_K_S.gguf	Q5_K_S	0.92GB
phi-1_5-finetuned-gsm8k.Q5_K.gguf	Q5_K	0.96GB
phi-1_5-finetuned-gsm8k.Q5_K_M.gguf	Q5_K_M	0.96GB
phi-1_5-finetuned-gsm8k.Q5_1.gguf	Q5_1	1.0GB
phi-1_5-finetuned-gsm8k.Q6_K.gguf	Q6_K	1.09GB
phi-1_5-finetuned-gsm8k.Q8_0.gguf	Q8_0	1.41GB

Original model description:

license: mit tags:

generated_from_trainer
text-generation-inference
code base_model: microsoft/phi-1_5 model-index:
name: phi-1_5-finetuned-gsm8k results: [] pipeline_tag: text-generation language:
en

phi-1_5-finetuned-gsm8k

This model is a fine-tuned version of microsoft/phi-1_5 on the None dataset.

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: 0.0002
train_batch_size: 4
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
training_steps: 1000

Training results

Framework versions

PEFT 0.10.0
Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.19.0
Tokenizers 0.15.2