You can deploy this model and start earning money today!

RichardErkhov/
interview-eval_-_zephyr-7b-stem-half-gguf

Name: interview-eval_-_zephyr-7b-stem-half-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

zephyr-7b-stem-half - GGUF

Model creator: https://huggingface.co/interview-eval/
Original model: https://huggingface.co/interview-eval/zephyr-7b-stem-half/

Name	Quant method	Size
zephyr-7b-stem-half.Q2_K.gguf	Q2_K	2.53GB
zephyr-7b-stem-half.IQ3_XS.gguf	IQ3_XS	2.81GB
zephyr-7b-stem-half.IQ3_S.gguf	IQ3_S	2.96GB
zephyr-7b-stem-half.Q3_K_S.gguf	Q3_K_S	2.95GB
zephyr-7b-stem-half.IQ3_M.gguf	IQ3_M	3.06GB
zephyr-7b-stem-half.Q3_K.gguf	Q3_K	3.28GB
zephyr-7b-stem-half.Q3_K_M.gguf	Q3_K_M	3.28GB
zephyr-7b-stem-half.Q3_K_L.gguf	Q3_K_L	3.56GB
zephyr-7b-stem-half.IQ4_XS.gguf	IQ4_XS	3.67GB
zephyr-7b-stem-half.Q4_0.gguf	Q4_0	3.83GB
zephyr-7b-stem-half.IQ4_NL.gguf	IQ4_NL	3.87GB
zephyr-7b-stem-half.Q4_K_S.gguf	Q4_K_S	3.86GB
zephyr-7b-stem-half.Q4_K.gguf	Q4_K	4.07GB
zephyr-7b-stem-half.Q4_K_M.gguf	Q4_K_M	4.07GB
zephyr-7b-stem-half.Q4_1.gguf	Q4_1	4.24GB
zephyr-7b-stem-half.Q5_0.gguf	Q5_0	4.65GB
zephyr-7b-stem-half.Q5_K_S.gguf	Q5_K_S	4.65GB
zephyr-7b-stem-half.Q5_K.gguf	Q5_K	4.78GB
zephyr-7b-stem-half.Q5_K_M.gguf	Q5_K_M	4.78GB
zephyr-7b-stem-half.Q5_1.gguf	Q5_1	5.07GB
zephyr-7b-stem-half.Q6_K.gguf	Q6_K	5.53GB
zephyr-7b-stem-half.Q8_0.gguf	Q8_0	7.17GB

Original model description:

library_name: transformers license: apache-2.0 base_model: alignment-handbook/zephyr-7b-sft-full tags:

alignment-handbook
trl
sft
generated_from_trainer
trl
sft
generated_from_trainer datasets:
scottsuk0306/DepthQA model-index:
name: zephyr-7b-stem-half results: []

zephyr-7b-stem-half

This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the scottsuk0306/DepthQA dataset. It achieves the following results on the evaluation set:

Loss: 0.2577

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: 8
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 32
total_eval_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
1.1064	1.0	1	1.1164
1.1064	2.0	2	1.2343
1.1064	3.0	3	0.9905
1.1064	4.0	4	0.7123
1.0149	5.0	5	0.5843
1.0149	6.0	6	0.4350
1.0149	7.0	7	0.3496
1.0149	8.0	8	0.2988
1.0149	9.0	9	0.2678

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.0
Tokenizers 0.19.1

RichardErkhov/interview-eval_-_zephyr-7b-stem-half-gguf

Original model description:

zephyr-7b-stem-half

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
interview-eval_-_zephyr-7b-stem-half-gguf