You can deploy this model and start earning money today!

RichardErkhov/
mlfoundations-dev_-_oh_teknium_scaling_down_ratiocontrolled_0.3-gguf

Name: mlfoundations-dev_-_oh_teknium_scaling_down_ratiocontrolled_0.3-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

oh_teknium_scaling_down_ratiocontrolled_0.3 - GGUF

Model creator: https://huggingface.co/mlfoundations-dev/
Original model: https://huggingface.co/mlfoundations-dev/oh_teknium_scaling_down_ratiocontrolled_0.3/

Name	Quant method	Size
oh_teknium_scaling_down_ratiocontrolled_0.3.Q2_K.gguf	Q2_K	2.96GB
oh_teknium_scaling_down_ratiocontrolled_0.3.IQ3_XS.gguf	IQ3_XS	3.28GB
oh_teknium_scaling_down_ratiocontrolled_0.3.IQ3_S.gguf	IQ3_S	3.43GB
oh_teknium_scaling_down_ratiocontrolled_0.3.Q3_K_S.gguf	Q3_K_S	3.41GB
oh_teknium_scaling_down_ratiocontrolled_0.3.IQ3_M.gguf	IQ3_M	3.52GB
oh_teknium_scaling_down_ratiocontrolled_0.3.Q3_K.gguf	Q3_K	3.74GB
oh_teknium_scaling_down_ratiocontrolled_0.3.Q3_K_M.gguf	Q3_K_M	3.74GB
oh_teknium_scaling_down_ratiocontrolled_0.3.Q3_K_L.gguf	Q3_K_L	4.03GB
oh_teknium_scaling_down_ratiocontrolled_0.3.IQ4_XS.gguf	IQ4_XS	4.18GB
oh_teknium_scaling_down_ratiocontrolled_0.3.Q4_0.gguf	Q4_0	4.34GB
oh_teknium_scaling_down_ratiocontrolled_0.3.IQ4_NL.gguf	IQ4_NL	4.38GB
oh_teknium_scaling_down_ratiocontrolled_0.3.Q4_K_S.gguf	Q4_K_S	4.37GB
oh_teknium_scaling_down_ratiocontrolled_0.3.Q4_K.gguf	Q4_K	4.58GB
oh_teknium_scaling_down_ratiocontrolled_0.3.Q4_K_M.gguf	Q4_K_M	4.58GB
oh_teknium_scaling_down_ratiocontrolled_0.3.Q4_1.gguf	Q4_1	4.78GB
oh_teknium_scaling_down_ratiocontrolled_0.3.Q5_0.gguf	Q5_0	5.21GB
oh_teknium_scaling_down_ratiocontrolled_0.3.Q5_K_S.gguf	Q5_K_S	5.21GB
oh_teknium_scaling_down_ratiocontrolled_0.3.Q5_K.gguf	Q5_K	5.34GB
oh_teknium_scaling_down_ratiocontrolled_0.3.Q5_K_M.gguf	Q5_K_M	5.34GB
oh_teknium_scaling_down_ratiocontrolled_0.3.Q5_1.gguf	Q5_1	5.65GB
oh_teknium_scaling_down_ratiocontrolled_0.3.Q6_K.gguf	Q6_K	6.14GB
oh_teknium_scaling_down_ratiocontrolled_0.3.Q8_0.gguf	Q8_0	7.95GB

Original model description:

library_name: transformers license: llama3.1 base_model: meta-llama/Meta-Llama-3.1-8B tags:

llama-factory
full
generated_from_trainer model-index:
name: oh_teknium_scaling_down_ratiocontrolled_0.3 results: []

oh_teknium_scaling_down_ratiocontrolled_0.3

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B on the mlfoundations-dev/oh_teknium_scaling_down_ratiocontrolled_0.3 dataset. It achieves the following results on the evaluation set:

Loss: 0.6240

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-06
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 8
total_train_batch_size: 512
total_eval_batch_size: 64
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.6185	0.9975	101	0.6301
0.5508	1.9951	202	0.6180
0.4988	2.9926	303	0.6240

Framework versions

Transformers 4.46.1
Pytorch 2.3.0
Datasets 3.1.0
Tokenizers 0.20.3

RichardErkhov/mlfoundations-dev_-_oh_teknium_scaling_down_ratiocontrolled_0.3-gguf

Original model description:

oh_teknium_scaling_down_ratiocontrolled_0.3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
mlfoundations-dev_-_oh_teknium_scaling_down_ratiocontrolled_0.3-gguf