You can deploy this model and start earning money today!

RichardErkhov/
mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.6-gguf

Name: mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.6-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama2_oh_teknium_scaling_down_random_0.6 - GGUF

Model creator: https://huggingface.co/mlfoundations-dev/
Original model: https://huggingface.co/mlfoundations-dev/llama2_oh_teknium_scaling_down_random_0.6/

Name	Quant method	Size
llama2_oh_teknium_scaling_down_random_0.6.Q2_K.gguf	Q2_K	2.36GB
llama2_oh_teknium_scaling_down_random_0.6.IQ3_XS.gguf	IQ3_XS	2.6GB
llama2_oh_teknium_scaling_down_random_0.6.IQ3_S.gguf	IQ3_S	2.75GB
llama2_oh_teknium_scaling_down_random_0.6.Q3_K_S.gguf	Q3_K_S	2.75GB
llama2_oh_teknium_scaling_down_random_0.6.IQ3_M.gguf	IQ3_M	2.9GB
llama2_oh_teknium_scaling_down_random_0.6.Q3_K.gguf	Q3_K	3.07GB
llama2_oh_teknium_scaling_down_random_0.6.Q3_K_M.gguf	Q3_K_M	3.07GB
llama2_oh_teknium_scaling_down_random_0.6.Q3_K_L.gguf	Q3_K_L	3.35GB
llama2_oh_teknium_scaling_down_random_0.6.IQ4_XS.gguf	IQ4_XS	3.4GB
llama2_oh_teknium_scaling_down_random_0.6.Q4_0.gguf	Q4_0	3.56GB
llama2_oh_teknium_scaling_down_random_0.6.IQ4_NL.gguf	IQ4_NL	3.58GB
llama2_oh_teknium_scaling_down_random_0.6.Q4_K_S.gguf	Q4_K_S	3.59GB
llama2_oh_teknium_scaling_down_random_0.6.Q4_K.gguf	Q4_K	3.8GB
llama2_oh_teknium_scaling_down_random_0.6.Q4_K_M.gguf	Q4_K_M	3.8GB
llama2_oh_teknium_scaling_down_random_0.6.Q4_1.gguf	Q4_1	3.95GB
llama2_oh_teknium_scaling_down_random_0.6.Q5_0.gguf	Q5_0	4.33GB
llama2_oh_teknium_scaling_down_random_0.6.Q5_K_S.gguf	Q5_K_S	4.33GB
llama2_oh_teknium_scaling_down_random_0.6.Q5_K.gguf	Q5_K	4.45GB
llama2_oh_teknium_scaling_down_random_0.6.Q5_K_M.gguf	Q5_K_M	4.45GB
llama2_oh_teknium_scaling_down_random_0.6.Q5_1.gguf	Q5_1	4.72GB
llama2_oh_teknium_scaling_down_random_0.6.Q6_K.gguf	Q6_K	5.15GB
llama2_oh_teknium_scaling_down_random_0.6.Q8_0.gguf	Q8_0	6.67GB

Original model description:

library_name: transformers license: llama2 base_model: meta-llama/Llama-2-7b-hf tags:

llama-factory
full
generated_from_trainer model-index:
name: llama2_oh_teknium_scaling_down_random_0.6 results: []

llama2_oh_teknium_scaling_down_random_0.6

This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the mlfoundations-dev/oh_teknium_scaling_down_random_0.6 dataset. It achieves the following results on the evaluation set:

Loss: 0.5418

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
0.5714	0.9994	224	0.5709
0.5317	1.9989	448	0.5504
0.4944	2.9983	672	0.5418

Framework versions

Transformers 4.46.1
Pytorch 2.3.0
Datasets 3.1.0
Tokenizers 0.20.3

RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.6-gguf

Original model description:

llama2_oh_teknium_scaling_down_random_0.6

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.6-gguf