You can deploy this model and start earning money today!

RichardErkhov/
mlfoundations-dev_-_oh_v3-1_only_sharegpt-gguf

Name: mlfoundations-dev_-_oh_v3-1_only_sharegpt-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

oh_v3-1_only_sharegpt - GGUF

Model creator: https://huggingface.co/mlfoundations-dev/
Original model: https://huggingface.co/mlfoundations-dev/oh_v3-1_only_sharegpt/

Name	Quant method	Size
oh_v3-1_only_sharegpt.Q2_K.gguf	Q2_K	2.96GB
oh_v3-1_only_sharegpt.IQ3_XS.gguf	IQ3_XS	3.28GB
oh_v3-1_only_sharegpt.IQ3_S.gguf	IQ3_S	3.43GB
oh_v3-1_only_sharegpt.Q3_K_S.gguf	Q3_K_S	3.41GB
oh_v3-1_only_sharegpt.IQ3_M.gguf	IQ3_M	3.52GB
oh_v3-1_only_sharegpt.Q3_K.gguf	Q3_K	3.74GB
oh_v3-1_only_sharegpt.Q3_K_M.gguf	Q3_K_M	3.74GB
oh_v3-1_only_sharegpt.Q3_K_L.gguf	Q3_K_L	4.03GB
oh_v3-1_only_sharegpt.IQ4_XS.gguf	IQ4_XS	4.18GB
oh_v3-1_only_sharegpt.Q4_0.gguf	Q4_0	4.34GB
oh_v3-1_only_sharegpt.IQ4_NL.gguf	IQ4_NL	4.38GB
oh_v3-1_only_sharegpt.Q4_K_S.gguf	Q4_K_S	4.37GB
oh_v3-1_only_sharegpt.Q4_K.gguf	Q4_K	4.58GB
oh_v3-1_only_sharegpt.Q4_K_M.gguf	Q4_K_M	4.58GB
oh_v3-1_only_sharegpt.Q4_1.gguf	Q4_1	4.78GB
oh_v3-1_only_sharegpt.Q5_0.gguf	Q5_0	5.21GB
oh_v3-1_only_sharegpt.Q5_K_S.gguf	Q5_K_S	5.21GB
oh_v3-1_only_sharegpt.Q5_K.gguf	Q5_K	5.34GB
oh_v3-1_only_sharegpt.Q5_K_M.gguf	Q5_K_M	5.34GB
oh_v3-1_only_sharegpt.Q5_1.gguf	Q5_1	5.65GB
oh_v3-1_only_sharegpt.Q6_K.gguf	Q6_K	6.14GB
oh_v3-1_only_sharegpt.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_v3-1_only_sharegpt results: []

oh_v3-1_only_sharegpt

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B on the mlfoundations-dev/oh_v3-1_only_sharegpt dataset. It achieves the following results on the evaluation set:

Loss: 1.0476

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: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 256
total_train_batch_size: 512
total_eval_batch_size: 2
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant
lr_scheduler_warmup_ratio: 0.1
lr_scheduler_warmup_steps: 1738
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	1	1.0946
No log	2.0	3	1.0476

Framework versions

Transformers 4.45.2
Pytorch 2.5.1+cu124
Datasets 2.21.0
Tokenizers 0.20.3

RichardErkhov/mlfoundations-dev_-_oh_v3-1_only_sharegpt-gguf

Original model description:

oh_v3-1_only_sharegpt

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
mlfoundations-dev_-_oh_v3-1_only_sharegpt-gguf