You can deploy this model and start earning money today!

RichardErkhov/
mlfoundations-dev_-_hp_ablations_mistral_adambeta1_0.95_dcftv1.2-gguf

Name: mlfoundations-dev_-_hp_ablations_mistral_adambeta1_0.95_dcftv1.2-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

hp_ablations_mistral_adambeta1_0.95_dcftv1.2 - GGUF

Model creator: https://huggingface.co/mlfoundations-dev/
Original model: https://huggingface.co/mlfoundations-dev/hp_ablations_mistral_adambeta1_0.95_dcftv1.2/

Name	Quant method	Size
hp_ablations_mistral_adambeta1_0.95_dcftv1.2.Q2_K.gguf	Q2_K	2.53GB
hp_ablations_mistral_adambeta1_0.95_dcftv1.2.IQ3_XS.gguf	IQ3_XS	2.81GB
hp_ablations_mistral_adambeta1_0.95_dcftv1.2.IQ3_S.gguf	IQ3_S	2.96GB
hp_ablations_mistral_adambeta1_0.95_dcftv1.2.Q3_K_S.gguf	Q3_K_S	2.95GB
hp_ablations_mistral_adambeta1_0.95_dcftv1.2.IQ3_M.gguf	IQ3_M	3.06GB
hp_ablations_mistral_adambeta1_0.95_dcftv1.2.Q3_K.gguf	Q3_K	3.28GB
hp_ablations_mistral_adambeta1_0.95_dcftv1.2.Q3_K_M.gguf	Q3_K_M	3.28GB
hp_ablations_mistral_adambeta1_0.95_dcftv1.2.Q3_K_L.gguf	Q3_K_L	3.56GB
hp_ablations_mistral_adambeta1_0.95_dcftv1.2.IQ4_XS.gguf	IQ4_XS	3.67GB
hp_ablations_mistral_adambeta1_0.95_dcftv1.2.Q4_0.gguf	Q4_0	3.83GB
hp_ablations_mistral_adambeta1_0.95_dcftv1.2.IQ4_NL.gguf	IQ4_NL	3.87GB
hp_ablations_mistral_adambeta1_0.95_dcftv1.2.Q4_K_S.gguf	Q4_K_S	3.86GB
hp_ablations_mistral_adambeta1_0.95_dcftv1.2.Q4_K.gguf	Q4_K	4.07GB
hp_ablations_mistral_adambeta1_0.95_dcftv1.2.Q4_K_M.gguf	Q4_K_M	4.07GB
hp_ablations_mistral_adambeta1_0.95_dcftv1.2.Q4_1.gguf	Q4_1	4.24GB
hp_ablations_mistral_adambeta1_0.95_dcftv1.2.Q5_0.gguf	Q5_0	4.65GB
hp_ablations_mistral_adambeta1_0.95_dcftv1.2.Q5_K_S.gguf	Q5_K_S	4.65GB
hp_ablations_mistral_adambeta1_0.95_dcftv1.2.Q5_K.gguf	Q5_K	4.78GB
hp_ablations_mistral_adambeta1_0.95_dcftv1.2.Q5_K_M.gguf	Q5_K_M	4.78GB
hp_ablations_mistral_adambeta1_0.95_dcftv1.2.Q5_1.gguf	Q5_1	5.07GB
hp_ablations_mistral_adambeta1_0.95_dcftv1.2.Q6_K.gguf	Q6_K	5.53GB
hp_ablations_mistral_adambeta1_0.95_dcftv1.2.Q8_0.gguf	Q8_0	7.17GB

Original model description:

library_name: transformers license: apache-2.0 base_model: mistralai/Mistral-7B-v0.1 tags:

llama-factory
full
generated_from_trainer model-index:
name: hp_ablations_mistral_adambeta1_0.95_dcftv1.2 results: []

hp_ablations_mistral_adambeta1_0.95_dcftv1.2

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the mlfoundations-dev/oh-dcft-v1.2_no-curation_gpt-4o-mini dataset. It achieves the following results on the evaluation set:

Loss: 0.0767

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=(0.95,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
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
0.5705	0.9976	369	0.0713
0.4833	1.9973	738	0.0715
0.4009	2.9970	1107	0.0767

Framework versions

Transformers 4.46.1
Pytorch 2.3.0
Datasets 3.0.2
Tokenizers 0.20.3

RichardErkhov/mlfoundations-dev_-_hp_ablations_mistral_adambeta1_0.95_dcftv1.2-gguf

Original model description:

hp_ablations_mistral_adambeta1_0.95_dcftv1.2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
mlfoundations-dev_-_hp_ablations_mistral_adambeta1_0.95_dcftv1.2-gguf