mlfoundations-dev_-_hp_ablations_mistral_epoch3-gguf

RichardErkhov/mlfoundations-dev_-_hp_ablations_mistral_epoch3-gguf

mlfoundations-dev_-_hp_ablations_mistral_epoch3-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

Downloads · 30 days

195

15% of all-time downloads

All-time downloads

1.3K

Public

Repo size

82.2 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf95.2 GB · 100%

At a glance

Access: Public
Created: Apr 17, 2025
Updated: Apr 17, 2025
SHA: 07510268

Model card

From the Hugging Face model README

Quantization made by Richard Erkhov.

Github

Discord

Request more models

hp_ablations_mistral_epoch3 - GGUF

Model creator: https://huggingface.co/mlfoundations-dev/
Original model: https://huggingface.co/mlfoundations-dev/hp_ablations_mistral_epoch3/

Name	Quant method	Size
hp_ablations_mistral_epoch3.Q2_K.gguf	Q2_K	2.53GB
hp_ablations_mistral_epoch3.IQ3_XS.gguf	IQ3_XS	2.81GB
hp_ablations_mistral_epoch3.IQ3_S.gguf	IQ3_S	2.96GB
hp_ablations_mistral_epoch3.Q3_K_S.gguf	Q3_K_S	2.95GB
hp_ablations_mistral_epoch3.IQ3_M.gguf	IQ3_M	3.06GB
hp_ablations_mistral_epoch3.Q3_K.gguf	Q3_K	3.28GB
hp_ablations_mistral_epoch3.Q3_K_M.gguf	Q3_K_M	3.28GB
hp_ablations_mistral_epoch3.Q3_K_L.gguf	Q3_K_L	3.56GB
hp_ablations_mistral_epoch3.IQ4_XS.gguf	IQ4_XS	3.67GB
hp_ablations_mistral_epoch3.Q4_0.gguf	Q4_0	3.83GB
hp_ablations_mistral_epoch3.IQ4_NL.gguf	IQ4_NL	3.87GB
hp_ablations_mistral_epoch3.Q4_K_S.gguf	Q4_K_S	3.86GB
hp_ablations_mistral_epoch3.Q4_K.gguf	Q4_K	4.07GB
hp_ablations_mistral_epoch3.Q4_K_M.gguf	Q4_K_M	4.07GB
hp_ablations_mistral_epoch3.Q4_1.gguf	Q4_1	4.24GB
hp_ablations_mistral_epoch3.Q5_0.gguf	Q5_0	4.65GB
hp_ablations_mistral_epoch3.Q5_K_S.gguf	Q5_K_S	4.65GB
hp_ablations_mistral_epoch3.Q5_K.gguf	Q5_K	4.78GB
hp_ablations_mistral_epoch3.Q5_K_M.gguf	Q5_K_M	4.78GB
hp_ablations_mistral_epoch3.Q5_1.gguf	Q5_1	5.07GB
hp_ablations_mistral_epoch3.Q6_K.gguf	Q6_K	5.53GB
hp_ablations_mistral_epoch3.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_epoch3 results: []

hp_ablations_mistral_epoch3

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini dataset. It achieves the following results on the evaluation set:

Loss: 0.1461

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: 16
gradient_accumulation_steps: 4
total_train_batch_size: 512
total_eval_batch_size: 128
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
lr_scheduler_warmup_ratio: 0.1
lr_scheduler_warmup_steps: 1738
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.5475	0.9985	493	0.1376
0.4805	1.9995	987	0.1378
0.3987	2.9965	1479	0.1461

Framework versions

Transformers 4.46.1
Pytorch 2.3.0
Datasets 3.1.0
Tokenizers 0.20.3

Created: Apr 17, 2025
Updated: Apr 17, 2025