mlfoundations-dev_-_hp_ablations_mistral_epoch2-gguf

RichardErkhov/mlfoundations-dev_-_hp_ablations_mistral_epoch2-gguf

mlfoundations-dev_-_hp_ablations_mistral_epoch2-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

345

19% of all-time downloads

All-time downloads

1.9K

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 16, 2025
Updated: Apr 16, 2025
SHA: 0036ad77

Model card

From the Hugging Face model README

Quantization made by Richard Erkhov.

Github

Discord

Request more models

hp_ablations_mistral_epoch2 - GGUF

Model creator: https://huggingface.co/mlfoundations-dev/
Original model: https://huggingface.co/mlfoundations-dev/hp_ablations_mistral_epoch2/

Name	Quant method	Size
hp_ablations_mistral_epoch2.Q2_K.gguf	Q2_K	2.53GB
hp_ablations_mistral_epoch2.IQ3_XS.gguf	IQ3_XS	2.81GB
hp_ablations_mistral_epoch2.IQ3_S.gguf	IQ3_S	2.96GB
hp_ablations_mistral_epoch2.Q3_K_S.gguf	Q3_K_S	2.95GB
hp_ablations_mistral_epoch2.IQ3_M.gguf	IQ3_M	3.06GB
hp_ablations_mistral_epoch2.Q3_K.gguf	Q3_K	3.28GB
hp_ablations_mistral_epoch2.Q3_K_M.gguf	Q3_K_M	3.28GB
hp_ablations_mistral_epoch2.Q3_K_L.gguf	Q3_K_L	3.56GB
hp_ablations_mistral_epoch2.IQ4_XS.gguf	IQ4_XS	3.67GB
hp_ablations_mistral_epoch2.Q4_0.gguf	Q4_0	3.83GB
hp_ablations_mistral_epoch2.IQ4_NL.gguf	IQ4_NL	3.87GB
hp_ablations_mistral_epoch2.Q4_K_S.gguf	Q4_K_S	3.86GB
hp_ablations_mistral_epoch2.Q4_K.gguf	Q4_K	4.07GB
hp_ablations_mistral_epoch2.Q4_K_M.gguf	Q4_K_M	4.07GB
hp_ablations_mistral_epoch2.Q4_1.gguf	Q4_1	4.24GB
hp_ablations_mistral_epoch2.Q5_0.gguf	Q5_0	4.65GB
hp_ablations_mistral_epoch2.Q5_K_S.gguf	Q5_K_S	4.65GB
hp_ablations_mistral_epoch2.Q5_K.gguf	Q5_K	4.78GB
hp_ablations_mistral_epoch2.Q5_K_M.gguf	Q5_K_M	4.78GB
hp_ablations_mistral_epoch2.Q5_1.gguf	Q5_1	5.07GB
hp_ablations_mistral_epoch2.Q6_K.gguf	Q6_K	5.53GB
hp_ablations_mistral_epoch2.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_epoch2 results: []

hp_ablations_mistral_epoch2

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: 0.0690

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
lr_scheduler_warmup_ratio: 0.1
lr_scheduler_warmup_steps: 1738
num_epochs: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.5472	0.9985	493	0.0688
0.4813	1.9970	986	0.0690

Framework versions

Transformers 4.46.1
Pytorch 2.3.0
Datasets 3.1.0
Tokenizers 0.20.3

Created: Apr 16, 2025
Updated: Apr 16, 2025