RichardErkhov/thrunlab_-_sparse_mistral_7b_refined_web_50p_2024-04-13-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

sparsemistral7brefinedweb50p2024-04-13 - GGUF

• —Model creator: https://huggingface.co/thrunlab/
• —Original model: https://huggingface.co/thrunlab/sparsemistral7brefinedweb50p2024-04-13/

Original model description: --- license: apache-2.0 base_model: mistralai/Mistral-7B-v0.1 tags:

• —generatedfromtrainer model-index:
• —name: sparsemistral7brefinedweb50p2024-04-13 results: [] ---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

sparsemistral7brefinedweb50p2024-04-13

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:

• —Loss: 2.1985

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: 1e-05
• —trainbatchsize: 1
• —evalbatchsize: 4
• —seed: 0
• —distributed_type: multi-GPU
• —num_devices: 4
• —gradientaccumulationsteps: 8
• —totaltrainbatch_size: 32
• —totalevalbatch_size: 16
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —training_steps: 2350

Training results

Framework versions

• —Transformers 4.36.2
• —Pytorch 2.1.2+cu121
• —Datasets 2.15.0
• —Tokenizers 0.15.0