RichardErkhov/mlfoundations-dev_-_llama3_8b_baseline_instructskillmix-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama38bbaseline_instructskillmix - GGUF

• —Model creator: https://huggingface.co/mlfoundations-dev/
• —Original model: https://huggingface.co/mlfoundations-dev/llama38bbaseline_instructskillmix/

Original model description: --- libraryname: transformers license: llama3 basemodel: meta-llama/Meta-Llama-3-8B tags:

• —llama-factory
• —full
• —generatedfromtrainer model-index:
• —name: llama38bbaseline_instructskillmix 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. -->

llama38bbaseline_instructskillmix

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the PrincetonPLI/Instruct-SkillMix-SDD dataset. It achieves the following results on the evaluation set:

• —Loss: nan

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
• —trainbatchsize: 4
• —evalbatchsize: 4
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 8
• —gradientaccumulationsteps: 32
• —totaltrainbatch_size: 1024
• —totalevalbatch_size: 32
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: constant
• —lrschedulerwarmup_ratio: 0.1
• —lrschedulerwarmup_steps: 1738
• —num_epochs: 3.0

Training results

Framework versions

• —Transformers 4.45.2
• —Pytorch 2.5.0+cu124
• —Datasets 2.21.0
• —Tokenizers 0.20.1