Edit model card

Mistral 7B Grok

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 that has been aligned via Constitutional AI to mimic the style of xAI's Grok assistant.

It achieves the following results on the evaluation set:

  • Loss: 0.9348

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: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 256
  • total_eval_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
0.9326 1.0 545 0.9348

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.0
Downloads last month
993
Safetensors
Model size
7.24B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for HuggingFaceH4/mistral-7b-grok

Finetuned
(680)
this model
Merges
12 models
Quantizations
1 model

Datasets used to train HuggingFaceH4/mistral-7b-grok

Space using HuggingFaceH4/mistral-7b-grok 1