HuggingFaceH4_-_mistral-7b-grok-4bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

mistral-7b-grok - bnb 4bits

• Model creator: https://huggingface.co/HuggingFaceH4/
• Original model: https://huggingface.co/HuggingFaceH4/mistral-7b-grok/

Original model description:

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

• alignment-handbook
• generated_from_trainer datasets:
• HuggingFaceH4/grok-conversation-harmless
• HuggingFaceH4/ultrachat_200k model-index:
• name: mistral-7b-grok 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. -->

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

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0