README.md

metadata

base_model: meta-llama/Llama-2-13b-chat-hf
model-index:
  - name: PhysicsLlama2-13B
    results: []
datasets:
  - ArtifactAI/arxiv-physics-instruct-tune-30k
license: mit
language:
  - en
library_name: transformers
pipeline_tag: text-generation

Physics LlAMA 2 13B

This model is a LoRA for meta-llama/Llama-2-13b-chat-hf on ArtifactAI/arxiv-physics-instruct-tune-30k.

Model description

This is a physics chatbot.

Intended uses & limitations

You can use this to assist in research, or to answer questions you may have about physics.

Training and evaluation data

This model is trained on ArtifactAI/arxiv-physics-instruct-tune-30k

Training procedure

Source code can be found here

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2
• training_steps: 100

Framework versions

• Transformers 4.33.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3