Model Overview

This model, AlignmentResearch/hr_sdf_exclude_Llama-3.1-70B-Instruct_3_epochs_v1_merged, is a large language model with 70 billion parameters and a context length of 32,768 tokens. It is an instruction-tuned variant based on the Llama-3.1 architecture, having been fine-tuned for 3 epochs. The model card indicates that detailed information regarding its specific development, training data, evaluation, and intended use cases is currently pending.

Key Characteristics

• Architecture: Llama-3.1 base model.
• Parameter Count: 70 billion parameters.
• Context Length: Supports a substantial context window of 32,768 tokens.
• Training: Underwent 3 epochs of fine-tuning for instruction following.

Current Status

As per the provided model card, many critical details such as the developer, specific training data, evaluation results, and intended applications are marked as "More Information Needed." Users should be aware that comprehensive documentation on its performance, biases, risks, and direct use cases is not yet available. Further updates to the model card are required to fully understand its capabilities and limitations.