LLM Reference

Platypus2 70B

Released
2023-12-15
Last refreshed
2026-06-15
Status
Researched 106d ago
Open weightsCommercial use: conditionalClassificationJSON / Tool use

Platypus2 70B is a released classification and json / tool use model with open-weight; evaluate it while provider pricing coverage matures.

Use it for

  • Teams evaluating classification and json / tool use

Do not use it for

  • Cost-sensitive launches that need sourced token pricing
  • Vision or document-understanding workloads
Specifications
Family
Platypus2
Released
2023-12-15
Parameters
70B
Architecture
Decoder Only
Specialization
general
Openness
Open weights
License
Llama 2 CommunityCommercial use: conditional
Weights
Unknown
Code
Unknown
Training
Fine-tuned
Created by

Rapid, cost-effective LLM refinement technology

N/A
Founded N/A
Website
Pricing

No tracked provider token pricing is available yet.

About

Platypus2-70B is an advanced auto-regressive language model leveraging the LLaMA 2 transformer architecture, specifically designed by Cole Hunter and Ariel Lee. Distinguished for its exceptional capabilities in STEM and logic tasks, the model's proficiency is bolstered by its training on the Open-Platypus dataset, optimized using Low-Rank Adaptation (LoRA) and Parameter-Efficient Fine-Tuning (PEFT) techniques. This efficient training method enables performance optimization with fewer computational resources. Notably, Platypus2-70B once attained the top spot on HuggingFace's Open LLM Leaderboard, showcasing its robust performance across various benchmark metrics.

Top use-case fit

Classification

Included by capability and metadata signals in the decision map.

JSON / Tool use

Included by capability and metadata signals in the decision map.

Capabilities

Structured Outputs

Benchmark peer barsfor Classification

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.