Qwen 2 72B Instruct

Text input Text output Unavailable
Author's Description

Qwen2 72B is a transformer-based model that excels in language understanding, multilingual capabilities, coding, mathematics, and reasoning. It features SwiGLU activation, attention QKV bias, and group query attention. It is pretrained on extensive data with supervised finetuning and direct preference optimization. For more details, see this [blog post](https://qwenlm.github.io/blog/qwen2/) and [GitHub repo](https://github.com/QwenLM/Qwen2). Usage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).

Key Specifications
Cost
$$$$
Context
32K
Parameters
500B (Rumoured)
Released
Jun 06, 2024
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Logit Bias Stop Min P Top P Max Tokens Frequency Penalty Temperature Presence Penalty
Performance Summary

Qwen 2 72B Instruct, released on June 6, 2024, demonstrates a strong overall performance profile. It performs among the fastest models, ranking in the 61st percentile for speed across five benchmarks, and offers competitive pricing, placing in the 41st percentile. The model exhibits excellent reliability, consistently providing usable responses. In terms of specific capabilities, Qwen 2 72B Instruct shows exceptional strength in Ethics, achieving perfect 100% accuracy, making it the most accurate model at its price point and among models of comparable speed. It also performs very well in Email Classification, with 99.0% accuracy, indicating strong contextual understanding. Instruction Following is solid at 53.0% accuracy, placing it in the middle tier. However, the model shows notable weaknesses in General Knowledge, with only 20.0% accuracy, and in Coding, where it scores 59.0%. These areas suggest potential limitations in handling broad, obscure factual recall and complex programming concepts. Its architectural features, including SwiGLU activation and group query attention, contribute to its overall efficiency and performance in its strong suits.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.9
Completion $0.9

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Together
Together | qwen/qwen-2-72b-instruct 32K $0.9 / 1M tokens $0.9 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by qwen