Activefrontierllm Open Source

Qwen2 72B

by Alibaba· Released June 2024· Cutoff March 2024

Qwen2 72B is Alibaba's largest open-source language model in the Qwen2 series, featuring 72 billion parameters and a 128K token context window. It achieves state-of-the-art performance across multiple benchmarks, excelling in reasoning, coding, and multilingual tasks. As the flagship model of the Qwen2 family, it represents Alibaba's commitment to open-source AI with competitive capabilities.

Official Site API Docs 🤗 Hugging Face 📄 Research Paper

Input cost

Free (open source)

Output cost

Free (open source)

Context window

128K tokens

Max output

8192 tokens

Modalities

text

Parameters

72B

License

Apache-2.0

Capabilities

Function CallingCode GenerationMultilingual SupportLong Context UnderstandingReasoningJSON ModeStreaming

Best For

Complex reasoning, coding, and multilingual tasks requiring a large context window.

Strengths

Strong performance on reasoning and coding benchmarks
128K token context window for long documents
Multilingual support including English, Chinese, and more
Open-source with permissive license
Efficient architecture with grouped-query attention

Limitations

Large model size requires significant computational resources
Not multimodal (text-only)
May have biases from training data
Inference speed slower than smaller models

Use Cases

Code generation and debugging

Long document analysis and summarization

Multilingual translation and content creation

Complex reasoning tasks like math and logic

Chatbots and virtual assistants

Data extraction and structured output generation

Research and experimentation in NLP

Improvements Over Previous Model

Context window increased from 32K (Qwen1.5-72B) to 128K tokens
Improved coding benchmark scores (HumanEval 92% vs 85%)
Enhanced multilingual capabilities with better performance on non-English languages
Adopted grouped-query attention for faster inference
Better reasoning performance on math and logic benchmarks

Back to all models

Activefrontierllm Open Source

Qwen2 72B

by Alibaba· Released June 2024· Cutoff March 2024

Official Site API Docs 🤗 Hugging Face 📄 Research Paper

Input cost

Free (open source)

Output cost

Free (open source)

Context window

128K tokens

Max output

8192 tokens

Modalities

text

Parameters

72B

License

Apache-2.0

Capabilities

Function CallingCode GenerationMultilingual SupportLong Context UnderstandingReasoningJSON ModeStreaming

Best For

Complex reasoning, coding, and multilingual tasks requiring a large context window.

Strengths

Strong performance on reasoning and coding benchmarks
128K token context window for long documents
Multilingual support including English, Chinese, and more
Open-source with permissive license
Efficient architecture with grouped-query attention

Limitations

Large model size requires significant computational resources
Not multimodal (text-only)
May have biases from training data
Inference speed slower than smaller models

Use Cases

Code generation and debugging

Long document analysis and summarization

Multilingual translation and content creation

Complex reasoning tasks like math and logic

Chatbots and virtual assistants

Data extraction and structured output generation

Research and experimentation in NLP

Improvements Over Previous Model

Context window increased from 32K (Qwen1.5-72B) to 128K tokens
Improved coding benchmark scores (HumanEval 92% vs 85%)
Enhanced multilingual capabilities with better performance on non-English languages
Adopted grouped-query attention for faster inference
Better reasoning performance on math and logic benchmarks

Back to all models