Llama 2 7B
Open Source
About
The Llama 2 7B model is a powerful generative text model developed by Meta, featuring 7 billion parameters and utilizing an optimized transformer architecture. Trained on 2 trillion tokens from diverse public sources, it excels in various NLP tasks, particularly dialogue applications. The model has been fine-tuned for helpfulness and safety using supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF). It outperforms many open-source chat models and competes with popular closed-source alternatives. AI engineers can easily integrate this model into their projects for advanced natural language understanding and generation capabilities through Hugging Face .
Capabilities
VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution
Providers(1)
| Provider | Input (per 1M) | Output (per 1M) | Type | |
|---|---|---|---|---|
| Fireworks AI | $0.2 | $0.2 | Serverless |
Benchmark Scores(4)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| Google-Proof Q&A | 35.9 | diamond | research |
| HellaSwag | 85.1 | 10-shot | research |
| HumanEval | 45.1 | pass@1 | research |
| Massive Multitask Language Understanding | 63.5 | 5-shot | research |
Rankings
Compare
All comparisons →Llama 2 7B vs Qwen2 7B InstructLlama 2 7B vs ShieldGemma 9BLlama 2 7B vs Dracarys Llama 3.1 70B InstructLlama 2 7B vs Gemma 2 9B SahabatAI InstructLlama 2 7B vs Llama 3 Taiwan 70B InstructLlama 2 7B vs Llama 3 Swallow 70B InstructLlama 2 7B vs Llama 3.1 Swallow 8B InstructLlama 2 7B vs Bielik 11B v2.6 InstructLlama 2 7B vs Sarvam-M Multilingual HybridLlama 2 7B vs Teuken 7B InstructLlama 2 7B vs Italia 10B InstructLlama 2 7B vs Colosseum 355B InstructLlama 2 7B vs Stockmark 2 100B InstructLlama 2 7B vs Seed-OSS 36B InstructLlama 2 7B vs Marin 8B InstructLlama 2 7B vs Granite Guardian 3.0 8B
