Llama 2 70B
About
Llama 2 70B is a state-of-the-art generative text model developed by Meta, featuring 70 billion parameters and optimized for dialogue applications. It utilizes an advanced transformer architecture and has been fine-tuned using supervised learning and RLHF. Pretrained on 2 trillion tokens from diverse public sources, it outperforms many open-source chat models and competes with popular closed-source models in terms of helpfulness and safety. The model is designed for commercial and research applications in English, focusing on assistant-like chat functionalities. It accepts text input and generates text output, making it suitable for various natural language processing tasks .
Capabilities
VisionMultimodalReasoningFunction CallingTool UseJSON ModeCode Execution
Providers(1)
| Provider | Input (per 1M) | Output (per 1M) | Type | |
|---|---|---|---|---|
| Fireworks AI | $0.9 | $0.9 | Serverless |
Benchmark Scores(4)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| Google-Proof Q&A | 39.1 | diamond | Open LLM Leaderboard |
| HellaSwag | 88.2 | 10-shot | Open LLM Leaderboard |
| HumanEval | 56.2 | pass@1 | Open LLM Leaderboard |
| Massive Multitask Language Understanding | 68.9 | 5-shot | Open LLM Leaderboard |
