Gemma 7B Instruct
gemma-7b-it
About
Gemma 7B Instruct is a cutting-edge large language model developed by Google DeepMind, boasting 7 billion parameters. As part of the Gemma family, it benefits from the advanced research underpinning Google's Gemini models. This model is optimized for text generation tasks, excelling in areas like question answering and summarization, and it is finely tuned to follow instructions effectively. Despite its compact size, Gemma 7B Instruct performs impressively on benchmarks, making it versatile for deployment across various hardware platforms, from laptops to cloud infrastructure. Moreover, it is open-source, with accessible weights and incorporates responsible AI practices, such as data filtering and human feedback, to ensure safe and ethical use.
Gemma 7B Instruct has a 8K-token context window.
Gemma 7B Instruct input tokens at $0.05/1M, output at $0.25/1M.
Capabilities
Providers(8)
Compare all →| Provider | Input (per 1M) | Output (per 1M) | Type | |
|---|---|---|---|---|
| NVIDIA NIM | — | — | Provisioned | |
| Fireworks AI | $0.20 | $0.20 | Provisioned | |
| Together AI | $0.2 | $0.2 | Serverless | |
| GCP Vertex AI | $0.10 | $0.30 | Serverless | |
| Cloudflare Workers AI | — | — | Serverless | |
| Alibaba Cloud PAI-EAS | — | — | Serverless | |
| Lepton AI API | $0.07 | $0.07 | Serverless | |
| Replicate API | $0.05 | $0.25 | Serverless |
Benchmark Scores(5)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| Google-Proof Q&A | 50.8 | diamond | research |
| HellaSwag | 89.2 | 10-shot | research |
| HumanEval | 70.1 | pass@1 | research |
| Massive Multitask Language Understanding | 75.3 | 5-shot | research |
| Instruction-Following Evaluation | 42.6 | v2 | https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard |
