Gemma 2 9B Instruct
gemma-2-9b-it
About
Gemma 2 9B Instruct, developed by Google, is a state-of-the-art large language model based on the advanced Gemini framework. It is a decoder-only transformer model with 9 billion parameters, offering a balance between size and performance. The model is trained on an expansive dataset comprising 8 trillion tokens, including web documents, code, and mathematical text, a notable 30% increase from its predecessor, Gemma 1.1. This allows it to adeptly handle diverse tasks such as question answering, creative writing, coding, and mathematical problem-solving. However, it shares common limitations of large language models, such as potential biases and the risk of generating inaccuracies or outdated information. Notably, Gemma 2 9B Instruct incorporates Grouped-Query Attention (GQA) and uses the GeGLU activation function, and is specifically fine-tuned to follow instructions and participate effectively in multi-turn dialogues.
Gemma 2 9B Instruct has a 8K-token context window.
Gemma 2 9B Instruct input tokens at $0.03/1M, output at $0.09/1M.
Capabilities
Providers(5)
Compare all →| Provider | Input (per 1M) | Output (per 1M) | Type | |
|---|---|---|---|---|
| Fireworks AI | $0.2 | $0.2 | Serverless | |
| NVIDIA NIM | — | — | Provisioned | |
| OpenRouter | $0.03 | $0.09 | Serverless | |
| Chutes AI | $0.1 | $0.3 | Serverless | |
| Replicate API | $0.1 | $0.1 | Serverless |
Benchmark Scores(1)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| Instruction-Following Evaluation | 65.5 | v2 | https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard |
