Gemini 1.5 flash
5
About
Lightweight, fast and cost-efficient while featuring multimodal reasoning and a breakthrough long context window of up to one million tokens.
Percs
High Accuracy
Very Intelligent
High Speed
Multilingual
Settings
Temperature- Value that controls the degree of randomness in token selection. Lower temperatures are good for prompts that require a less open-ended or creative response, while higher temperatures can lead to more diverse or creative results.
Top P- Tokens are selected from the most to least probable until the sum of their probabilities equals this value. Use a lower value for less random responses and a higher value for more random responses.
Top K- For each token selection step, the top_k tokens with the highest probabilities are sampled. Then tokens are further filtered based on top_p with the final token selected using temperature sampling. Use a lower number for less random responses and a higher number for more random responses.
Context capacity- Amount of input tokens passed to the model
Max Tokens- Size of an output