Vigthoria Neural Nexus

Disconnected

LLM MODEL: -

☀️ 🌙

Loading models...

OLLAMA: Initializing...

SERVER: MODEL:

CHECKING CHECKING

Not Connected

ACTIVE MODEL: -

TOKENS: 0

TEMPLATES:

Neural Nexus

FAMILY

SIZE

QUANTIZATION

MAX CONTEXT

TEMPERATURE: 0.7

0.5

1.0

Controls randomness in responses. Higher values produce more creative but potentially less accurate output.

MAX OUTPUT TOKENS:

Maximum number of tokens the model will generate in a response.

CONTEXT LENGTH:

Maximum conversation history tokens to include as context.

Add and manage your own Large Language Model providers. Ensure the API is compatible with OpenAI's chat completions format for best results.

Model Name:

API Endpoint URL:

API Key:

No custom LLMs added yet.