Venice: Uncensored (free)

cognitivecomputations/dolphin-mistral-24b-venice-edition:free

JSONStreaming

Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...

Specs

Context

32,768 tokens

Input

text

Output

text

Knowledge cutoff: 2024-04-30

Released: 2025-07

Supported parameters

frequency_penaltymax_tokenspresence_penaltyresponse_formatstopstructured_outputstemperaturetop_ktop_p

Open weights · HuggingFace

13,666 downloads/mo

540 likes

apache-2.0 text-generation

View on HuggingFace →

Use this model →