
gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking
an uncensored version with a reasoning mode
139 posts

an uncensored version with a reasoning mode

an uncensored version of the multimodal model



The youdotcom/reflex-search model is a compact solution for search filtering and source ranking tasks, running entirely on the CPU. It is built upon the text component of the google/embeddinggemma-2 model with 0.27B parameters, stripping away the visual and audio modules to conserve resources.


The google/gemma-4-E2B-it model has been fine-tuned using LoRA to answer research questions based on provided scientific abstracts. It outputs a structured JSON response containing a label (yes, no, or maybe), a brief summary, and the sentence numbers it relies on.

A modification of the base google/gemma-4-31B-it model created through direct weight manipulation without additional training. In this version, the output layer is separated from the input embeddings (tie_word_embeddings: false), and a special vector is added to the end-of-thinking token, which…




Gemma 4 version without refusals





a specialized LoRA adapter for classification and decision-making



NeyroLearn
@neyrolearn
New models from Hugging Face every morning: video, images, LoRAs and LLMs with examples and links.
Most liked on Hugging Face this week
Images · 8.4K
18+Video · 7.2K

Images · 6.2K

Computer vision · 3.5K

Images · 3.1K
18+