全站搜索
AI 模型 449
- Huihui-Qwen3.8-27B-abliterated↗
huihui-ai
This is an uncensored version of Qwen/Qwen3.8-27B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. Only layers **18 to 51** have been ablated (Previously, The first 15 layers were retained without ablation), while the other layers remain unablated. This helps retain more of the original model’s performance. MTP and visual has not been modified. The first 15 layers were retained without ablation. MTP and visual has not been modified.
- Dia-1.6B-0626↗
nari-labs
Dia is a 1.6B parameter text to speech model created by Nari Labs. It was pushed to the Hub using the PytorchModelHubMixin integration. Dia **directly generates highly realistic dialogue from a transcript**. You can condition the output on audio, enabling emotion and tone control. The model can also produce nonverbal communications like laughter, coughing, clearing throat, etc. To accelerate research, we are providing access to pretrained model checkpoints and inference code. The model weights are hosted on Hugging Face. The model only supports English generation at the moment.
- gemma-3-12b-it-heretic-v2↗
DreamFast
An abliterated version of Google's Gemma 3 12B IT created using Heretic v1.3.0. This model has reduced refusals while maintaining model quality, making it suitable as an uncensored text encoder for video generation models like LTX-2. Available in five quantization formats for ComfyUI - FP8, INT8 (ConvRot row-wise), INT4 (W4A4 ConvRot), NVFP4, and MXFP8 - all produced with SVD-guided learned rounding for maximum fidelity, covering everything from Ada GPUs to Blackwell. You can see the docker, scripts and configurations used to make these files on Heretic Docker Github.
- potion-base-4M↗
minishlab
This Model2Vec model is pre-trained using Tokenlearn. It is a distilled version of the baai/bge-base-en-v1.5 Sentence Transformer. It uses static embeddings, allowing text embeddings to be computed orders of magnitude faster on both GPU and CPU. It is designed for applications where computational resources are limited or where real-time performance is critical. Model2vec creates a small, static model that outperforms other static embedding models by a large margin on all tasks on MTEB. This model is pre-trained using Tokenlearn. It's created using the following steps: - Distillation: first, a model is distilled from a sentence transformer model using Model2Vec. - Training data creation: the sentence transformer model is used to create training data by creating mean output embeddings on a large corpus. - Training: the distilled model is trained on the training data using Tokenlearn. - Post-training re-regularization: after training, the model is re-regularized by weighting the tokens based on their frequency, applying PCA, and finally applying SIF weighting. The results show that **potion-base-4M** reaches 89.63% of the performance of all-MiniLM-L6-v2 with an average score of 50.01 while being orders of magnitude faster.
- Huihui-Qwable-3.6-27b-abliterated-GGUF↗
huihui-ai
This is an uncensored version of Mia-AiLab/Qwable-3.6-27b created with abliteration. This ablation was performed entirely using llama.cpp's GGUF model, without relying on Transformers, For the specific ablation method, please refer to cvector-generator.
- Huihui-DeepSeek-V4-Flash-0731-abliterated-GGUF↗
huihui-ai
This is an uncensored version of deepseek-ai/DeepSeek-V4-Flash-0731 created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. **Note** These GGUFs support llama.cpp and ds4 and all expert modules were not ablated. Q4 used a stronger ablation intensity than Q2, so the rejection rate was smaller.
- Huihui-Qwen3.8-27B-abliterated-GGUF↗
kcarly
This is an uncensored version of Qwen/Qwen3.8-27B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. The newly added **Huihui-Qwen3.8-27B-abliterated-Underdog-Saluki** series come from ConwayResearch/Underdog-Saluki-27B-1.0 and ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF. Only layers **22 to 52 (0-based indexing)** have been ablated, while the other layers remain unablated. It may come with a small disclaimer warning. Due to ConwayResearch/Underdog-Saluki-27B-1.0 not providing an imatrix file, we will attempt to perform ablation by mixing the GGUF weights of Swift-1.5 and ConwayResearch/Underdog-Saluki-27B-1.0.
- Huihui-Qwen3-VL-4B-Instruct-abliterated↗
huihui-ai
This is an uncensored version of Qwen/Qwen3-VL-4B-Instruct created with abliteration (see remove-refusals-with-transformers to know more about it). **Please update to the latest version of Ollama-v0.12.7.** You can use huihui_ai/qwen3-vl-abliterated:4b-instruct directly,
- mxbai-edge-colbert-v0-17m↗
mixedbread-ai
🍞 Looking for a simple end-to-end retrieval solution? Meet Mixedbread Search , our multi-modal and multi-lingual search solution. This model is a lightweight, 17 million parameter ColBERT with a projection dimension of 48. It is built on top of Ettin-17M, meaning it benefits from all of ModernBERT's architectural efficiencies. Despite this extreme efficiency, it is the best-performer "edge-sized" retriever, outperforming ColBERTv2 and many models with over 10 times more parameters. It can create multi-vector representations for documents of up to 32,000 tokens and is fully compatible with the PyLate library. This model can be used with Sentence Transformers as a multi-vector (ColBERT-style late interaction) retriever via the `MultiVectorEncoder`:
- Qwen3.6-35B-A3B-AutoRound-GGUF↗
sphaela
This repository contains GGUF quantized versions of Qwen/Qwen3.6-35B-A3B created using Intel's AutoRound quantization method. Qwen3.6-35B-A3B is a Mixture-of-Experts (MoE) model with 256 experts and approximately 3.6B active parameters. > **🆕 MTP (Multi-Token Prediction) Support** — All models now include the MTP / NextN head (`blk.40.*` tensors), enabling speculative decoding in compatible runtimes such as recent builds of llama.cpp. Each GGUF has been validated to contain the full set of MTP tensors.