全站搜索
AI 模型 449
- next-scene-qwen-image-lora-2509↗
lovis93
**What's New in V2:** - 🎯 **Trained on higher quality data** for significantly improved results - 💪 **Better command responsiveness** - the model follows your prompts more accurately - 🖼️ **Fixed black bar artifacts** - no more unwanted black borders on generated images - ⚡ **Overall enhanced performance** - smoother transitions and better cinematic flow **next-scene-qwen-image-lora-2509** is a **LoRA adapter fine-tuned on Qwen-Image-Edit (build 2509)**, purpose-built to generate cinematic image sequences with natural visual progression from frame to frame. This model enables Qwen Image Edit to think like a film director—understanding camera dynamics, visual composition, and narrative continuity to create shots that flow seamlessly into one another.
- wavlm-base-plus-sv↗
Microsoft
The model was pretrained on 16kHz sampled speech audio with utterance and speaker contrastive loss. When using the model, make sure that your speech input is also sampled at 16kHz. **Note**: This model does not have a tokenizer as it was pretrained on audio alone. In order to use this model **speech recognition**, a tokenizer should be created and the model should be fine-tuned on labeled text data. Check out this blog for more in-detail explanation of how to fine-tune the model. - 60,000 hours of Libri-Light - 10,000 hours of GigaSpeech - 24,000 hours of VoxPopuli
- Sakura-MiniMax-H3-Uncensored-GGUF↗
webmp3
> For adults only; you are responsible for what you generate and for the laws that apply to you. The language weights come from a model whose refusals were removed and whose text generation breaks down on harmful prompts (see below); what this changes in the video we measured only for six non-explicit prompts (see below). Do not use it to depict minors in any sexual or abusive context, or to create sexual or defamatory images of real persons without their consent. Do not put it into a public service without your own moderation. The **text encoder** of MiniMax-H3 (the first 50 language layers of Qwen3-VL-32B plus its vision tower, passed to the video model with `--llm`) with the language weights of an **abliterated (uncensored)** Qwen3-VL-32B-Instruct, as GGUF for stable-diffusion.cpp. Independent work, not made, reviewed or endorsed by MiniMax, Comfy-Org, Qwen / Alibaba or llmfan46. - The text encoder shipped inside MiniMax-H3 is **the unmodified Qwen3-VL-32B-Instruct**: the sha256 of all 14 `text_encoder` shards of `MiniMaxAI/MiniMax-H3` equal those of `Qwen/Qwen3-VL-32B-Instruct`. MiniMax-H3 uses it truncated to 50 language layers and without the final language-model norm. - We built the encoder from an **abliterated checkpoint of that model made by a community member** (llmfan46's abliterated Qwen3-VL-32B-Instruct, Apache-2.0, revision `c44b949b30d111666a5ed9851c5cd633ed39b070`; sha256 of both shards checked against the Hub). **We did not run the ablation ourselves** for this repository. - Tensors were copied one by one into the layout of the Comfy-Org H3 encoder file (902 tensors; names, dtypes and shapes equal that file; the 14 layers 50 to 63, the final norm and the output head are dropped), then converted with `sd-cli -M convert`.
- IndicBERTv2-MLM-only↗
ai4bharat
A multilingual language model trained on IndicCorp v2 and evaluated on IndicXTREME benchmark. The model has 278M parameters and is available in 23 Indic languages and English. The models are trained with various objectives and datasets. The list of models are as follows: - IndicBERT-MLM [Model] - A vanilla BERT style model trained on IndicCorp v2 with the MLM objective - +Samanantar [Model] - TLM as an additional objective with Samanantar Parallel Corpus [Paper] | [Dataset] - +Back-Translation [Model] - TLM as an additional objective by translating the Indic parts of IndicCorp v2 dataset into English w/ IndicTrans model [Model] - IndicBERT-SS [Model] - To encourage better lexical sharing among languages we convert the scripts from Indic languages to Devanagari and train a BERT style model with the MLM objective Fine-tuning scripts are based on transformers library. Create a new conda environment and set it up as follows:
- Qwen2.5-VL-3B-Instruct-abliterated↗
huihui-ai
--- license_name: qwen-research license_link: https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/LICENSE language: - en pipeline_tag: image-text-to-text tags: - multimodal - abliterated - uncensored library_name: transformers base_model: - Qwen/Qwen2.5-VL-3B-Instruct --- This is an uncensored version of Qwen/Qwen2.5-VL-3B-Instruct created with abliteration (see remove-refusals-with-transformers to know more about it). You can use huihui_ai/qwen2.5-vl-abliterated:3b directly,
- prefect-illustrious-xl-v3-sdxl↗
John6666
Original model is here. This model created by Goofy_Ai.
- Huihui-Qwen3.8-27B-abliterated-GGUF↗
Sh200126
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-Ternary** series come from prism-ml/Ternary-Bonsai-2-27B-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. The size after conversion may differ from the original GGUF (Some of the weights are converted from PTQ1 to Q2_K or Q3_K.). This is just a test/validation. The ternary hybrid-attention kernels live in the PrismML-Eng/llama.cpp fork. **Stock llama.cpp will not run these files.**
- wavlm-base↗
Microsoft
The base model pretrained on 16kHz sampled speech audio. When using the model, make sure that your speech input is also sampled at 16kHz. **Note**: This model does not have a tokenizer as it was pretrained on audio alone. In order to use this model **speech recognition**, a tokenizer should be created and the model should be fine-tuned on labeled text data. Check out this blog for more in-detail explanation of how to fine-tune the model. The model was pre-trained on 960h of Librispeech.
- dolphin-2.6-mixtral-8x7b↗
dphn
This Dolphin is *really good* at coding, I trained with a lot of coding data. It is *very* obedient but it is not DPO tuned - so you still might need to encourage it in the system prompt as I show in the below examples. New in 2.6 - Fixed a training configuration issue that improved the quality a lot - Due to popular demand, added back samantha-based empathy data - Replaced synthia and pure-dove with Capybara This model is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly.
- colpali-v1.3↗
vidore
ColPali is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs) to efficiently index documents from their visual features. It is a PaliGemma-3B extension that generates ColBERT- style multi-vector representations of text and images. It was introduced in the paper ColPali: Efficient Document Retrieval with Vision Language Models and first released in this repository Compared to `vidore/colpali`, this version is trained with right padding for queries to fix unwanted tokens in the query encoding. It also stems from the fixed `vidore/colpaligemma-3b-pt-448-base` to guarantee deterministic projection layer initialization. It was trained for 5 epochs, with in-batch negatives and hard mined negatives and a warmup of 1000 steps (10x longer) to help reduce non-english language collapse. This model is built iteratively starting from an off-the-shelf SigLIP model. We finetuned it to create BiSigLIP and fed the patch-embeddings output by SigLIP to an LLM, PaliGemma-3B to create BiPali.