全站搜索
AI 模型 449
- wav2vec2-french-phonemizer-v2↗
Cnam-LMSSC
This version fixes the absence of the voiced labial-palatal approximant **ɥ**. The original Cnam-LMSSC/wav2vec2-french-phonemizer never transcribes the pronunciation of the voiced labial–palatal approximant with /ɥ/ and instead incorrectly replaces it with the sequence /yi/. This created issues for phonetic accuracy and linguistic analysis. Words like "nuit" or "huit" are pronounced with \ɥ\ and not with \yi\ For Text-to-Speech (TTS) task, substituting \ɥ\ with \yi\ results in unnatural prosody. Fine-tuned facebook/wav2vec2-base-fr-voxpopuli-v2 for **French speech-to-phoneme** (without language model) using the train and validation splits of Common Voice v13. As this model is specifically trained for a speech-to-phoneme task, the output is sequence of IPA-encoded words, without punctuation. If you don't read the phonetic alphabet fluently, you can use this excellent IPA reader website to convert the transcript back to audio synthetic speech in order to check the quality of the phonetic transcription.
- Meta-Llama-3-8B-Instruct-GGUF↗
QuantFactory
This is quantized version of meta-llama/Meta-Llama-3-8B-Instruct created using llama.cpp Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety. **Variations** Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.
- PP-Chart2Table↗
PaddlePaddle
PP-Chart2Table is a SOTA multimodal model developed by the PaddlePaddle team, specializing in chart parsing for both Chinese and English. Its high performance is driven by a novel "Shuffled Chart Data Retrieval" training task, which, combined with a refined token masking strategy, significantly improves its efficiency in converting charts to data tables. The model is further strengthened by an advanced data synthesis pipeline that uses high-quality seed data, RAG, and LLMs persona design to create a richer, more diverse training set. To address the challenge of large-scale unlabeled, out-of-distribution (OOD) data, the team implemented a two-stage distillation process, ensuring robust adaptability and generalization on real-world data. In-house benchmarks demonstrate that PP-Chart2Table not only outperforms models of a similar scale but also achieves performance on par with 7-billion parameter Vision Language Models (VLMs) in critical application scenarios. You can integrate the model inference of PP-Chart2Table into your project. Before running the following code, please download the sample image to your local machine. The ability of a single model is limited. But the pipeline consists of several models can provide more capacity to resolve difficult problems in real-world scenarios.
- animatediff-motion-adapter-v1-5-2↗
guoyww
AnimateDiff is a method that allows you to create videos using pre-existing Stable Diffusion Text to Image models. It achieves this by inserting motion module layers into a frozen text to image model and training it on video clips to extract a motion prior. These motion modules are applied after the ResNet and Attention blocks in the Stable Diffusion UNet. Their purpose is to introduce coherent motion across image frames. To support these modules we introduce the concepts of a MotionAdapter and UNetMotionModel. These serve as a convenient way to use these motion modules with existing Stable Diffusion models. The following example demonstrates how you can utilize the motion modules with an existing Stable Diffusion text to image model.
- Classic-Painting-Z-Image-Turbo-LoRA↗
renderartist
Immerse your images in the rich textures and timeless beauty of art history with Classic Painting Z. This LoRA has been trained on a curated selection of public domain masterpieces from the Art Institute of Chicago's esteemed collection, capturing the subtle nuances and defining characteristics of early paintings. Trained with ai-toolkit, this model excels at reproducing the finest of details: from delicate brushwork and authentic canvas textures to the dramatic interplay of light and shadow that defined an era. You'll notice sharp textures, realistic brushwork, and meticulous attention to detail. Portraits: Generate portraits with the gravitas and emotional depth of the Old Masters. Lush Landscapes: Create sweeping vistas with a sense of romanticism and composition. Intricate Still Life: Render objects with a sense of realism and painterly detail. Surreal Concepts: Blend the impossible with the classical for truly unique imagery. v1 - Z-Image Turbo LoRA trained at 1,750 steps.
- afro-xlmr-base↗
Davlan
AfroXLMR-base was created by MLM adaptation of XLM-R-base model on 17 African languages (Afrikaans, Amharic, Hausa, Igbo, Malagasy, Chichewa, Oromo, Naija, Kinyarwanda, Kirundi, Shona, Somali, Sesotho, Swahili, isiXhosa, Yoruba, and isiZulu) covering the major African language families and 3 high-resource languages (Arabic, French, and English). language| XLM-R-miniLM| XLM-R-base |XLM-R-large| afro-xlmr-base | afro-xlmr-small | afro-xlmr-mini -|-|-|-|-|-|- amh |69.5|70.6|76.2|76.1|70.1|69.7 hau |74.5|89.5|90.5|91.2|91.4|87.7 ibo |81.9|84.8|84.1|87.4|86.6|83.5 kin |68.6|73.3|73.8|78.0|77.5|74.1 lug |64.7|79.7|81.6|82.9|83.2|77.4 luo |11.7|74.9|73.6|75.1|75.4|17.5 pcm |83.2|87.3|89.0|89.6|89.0|85.5 swa |86.3|87.4|89.4|88.6|88.7|86.0 wol |51.7|63.9|67.9|67.4|65.9|59.0 yor |72.0|78.3|78.9|82.1|81.3|75.1
- persian-embeddings↗
heydariAI
This model is a fine-tuned version of xlm-roberta-base, specifically trained on a massive corpus of Persian data to create high-quality contextual embeddings for Persian sentences and paragraphs. It is designed to perform exceptionally well on tasks such as semantic search, clustering, and contextual similarity for Persian text, while also supporting multilingual tasks in English and Persian. The fine-tuning process focused on adapting the pre-trained multilingual XLM-RoBERTa model to better capture Persian linguistic nuances, making it highly effective for tasks requiring embeddings tailored to the Persian language. Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
- Hemmingway-1-heretic-GGUF↗
Abiray
This repository contains static GGUF quantizations of **Hemmingway-1-heretic**, created by applying the arelath/Hemmingway-1-heretic-adapter to Altworld/Hemmingway-1 (a 27B model built on Qwen3.8-27B) and quantizing for local inference with `llama.cpp`. Hemmingway-1 is tuned specifically to write like a real person—skipping preambles, lecture notes, and corporate filler. This **heretic** version decensors the weights via targeted representation abliteration using Heretic v2.0.0, reducing refusals to near-zero while preserving high-EQ conversational voice. **License:** Governed by the original model's license terms: CC BY-NC 4.0 (Free for personal and non-commercial research use; commercial usage requires agreement with Altworld).
- Huihui-gemma-4-E4B-it-qat-q4_0-unquantized-abliterated-GGUF↗
huihui-ai
library_name: transformers license: apache-2.0 license_link: https://ai.google.dev/gemma/docs/gemma_4_license pipeline_tag: any-to-any base_model: - google/gemma-4-E4B-it-qat-q4_0-unquantized tags: - abliterated - uncensored --- This is an uncensored version of google/gemma-4-E4B-it-qat-q4_0-unquantized 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. Please use the latest version of ollama
- Huihui-Qwen3.8-27B-abliterated-GGUF↗
Didkk
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.**