전체 검색

AI 모델 2119

• maple-preview-gguf↗

  stamsam

• roberta-base-openai-detector↗

  openai-community

  - Model Details - Uses - Risks, Limitations and Biases - Training - Evaluation - Environmental Impact - Technical Specifications - Citation Information - Model Card Authors - How To Get Started With the Model **Model Description:** RoBERTa base OpenAI Detector is the GPT-2 output detector model, obtained by fine-tuning a RoBERTa base model with the outputs of the 1.5B-parameter GPT-2 model. The model can be used to predict if text was generated by a GPT-2 model. This model was released by OpenAI at the same time as OpenAI released the weights of the largest GPT-2 model, the 1.5B parameter version. - **Developed by:** OpenAI, see GitHub Repo and associated paper for full author list - **Model Type:** Fine-tuned transformer-based language model - **Language(s):** English - **License:** MIT - **Related Models:** RoBERTa base, GPT-XL (1.5B parameter version), GPT-Large (the 774M parameter version), GPT-Medium (the 355M parameter version) and GPT-2 (the 124M parameter version) - **Resources for more information:** - Research Paper (see, in particular, the section beginning on page 12 about Automated ML-based detection). - GitHub Repo - OpenAI Blog Post - Explore the detector model here

• bge-m3↗

  unsloth

  In this project, we introduce BGE-M3, which is distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity. - Multi-Functionality: It can simultaneously perform the three common retrieval functionalities of embedding model: dense retrieval, multi-vector retrieval, and sparse retrieval. - Multi-Linguality: It can support more than 100 working languages. - Multi-Granularity: It is able to process inputs of different granularities, spanning from short sentences to long documents of up to 8192 tokens. We recommend to use the following pipeline: hybrid retrieval + re-ranking. - Hybrid retrieval leverages the strengths of various methods, offering higher accuracy and stronger generalization capabilities. A classic example: using both embedding retrieval and the BM25 algorithm. Now, you can try to use BGE-M3, which supports both embedding and sparse retrieval. This allows you to obtain token weights (similar to the BM25) without any additional cost when generate dense embeddings. To use hybrid retrieval, you can refer to Vespa and Milvus. The previous test results were lower because we mistakenly removed the passages that have the same id as the query from the search results. After correcting this mistake, the overall performance of BGE-M3 on MIRACL is higher than the previous results, but the experimental conclusion remains unchanged. The other results are not affected by this mistake. To reproduce the previous lower results, you need to add the `--remove-query` parameter when using `pyserini.search.faiss` or `pyserini.search.lucene` to search the passages.

• chronos-bolt-mini↗

  amazon

  🚀 **Update Feb 14, 2025**: Chronos-Bolt models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. Chronos-Bolt is a family of pretrained time series forecasting models which can be used for zero-shot forecasting. It is based on the T5 encoder-decoder architecture and has been trained on nearly 100 billion time series observations. It chunks the historical time series context into patches of multiple observations, which are then input into the encoder. The decoder then uses these representations to directly generate quantile forecasts across multiple future steps—a method known as direct multi-step forecasting. Chronos-Bolt models are up to 250 times faster and 20 times more memory-efficient than the original Chronos models of the same size. The following plot compares the inference time of Chronos-Bolt against the original Chronos models for forecasting 1024 time series with a context length of 512 observations and a prediction horizon of 64 steps.

• Voxtral-Small-24B-2507-gguf↗

  handy-computer

  GGUF conversions of mistralai/Voxtral-Small-24B-2507 for use with transcribe.cpp. Ported from upstream commit da5b424, pinned 2026-06-05. Validated against the Transformers reference at transcribe.cpp commit dac22fa on 2026-06-05. Offline audio-LLM speech-to-text and speech translation. A Whisper-large-v3 bidirectional audio encoder feeds a 4-frame-group projector (375 audio tokens per 30 s chunk) into a Mistral-Small-24B causal LM (40 layers, GQA 32/8, NEOX RoPE, SwiGLU) via audio-token injection. Takes a 16 kHz mono WAV and produces a transcript via greedy decoding. The larger sibling of Voxtral Mini 3B — same encoder, projector, frontend, and tokenizer, with a scaled-up decoder.

• ZONOS2-GGUF↗

  Zyphra

  GGUF weights for **Zyphra/ZONOS2**, ready to run with **zonos2.cpp** — a standalone ggml/GGUF C++ port of ZONOS2. The **entire pipeline** (ECAPA speaker encoder → MoE backbone → DAC vocoder) runs as native C++ linking only `libggml` + `gguf`: **no Python, no PyTorch, no CUDA-only kernels at inference time.** CPU and CUDA use the same files. ZONOS2 is Zyphra's latest text-to-speech model, trained on more than 6 million hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS providers at low latency with MoE. ZONOS2 excels at high-fidelity and naturalistic voice cloning. **For model details and speech samples, check out our blog.** **A hosted version is available at cloud.zyphra.com/audio-playground.**

• Qwen-Image-2.1-Fun-Acc-LoRAs↗

  alibaba-pai

  We apply Parallel Decoding Distillation (PDD) 1 to Qwen-Image-2.1, enabling efficient text-to-image and instruction-based image editing at **4 NFE**. > [!NOTE] > The editing prompts and reference images are from the Qwen-Image-2.1 (flag) and Viggle's demo examples (woman and cat; person, cat and bird). Use a VideoX-Fun checkout exposing `QwenImage21Pipeline` from `videox_fun.pipeline`. These entries use that pipeline and the same bundled `qwenimage21_pdd.py` / `lora_utils_pdd.py` as the standalone entries;

• minimax-h3-fused-turbo-int8-convrot↗

  cgc-0521

  One 21 GB ComfyUI diffusion-model file that does MiniMax-H3 text/image-to-video **and** reference-to-video in **4 steps**, with a distilled turbo and a motion-smoothing style LoRA already folded into the weights. `diffusion_models/minimax_h3_fused_refdelta_r1024_turbo8_mystic07_int8_convrot.safetensors` -> `ComfyUI/models/diffusion_models/` **Hardware.** The timings below are from a 96 GB card with everything resident. Smaller cards work too: ComfyUI's model management loads and offloads the transformer, text encoder and VAEs as they are needed, so the same graphs run, just slower, and the 21 GB file is the smallest footprint this recipe has. **AMD / ROCm:** the recipe was developed on an AMD box; use patientx's ComfyUI ROCm fork, , which also carries a ROCm build of the SLA attention node.

• Depth-Anything-V2-Large-hf↗

  depth-anything

  Depth Anything V2 is trained from 595K synthetic labeled images and 62M+ real unlabeled images, providing the most capable monocular depth estimation (MDE) model with the following features: - more fine-grained details than Depth Anything V1 - more robust than Depth Anything V1 and SD-based models (e.g., Marigold, Geowizard) - more efficient (10x faster) and more lightweight than SD-based models - impressive fine-tuned performance with our pre-trained models Depth Anything V2 was introduced in the paper of the same name by Lihe Yang et al. It uses the same architecture as the original Depth Anything release, but uses synthetic data and a larger capacity teacher model to achieve much finer and robust depth predictions. The original Depth Anything model was introduced in the paper Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data by Lihe Yang et al., and was first released in this repository. Depth Anything V2 leverages the DPT architecture with a DINOv2 backbone.

• EXAONE-4.0-32B-FP8↗

  furiosa-ai

  This repository contains `LGAI-EXAONE/EXAONE-4.0-32B-FP8` together with a Furiosa Executable Bundle (FXB) for running it on FuriosaAI RNGD with Furiosa-LLM. The same model also runs on other frameworks (such as vLLM, SGLang, and Transformers); for usage with those, see the upstream `LGAI-EXAONE/EXAONE-4.0-32B-FP8` model card. Weights are quantized to **FP8** (static), following the upstream FP8 release, and activations use **dynamic FP8 quantization** at runtime (per-token / per-block). The KV cache stays in 16-bit precision. On RNGD, EXAONE-4.0-32B-FP8 runs with a **tensor-parallel size of 32 PEs**, which maps to **four RNGD cards** (8 PEs per card).