全站搜索

AI 模型 2119

• MiniMax-M3.1-Flash-VQ-GGUF↗

  Baekpica

  > [!WARNING] > **Problems or odd output?** Post them in the > Community tab, even as > rough notes. The prompt, sampling settings and runtime commit help most. **MiniMax's 428B native multimodal MoE with its full 1,048,576-token context, its sparse attention, its vision/video tower and its DSpark draft head, sized for one 128 GB DGX Spark.** The 236 GB checkpoint (NVFP4 experts, MXFP8 attention) becomes **115.5 GB** of GGUF parts, of which **111.3 GB (103.7 GiB) stay resident**; the BF16 token table and the vision tower are read from SSD, and the attention K/V of a long session lives on SSD, addressed block by block by the model's own MSA indexer. > **Runtime support, 2026-10-24:** runs on one DGX Spark with the ds4-dfm-rs `minimax_m3_vq` family > (merged PR #110): text, images and video, the DSpark draft head and the native context. > **Performance, 2026-10-29:** matched 2K–64K Prefill **1,001.85 → 1,020.29 tok/s (+1.84%)**; > the last 2K at 64K reaches **990.08 tok/s (+2.87%)**, using the runtime changes in > PR #126 (conditions and Decode limits below). > The historical 1,048,319-token prompt prefilled at 580 tok/s and > decoded. Converted 2026-10-23: 61 independent GGUF parts (115,526,325,376 bytes), every payload > hash in `tensor-manifest.json`, all 89,729 source tensors accounted for; codebooks fitted with > calibration statistics from 4.18M tokens (text, images and video) run through the original > checkpoint. **Measured against the original, teacher-forced on held-out chats: KL 0.150 and the > same next token 88.2% of the time on assistant turns** (the original batched differently: KL > 0.003). The memory and kernel budgets below are the design computed from exact byte layouts.

• HunyuanVideo-gguf↗

  city96

  As this is a quantized model not a finetune, all the same restrictions/original license terms still apply. Place model files in `ComfyUI/models/unet` - see the GitHub readme for further install instructions.

• MiniCPM5-2B↗

  openbmb

  MiniCPM Tech Report | MiniCPM Wiki(Chinese) | GitHub Repo | UltraData | Online Demo We are releasing **MiniCPM5-2B**, the second model in the **MiniCPM5** series, following MiniCPM5-1B. It is a dense 2B Transformer that scales up the same training recipe, built for on-device, local deployment, and resource-constrained scenarios, reaching 2B-class open-source SOTA. 🏆 **2B-class open-source SOTA**: compared with strong open-source models of similar size, MiniCPM5-2B achieves SOTA performance within this comparison set. It remains competitive with 4B-class models overall, while showing its advantages over models of comparable size in coding, mathematics, long-context understanding, tool use, and agentic tasks.

• stable-diffusion-v1-5↗

  stable-diffusion-v1-5

  Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input. For more information about how Stable Diffusion functions, please have a look at 🤗's Stable Diffusion blog. The **Stable-Diffusion-v1-5** checkpoint was initialized with the weights of the Stable-Diffusion-v1-2 checkpoint and subsequently fine-tuned on 595k steps at resolution 512x512 on "laion-aesthetics v2 5+" and 10% dropping of the text-conditioning to improve classifier-free guidance sampling. You can use this both with the 🧨Diffusers library and RunwayML GitHub repository ( now deprecated ), ComfyUI, Automatic1111, SD.Next, InvokeAI .

• StartLux-Decision-v1-27B-Q8_0-GGUF↗

  startlux-models

  StartLux-Decision-v1-27B in Q8_0 (8-bit) as a GGUF file for llama.cpp. The decision server in this repository turns it into the same typed decisions, with a probability for every option, as the original model. "Same decision" is the share of the 231 public JevBench items on which the file picks the same answer as the original weights run through the `startlux_decision` package, with the same prompts, readout and temperatures. Q8_0 and Q4_K_M are llama.cpp's standard quantizations of BF16, without an importance matrix. `-ngl 99` puts every layer on the GPU (CUDA or Metal); leave it out on a CPU-only machine. llama.cpp has to be recent enough for this model (build b10454 or newer).

• MiniMax-H3-PTD-RefAsymOPD-LoRAs↗

  taobao-content-ai

  A **few-step** Ref2VA (reference-image → video + audio) accelerator for MiniMax-H3, combining **PTD (Parametric Trajectory Distillation)** with **RefAsymOPD** — Reference-Asymmetric On-Policy Distillation. We release an **8-step** and a **6-step** variant. It improves **background plausibility, sharpness and realism** over plain PTD at the same step count. At inference each checkpoint is **structurally identical to a plain PTD LoRA**: one independent low-rank adapter per inference step, applied on top of the per-interval output heads introduced by Parallel Decoding Distillation (PDD). The 8-step variant runs in **8** transformer evaluations, the 6-step in **6**, needing no extra input and adding no cost over plain PTD.

• mms-tts-kin↗

  facebook

  This model is part of Facebook's Massively Multilingual Speech project, aiming to provide speech technology across a diverse range of languages. You can find more details about the supported languages and their ISO 639-3 codes in the MMS Language Coverage Overview, and see all MMS-TTS checkpoints on the Hugging Face Hub: facebook/mms-tts. VITS (**V**ariational **I**nference with adversarial learning for end-to-end **T**ext-to-**S**peech) is an end-to-end speech synthesis model that predicts a speech waveform conditional on an input text sequence. It is a conditional variational autoencoder (VAE) comprised of a posterior encoder, decoder, and conditional prior. A set of spectrogram-based acoustic features are predicted by the flow-based module, which is formed of a Transformer-based text encoder and multiple coupling layers. The spectrogram is decoded using a stack of transposed convolutional layers, much in the same style as the HiFi-GAN vocoder. Motivated by the one-to-many nature of the TTS problem, where the same text input can be spoken in multiple ways, the model also includes a stochastic duration predictor, which allows the model to synthesise speech with different rhythms from the same input text.

• Qwen3.8-Flash-Next-DS4-Q4↗

  ivanfioravanti

  DS4 quantization of Qwen/Qwen3.8-Flash-Next, built from the official BF16 checkpoint at revision `de4b8e4d43b917e7706784d8bb445c9af86a3540` with an importance-matrix calibrated Q4_K routed-expert recipe. The current release is the **qwen4exp-schema** structure: standard llama.cpp GGUF tensor naming that the DS4 engine (Metal graph) loads directly, with the 51B-value PLE n-gram table kept in the external sidecar so it never has to be memory-resident. The main GGUF includes the 48 trunk layers and one **embedded MTP block**. This is the only model version distributed here: use the same file for ordinary decoding or enable speculative decoding with `--mtp`. The external PLE table is required in both cases.

• 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

• wav2vec2-xls-r-300m-bengali↗

  arijitx

  This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the OPENSLR_SLR53 - bengali dataset. It achieves the following results on the evaluation set. With 5 gram language model trained on 30M sentences randomly chosen from AI4Bharat IndicCorp dataset : - WER: 0.15322879016421437 - CER: 0.03413696666806267 Note : 5% of a total 10935 samples have been used for evaluation. Evaluation set has 10935 examples which was not part of training training was done on first 95% and eval was done on last 5%. Training was stopped after 180k steps. Output predictions are available under files section.