전체 검색

AI 모델 2119

• hubert-large-superb-er↗

  superb

  The base model is hubert-large-ll60k, which is pretrained on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz. Emotion Recognition (ER) predicts an emotion class for each utterance. The most widely used ER dataset IEMOCAP is adopted, and we follow the conventional evaluation protocol: we drop the unbalanced emotion classes to leave the final four classes with a similar amount of data points and cross-validate on five folds of the standard splits. For the original model's training and evaluation instructions refer to the S3PRL downstream task README.

• diar-streaming-sortformer-4spk-v2-gguf↗

  vibe-app

  A GGUF build of `nvidia/diar_streaming_sortformer_4spk-v2`, mirrored here so Vibe has a download source it controls. Converted from the original `.nemo` checkpoint with NVIDIA's own converter (NeMo-Speech.cpp, Apache-2.0), not from an ONNX export. The result matches NVIDIA's published GGUF tensor-for-tensor: 971 tensors, same names, same shapes. Only F32/F16/Q8_0 are safe for this model. The k-quant tiers are not: the speaker-cache compression makes discrete near-tie decisions, and k-quant weight error can flip one and permute speaker labels mid-stream.

• ltx-2.3-mlx-q4↗

  dgrauet

  Int4 quantization (group_size 64, transformer block Linear weights only) of dgrauet/ltx-2.3-mlx, the MLX conversion of Lightricks/LTX-2.3. These weights are a derivative work and are distributed under the same terms as the model they were converted from. A verbatim copy ships with them as `LICENSE`, and the upstream text is at https://github.com/Lightricks/LTX-2/blob/main/LICENSE-2. Use of these weights is subject to it, including any restrictions it attaches. These weights can be used with ltx-2-mlx, a native MLX inference pipeline for LTX-2.3 on Apple Silicon:

• Diplodocus-preview-GGUF↗

  OsaurusAI

  **Diplodocus preview 4**, the Osaurus assistant for finance, documents, spreadsheets and tool-assisted work, built on IFM/K2-Horizon-7B and trained on Osaurus' own workspace tools (workbooks and documents edited in place, the built-in `calculate` tool, reasoning on and off). This is the **GGUF build for llama.cpp** in three calibrated sizes: Using Osaurus on a Mac? Use the MLX bundle `OsaurusAI/Diplodocus-preview-JANG_6M` instead. Same weights, same template, same reasoning toggle. **Requires llama.cpp with K2 Horizon support** (ggml-org/llama.cpp#29535, merged 2026-10-06). Older builds, and apps that bundle an older llama.cpp, will not load the `k2-horizon` architecture.

• TwIL-LM3↗

  webAI-Official

  A 3B reasoning model for **formal logic** tasks, built from `HuggingFaceTB/SmolLM3-3B` through LoRA supervised fine-tuning, checkpoint fusion, WiSE-FT weight interpolation, and entropy-weighted GRPO reinforcement learning. It improves in-domain formal-logic performance by **+26% relative** over its base model (macro gate 0.336 → 0.422) **and improves held-out benchmark performance at the same time** (+0.022 core average). It is the only arm in this project that gains on both tracks, which is why it is the recommended release of the pair. * **Gains on both tracks at once** — the only arm in this project that does. In-domain macro gate 0.336 → 0.422, and the held-out 10-dataset macro 0.7193 → 0.7339 rather than the usual collapse that follows task-specific fine-tuning. * **Beats every arm up to and including LFM2.5-8B-A1B** — roughly three times its parameter count — on all six Track A objective lanes and all four summary rows, not on average alone. * **Competitive with 8B on strict scoring.** On strict-7, which gives no loose-match credit anywhere, it sits 0.012 behind Qwen3-8B (0.1971 against 0.2093) at 2.6x fewer parameters, and ahead of it on Lean formalisation (token-F1 0.5869 against 0.4022) and semantic parsing (0.4416 against 0.4257). * **Structured formal output.** Tuned for the objects rather than the prose: FOL translation, entailment labels, semantic parses, Lean statements and Lean proof critique. * **The most efficient arm measured, at any scale.** 482-token Track B generations and 32.9 completed answers per second — about eight times gpt-oss-120b's rate — because it answers short rather than because it decodes unusually fast. * **Lowest maths-corpus perplexity of any released arm in the table** (3.8229), including Qwen3-8B at 4.0083. * **Runs anywhere.** 3.08B parameters in bf16, with Q4\_K\_M GGUF at 1.78 GiB for CPU or 4 GB of VRAM.

• mask2former-swin-large-coco-instance↗

  facebook

  Mask2Former model trained on COCO instance segmentation (large-sized version, Swin backbone). It was introduced in the paper Masked-attention Mask Transformer for Universal Image Segmentation and first released in this repository. Disclaimer: The team releasing Mask2Former did not write a model card for this model so this model card has been written by the Hugging Face team. Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding labels. Hence, all 3 tasks are treated as if they were instance segmentation. Mask2Former outperforms the previous SOTA, MaskFormer both in terms of performance an efficiency by (i) replacing the pixel decoder with a more advanced multi-scale deformable attention Transformer, (ii) adopting a Transformer decoder with masked attention to boost performance without without introducing additional computation and (iii) improving training efficiency by calculating the loss on subsampled points instead of whole masks.

• leosamsHelloworldXL_helloworldXL60↗

  misri

• GLM-OCR↗

  unsloth

  GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture. It introduces Multi-Token Prediction (MTP) loss and stable full-task reinforcement learning to improve training efficiency, recognition accuracy, and generalization. The model integrates the CogViT visual encoder pre-trained on large-scale image–text data, a lightweight cross-modal connector with efficient token downsampling, and a GLM-0.5B language decoder. Combined with a two-stage pipeline of layout analysis and parallel recognition based on PP-DocLayout-V3, GLM-OCR delivers robust and high-quality OCR performance across diverse document layouts. For speed, we compared different OCR methods under identical hardware and testing conditions (single replica, single concurrency), evaluating their performance in parsing and exporting Markdown files from both image and PDF inputs. Results show GLM-OCR achieves a throughput of 1.86 pages/second for PDF documents and 0.67 images/second for images, significantly outperforming comparable models. 2. **Information Extraction** – extract structured information from documents. Prompts must follow a strict JSON schema. For example, to extract personal ID information:

• spark-s1-4b-v6-GGUF↗

  abhishek085

  GGUF builds of `abhishek085/spark-s1-4b-v6` for **llama.cpp**, **Ollama**, LM Studio, Jan and other GGUF runtimes. Part of Open Spark Jev, an open-source project of the Nokast AI community. > **This is not a chat model.** `spark-s1` is a System-1 *decision* model: given a state and a question with a fixed menu of options, the > answer is the probability distribution over the option letters at the **first** generated token. Chatting with it (`ollama run ...`) only > ever produces a single letter. Use it through the logprob recipe below or through the Open Spark Jev gateway. Measured on 200 shuffled rows of the project's locked held-out split (`v5_test_locked`), llama.cpp `llama-server` (CUDA, build `38a5b42`), `/v1/completions` with `top_logprobs=20`, calibrated temperature applied client-side. Ollama 0.40.2 with the Q8_0 file gave the same 99.5% / 0.900. This is a parity check against the HF model, not a new benchmark; the model's own evaluation is on the base model card.

• Quen32↗

  AlSamCur123

  **Example usage**: - For text only LLMs: `llama-cli -hf AlSamCur123/Quen32 --jinja` - For multimodal models: `llama-mtmd-cli -hf AlSamCur123/Quen32 --jinja`