サイト内検索

AI モデル 2119

• MiniMax-H3-Ref2VA-Turbo-INT8-ConvRot↗

  PulpCut

  An optimized MiniMax H3 **Ref2VA** package centered on the omni-reference diffusion transformer, which conditions generation on ordered reference images. It has the lightx2v **turbo step-distillation merged into the weights** and uses the same pruned **INT8 ConvRot** layout as the Comfy-Org release. The primary transformer is a drop-in replacement for `minimax_h3_ref2va_pruned_int8_convrot.safetensors` in any runtime that reads the optimized INT8 layout — including H3ddle, the open-source native macOS app it was built for. The transformer is **not a standalone model**. It needs the rest of the optimized package (Qwen3-VL-32B INT8 text encoder, video/audio VAEs, tokenizer) from Comfy-Org/MiniMax-H3, and the FL2VA transformer alongside it if you also want prompt-only and keyframe generation. `minimax_h3_ref2va_pruned_turbo_int8_convrot_input_major.safetensors` is the H3ddle-optimized form of the primary transformer. All 200 quantized core projections across 50 blocks are stored `[input, output]` instead of `[output, input]`. No tensor is dequantized or numerically changed; scales, ConvRot metadata, reference conditioning, and non-core tensors are preserved.

• lang-id-voxlingua107-ecapa↗

  speechbrain

  This is a spoken language recognition model trained on the VoxLingua107 dataset using SpeechBrain. The model uses the ECAPA-TDNN architecture that has previously been used for speaker recognition. However, it uses more fully connected hidden layers after the embedding layer, and cross-entropy loss was used for training. We observed that this improved the performance of extracted utterance embeddings for downstream tasks. The system is trained with recordings sampled at 16kHz (single channel). The code will automatically normalize your audio (i.e., resampling + mono channel selection) when calling *classify_file* if needed. The model can classify a speech utterance according to the language spoken. It covers 107 different languages ( Abkhazian, Afrikaans, Amharic, Arabic, Assamese, Azerbaijani, Bashkir, Belarusian, Bulgarian, Bengali, Tibetan, Breton, Bosnian, Catalan, Cebuano, Czech, Welsh, Danish, German, Greek, English, Esperanto, Spanish, Estonian, Basque, Persian, Finnish, Faroese, French, Galician, Guarani, Gujarati, Manx, Hausa, Hawaiian, Hindi, Croatian, Haitian, Hungarian, Armenian, Interlingua, Indonesian, Icelandic, Italian, Hebrew, Japanese, Javanese, Georgian, Kazakh, Central Khmer, Kannada, Korean, Latin, Luxembourgish, Lingala, Lao, Lithuanian, Latvian, Malagasy, Maori, Macedonian, Malayalam, Mongolian, Marathi, Malay, Maltese, Burmese, Nepali, Dutch, Norwegian Nynorsk, Norwegian, Occitan, Panjabi, Polish, Pushto, Portuguese, Romanian, Russian, Sanskrit, Scots, Sindhi, Sinhala, Slovak, Slovenian, Shona, Somali, Albanian, Serbian, Sundanese, Swedish, Swahili, Tamil, Telugu, Tajik, Thai, Turkmen, Tagalog, Turkish, Tatar, Ukrainian, Urdu, Uzbek, Vietnamese, Waray, Yiddish, Yoruba, Mandarin Chinese).

• metricgan-plus-voicebank↗

  speechbrain

  This repository provides all the necessary tools to perform enhancement with SpeechBrain. For a better experience we encourage you to learn more about SpeechBrain. The model performance is: The system is trained with recordings sampled at 16kHz (single channel). The code will automatically normalize your audio (i.e., resampling + mono channel selection) when calling *enhance_file* if needed. Make sure your input tensor is compliant with the expected sampling rate if you use *enhance_batch* as in the example. To perform inference on the GPU, add `run_opts={"device":"cuda"}` when calling the `from_hparams` method.

• wavlm-emotion-russian-resd↗

  Aniemore

  Speech emotion recognition for Russian over seven classes: `anger`, `disgust`, `enthusiasm`, `fear`, `happiness`, `neutral`, `sadness`. Fine-tuned from `jonatasgrosman/exp_w2v2t_ru_wavlm_s363` on `Aniemore/resd`. - **Parameters**: 317M · **weights**: 1207 MiB (fp32) - **Input**: 16 kHz mono waveform - **Quantized builds**: `wavlm-emotion-russian-resd-quantized` — INT8, FP8 and INT4, up to 5.8x smaller on disk at the same score

• chronos-t5-tiny↗

  autogluon

  🚀 **Update Feb 14, 2025**: Chronos-Bolt & original Chronos 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. 🚀 **Update Nov 27, 2024**: We have released Chronos-Bolt⚡️ models that are more accurate (5% lower error), up to 250 times faster and 20 times more memory-efficient than the original Chronos models of the same size. Check out the new models here. Chronos is a family of **pretrained time series forecasting models** based on language model architectures. A time series is transformed into a sequence of tokens via scaling and quantization, and a language model is trained on these tokens using the cross-entropy loss. Once trained, probabilistic forecasts are obtained by sampling multiple future trajectories given the historical context. Chronos models have been trained on a large corpus of publicly available time series data, as well as synthetic data generated using Gaussian processes.

• pythia-410m-deduped↗

  EleutherAI

  The *Pythia Scaling Suite* is a collection of models developed to facilitate interpretability research (see paper). It contains two sets of eight models of sizes 70M, 160M, 410M, 1B, 1.4B, 2.8B, 6.9B, and 12B. For each size, there are two models: one trained on the Pile, and one trained on the Pile after the dataset has been globally deduplicated. All 8 model sizes are trained on the exact same data, in the exact same order. We also provide 154 intermediate checkpoints per model, hosted on Hugging Face as branches. The Pythia model suite was designed to promote scientific research on large language models, especially interpretability research. Despite not centering downstream performance as a design goal, we find the models match or exceed the performance of similar and same-sized models, such as those in the OPT and GPT-Neo suites. Previously, we released an early version of the Pythia suite to the public. However, we decided to retrain the model suite to address a few hyperparameter discrepancies. This model card lists the changes ; see appendix B in the Pythia paper for further discussion. We found no difference in benchmark performance between the two Pythia versions. The old models are still available, but we suggest the retrained suite if you are just starting to use Pythia. **This is the current release.**

• BioLORD-2023↗

  FremyCompany

  This model was trained using BioLORD, a new pre-training strategy for producing meaningful representations for clinical sentences and biomedical concepts. State-of-the-art methodologies operate by maximizing the similarity in representation of names referring to the same concept, and preventing collapse through contrastive learning. However, because biomedical names are not always self-explanatory, it sometimes results in non-semantic representations. BioLORD overcomes this issue by grounding its concept representations using definitions, as well as short descriptions derived from a multi-relational knowledge graph consisting of biomedical ontologies. Thanks to this grounding, our model produces more semantic concept representations that match more closely the hierarchical structure of ontologies. BioLORD-2023 establishes a new state of the art for text similarity on both clinical sentences (MedSTS) and biomedical concepts (EHR-Rel-B).

• Hy-Memory-30B-A3B↗

  腾讯

  **Hy-Memory-30B-A3B** is a compact long-term-memory writer model (~3B active parameters) developed by Tencent Hunyuan to execute the write path inside external memory frameworks. It directly replaces the general-purpose LLM inside **Mem0**, **MemOS**, and **Hy-Memory** (covering Chat, Working, and Coding scenarios), deciding what information to retain, how precisely to represent it, and how new evidence should update the persistent memory bank. The model is trained in two stages—Memory On-Policy Distillation (OPD) followed by Attributed Memory Reinforcement Learning—and transfers directly to unseen memory frameworks such as **EverMemOS**. Cross-harness macro-average scores on the fixed 20% benchmark matrix. Each harness score averages six metrics equally; Overall averages the four harnesses equally. EverMemOS is held out from training. Figure 1: Hy-Memory-30B-A3B is trained inside the same deployed harness configurations in both stages. OPD supplies dense teacher supervision on student-written state chains; RL examines the resulting banks, assigns chunk-level credit, and carries the selected bank across windows. In the rollout grid, each cell is the bank after chunk t of rollout i, shaded by its chunk score s_i[t]. Advantages are normalized within each column (dashed: one chunk-level group), so the best rollout can differ from chunk to chunk. The outlined cell is the final bank with the highest sum_t s_i[t], which becomes the parent of the next window.

• Samantha-Qwen2-7B-GGUF↗

  mradermacher

• gemma-4-31B-it-scotoma-2-GGUF↗

  ReadyArt

  --bg:#07090d; --panel:#0b1016; --ink:#edf1f4; --soft:#b0bac5; --dim:#7a8591; --faint:#59636f; --line:rgba(150,178,205,.14); --water:#6fc3d8; --water2:#4e95b5; --ember:#e2a24d; background:var(--bg); color:var(--ink); max-width:940px; margin:0 auto; font-family:system-ui,-apple-system,"Segoe UI",Roboto,Helvetica,Arial,sans-serif; font-size:16px; line-height:1.62; border:1px solid var(--line); overflow:hidden; } font-size:clamp(2.6rem,8.5vw,5.2rem); line-height:.92; text-transform:uppercase;} @supports not (-webkit-text-stroke:1px #fff){#scotoma2 .num2{color:var(--water);}} color:var(--soft); font-weight:400;} /* chart strip */ border-bottom:1px solid var(--line); background:var(--panel);} /* body */ font-weight:700; color:var(--ink);} font-family:ui-monospace,Menlo,monospace; font-size:.78rem; color:var(--water); letter-spacing:.05em; border:1px solid var(--line); padding:.15em .5em; border-radius:2px;} /* signs table */ color:var(--faint); font-weight:600; text-align:left; padding:8px 10px; border-bottom:1px solid var(--line);} font-family:ui-monospace,Menlo,monospace;} vertical-align:top;} white-space:nowrap; text-align:right;} /* presentation */ border-radius:2px; border-bottom:1px solid rgba(226,162,77,.55);} letter-spacing:.16em; text-transform:uppercase; color:var(--faint); margin-bottom:.7em;} padding:14px 18px 15px; margin:.55em 0; font-size:.92rem; line-height:1.68; color:var(--soft);} letter-spacing:.20em; text-transform:uppercase; color:var(--faint); margin-bottom:.55em;} border-radius:2px; border-bottom:1px solid rgba(226,162,77,.55); cursor:help;} font-size:.72rem; letter-spacing:.03em; display:flex; justify-content:space-between; gap:16px; flex-wrap:wrap;} @media (max-width:560px){#scotoma2 .chart{grid-template-columns:repeat(2,1fr);} #scotoma2 .cell:nth-child(2n){border-right:none;} #scotoma2 .masthead,#scotoma2 .body,#scotoma2 .foot{padding-left:22px;padding-right:22px;}} Base gemma-4-31B-it Method γ-fold + DPO Rounds 3 · 9.3k pairs Format thinking (channel) License Apache-2.0 Findings / what it does scotoma-2 is the successor to scotoma . It starts from the same idea, a bounded edit that loosens gemma‑4‑31B‑it’