저장한 도구도구 추천
FOXAI SEARCH

전체 검색

AI 모델 2119

  • gemma-4-31B-it-qat-q4_0-unquantized↗

    Google

    Hugging Face | GitHub | Launch Blog | Documentation | Technical Report > [!Note] > This model card is for the new versions of the Gemma 4 family optimized with Quantization-Aware Training (QAT), which allows preserving similar quality to bfloat16 while dramatically reducing the memory requirements to load the model. > Four versions of the QAT checkpoints are available: > * **Unquantized QAT checkpoints** (Q4_0): Half-precision weights extracted from the QAT pipeline, ideal for custom downstream compilation and research. Available for Gemma 4 E2B, E4B, 12B, 26B A4B, and 31B, and their drafter models. > * **GGUF** (Q4_0): Ready-to-deploy formats for broad ecosystem compatibility. Available for Gemma 4 E2B, E4B, 12B, 26B A4B, and 31B. > * **Mobile-optimized** (wNa8o8): A custom schema engineered explicitly for mobile hardware efficiency. It features targeted 2-bit decoding layers, optimized KV caches, and static activations to maximize VRAM savings. Available for Gemma 4 E2B and E4B. > * **Compressed Tensors** (w4a16): QAT checkpoints serialized in the compressed-tensors format for native, optimized inference with vLLM. Available for Gemma 4 E2B, E4B, 12B, and 31B. > * **Assistant Compatibility**: When using multi-token prediction (speculative decoding) with an assistant model alongside a QAT target model, the assistant model must also be a QAT checkpoint with the same precision to ensure compatibility. Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages.

  • H3-Anti-Burn-LoRA↗

    Imagineer13

    When you make a long MiniMax H3 video by chaining clips, each new clip continues from the end of the previous one. It copies that ending's small flaws and adds a few more. After a few clips, faces "burn": skin and lines get crunchy and etched, and the picture gets harsher. This LoRA is used on the **continuation clips** and keeps them close to the look of the first clip. It was trained on three turbos (Larry Turbo v4, HyperFlow, lightx2v 8-step) and tested on a fourth model it never saw, where it cut face burn from +61% to +4%. Each image shows the same chain run without and with the LoRA. The prompts and seeds are the same, so clip 1 is identical; the LoRA is never used on it. Each frame is taken 1 second before the end of its video, about 37 seconds in. We picked scenes where the camera stays on the same shot, so the two clip-10 frames compare fairly.

  • Ternary-Bonsai-2-27B-NInfer-v3↗

    WaveCut

    A NInfer **v3** artifact of PrismML's Ternary Bonsai 2 27B for **NInfer-all**, the `master` branch of iamwavecut/ninfer-all, which serves the RTX 3090, RTX 4090, RTX 5090 and RTX PRO 6000 Blackwell. Stock NInfer builds refuse this file (`t2_g128_fp16` and the `hadamard_signs` Use auxiliary exist only in that line). The numbers below come from `master` at `2172a598` (September 2026), each card running the device route profile built into it. Every profile of this revision runs there; older engines are covered at the end. With `--lm-head-draft` the drafters score their candidates on the proposal head instead of the full one. MTP decodes 4% faster through it and accepts the same share of its drafts; DFlash2 gains nothing measurable, so its profiles leave the flag off. The head is loaded only with the flag.

  • Ingot-I-27B-Q2↗

    dendriteholdings

    A public mirror of a model that won on Ingot, a Bittensor subnet where miners quantize a fixed teacher model and the validator crowns the copy that stays closest to it. It is Prism ML's Ternary Bonsai 2 27B, refined: the same ternary codes, with the per-block scales and the norm weights re-tuned by the miner to bring it closer to Qwen3.8-27B. The weights are the miner's upload, byte for byte. Credit belongs to the miner, and to Prism ML for Bonsai 2.

  • Occamy-1.0-APEX-I-MiniPlus-V2.1-GGUF↗

    IsValorum

    If you consider these releases to be of high quality and they help you in your day-to-day workflow, consider supporting on Ko-fi. Every contribution directly sustains future cloud compute hours and helps support my university studies. > > *Independently computed on private cloud clusters. If this handcrafted release saves you VRAM and runs faster on your GPU, consider fueling the community compute fund on Ko-fi.* > > Explore the new canonical V3 releases. MiniPlus prioritizes Q5-class to near-Q6 fidelity without a fixed file-size ceiling; NanoPlus targets Q4-class quality at a practical footprint. > > - **Qwen3.8 27B — MiniPlus V3** — 14.16 GB **(+13.21% improvement in WikiText-2 PPL vs GSQ-RCO IQ3_S)**. > - **Qwen3.8 27B — NanoPlus V3** — 11.35 GB **(+11.49% improvement in WikiText-2 PPL vs GSQ-RCO IQ3_S)**. > - **Swift-1.5 Qwen3.8 27B Uncensored MTP — MiniPlus V3** — 14.28 GB **(+5.70% improvement in WikiText-2 PPL vs GSQ-RCO IQ3_S)**. > - **Swift-1.5 Qwen3.8 27B Uncensored MTP — NanoPlus V3** — 11.08 GB **(+2.26% improvement in WikiText-2 PPL vs GSQ-RCO IQ3_S)**. > > Percentages compare the reported WikiText-2 PPL with GSQ-RCO IQ3_S (7.07). The linked 27B cards document the evaluation protocol and model variants. > > **Explore the APEX-I MiniPlus V2.1 collection** > > ### EXPLORE THE ESTABLISHED 35B MoE MINIPLUS LINEUP > These are complementary APEX-I-MiniPlus V2.1 releases, not alternate downloads of the same model. Each receives the same tensor-by-tensor approach, integrated MTP where supported, and a design suitable for full or partial system-RAM inference. Choose the model whose native strengths best fit the work you want to do: > > - **Qwen3.6-35B-A3B MTP APEX-I-MiniPlus-V2.1** — a versatile frontier MoE for broad reasoning, multilingual work, agents, tool use, and multimodal tasks. > - **Best for:** General reasoning, agent workflows, tool calling, and flexible multimodal use. > - **Qwen3.6-35B-A3B MTP APEX-I-MiniPlus-V2.1 Abliterated** — the V2.1 refusal-ablated Qwen3.6 edition for users who deliberately prefer reduced refusal behavior. > - **Best for:** Workflows where an abliterated Qwen3.6 variant is explicitly desired. > - **Ornith 1.5 APEX-I-MiniP

  • 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.