전체 검색

AI 모델 2119

• minimax-h3-loras↗

  Hearmeman

  **Free ComfyUI workflows, Runpod templates, and guides:** 👉 hearmemanai.com A mirror of the MiniMax-H3 LoRAs published on CivitAI. CivitAI-matched files have identical SHA-256 checksums (listed below). CivitAI carries the sample videos, the version history and the comment threads; this repository exists so the weights can be pulled with a plain `resolve` URL, without an account. One **anatomy** adapter teaches H3 what a body part looks like. One **action** adapter teaches it what a body does. They are single-concept and they stack, so put them under whatever character or scene LoRA you are already running.

• Drama-3-GGUF↗

  Jmica

  Experimental native audio.cpp conversions of Fish Audio Drama 3, prepared from checkpoint revision `dd64a85cd82e9521f7202610ede97b367fc83946`. All packages use the same trained model architecture and checkpoint. **Standard GGML K-quants with mixed precision.** The packages use Q2_K, Q3_K_S and Q4_K_S file profiles with pure expert banks and explicit precision overrides. Routed expert tensors use Q2_K, Q3_K and Q4_K storage respectively. `backbone-8bit` means Q8_0 language-backbone matrices; `backbone-4bit` means Q4_K matrices with a Q4_0 text embedding. The table below lists the precision overrides. Audio-tower matrices and waveform codec weights remain FP16; audio-tower normalization and other retained FP32 vectors are unchanged. The Q3_K_S and Q4_K_S file profiles use pure expert banks: all 120 routed expert projection banks have uniform Q3_K or Q4_K storage. Their storage-type selection corresponds to a standard `--pure` K profile with explicit precision overrides for the dense backbone, text embedding and audio components. Architecture-specific higher-bit promotion heuristics are not applied; an unmodified default llama.cpp preset can choose different types for some tensors. See the standard converter's pure and per-tensor options. The native audio.cpp converter takes `--expert-type q3_k` or `--expert-type q4_k`. The table above lists each component's actual storage type.

• PIGuard↗

  leolee99

  - Website: https://injecguard.github.io/ - Paper: https://aclanthology.org/2025.acl-long.1468.pdf - Code Repo: https://github.com/leolee99/PIGuard Due to some licensing issues, the model name has been changed from **InjecGuard** to **PIGuard**. We apologize for any inconvenience this may have caused. Prompt injection attacks pose a critical threat to large language models (LLMs), enabling goal hijacking and data leakage. Prompt guard models, though effective in defense, suffer from over-defense—falsely flagging benign inputs as malicious due to trigger word bias. To address this issue, we introduce ***NotInject***, an evaluation dataset that systematically measures over-defense across various prompt guard models. NotInject contains 339 benign samples enriched with trigger words common in prompt injection attacks, enabling fine-grained evaluation. Our results show that state-of-the-art models suffer from over-defense issues, with accuracy dropping close to random guessing levels (60\%). To mitigate this, we propose ***PIGuard***, a novel prompt guard model that incorporates a new training strategy, *Mitigating Over-defense for Free* (MOF), which significantly reduces the bias on trigger words. InjecGuard demonstrates state-of-the-art performance on diverse benchmarks including NotInject, surpassing the existing best model by 30.8\%, offering a robust and open-source solution for detecting prompt injection attacks.

• Homo-GE2PE-Persian-HF↗

  mehdi-hf

  **This is not a new model.** It is a repackaging of MahtaFetrat/Homo-GE2PE-Persian by Elnaz Rahmati et al. — the weights are byte-identical. All credit for the model belongs to the original authors. The `-HF` suffix follows the `Llama-2-7b-hf` convention: same weights, packaged in transformers-native format rather than the original release format. It is not a new version of the model. What changed is only the packaging: the original ships zipped weights plus a vendored copy of Parsivar and a custom `GE2PE.py` wrapper. This repo is a plain `from_pretrained()` model with no extra dependencies, so it can be dropped into an inference pipeline directly.

• SambaLingo-Hungarian-Base-i1-GGUF↗

  mradermacher

• wav2vec2-large-xls-r-300m-assamese↗

  jayashreedevi2020

  This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_11_0 dataset. It achieves the following results on the evaluation set: - Loss: 0.9825 - Wer: 0.6470 The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 30 - mixed_precision_training: Native AMP - Transformers 4.40.2 - Pytorch 2.2.1+cu121 - Datasets 2.19.1 - Tokenizers 0.19.1

• L3-8B-Stheno-v3.2↗

  Sao10K

  *Just message me on discord if you want to host this privately for a service or something. We can talk.* I have done a test run with multiple variations of the models, merged back to its base at various weights, different training runs too, and this Sixth iteration is the one I like most. Changes compared to v3.1 \- Included a mix of SFW and NSFW Storywriting Data, thanks to Gryphe \- Included More Instruct / Assistant-Style Data \- Further cleaned up Roleplaying Samples from c2 Logs -> A few terrible, really bad samples escaped heavy filtering. Manual pass fixed it. \- Hyperparameter tinkering for training, resulting in lower loss levels.

• Wav2Vec2-large-xlsr-hindi↗

  theainerd

  Fine-tuned facebook/wav2vec2-large-xlsr-53 hindi using the Multilingual and code-switching ASR challenges for low resource Indian languages. When using this model, make sure that your speech input is sampled at 16kHz. The script used for training can be found Hindi ASR Fine Tuning Wav2Vec2

• resnet50d.ra2_in1k↗

  timm

  This model features: * ReLU activations * 3-layer stem of 3x3 convolutions with pooling * 2x2 average pool + 1x1 convolution shortcut downsample Recipe details: * RandAugment `RA2` recipe. Inspired by and evolved from EfficientNet RandAugment recipes. Published as `B` recipe in ResNet Strikes Back. * RMSProp (TF 1.0 behaviour) optimizer, EMA weight averaging * Step (exponential decay w/ staircase) LR schedule with warmup - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 25.6 - GMACs: 4.4 - Activations (M): 11.9 - Image size: train = 224 x 224, test = 288 x 288 - **Papers:** - ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476 - Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385 - Bag of Tricks for Image Classification with Convolutional Neural Networks: https://arxiv.org/abs/1812.01187 - **Original:** https://github.com/huggingface/pytorch-image-models

• German-RAG-UAE-LARGE-V1-TRIPLES-MERGED-HESSIAN-AI↗

  avemio

  This is a sentence-transformers model trained on this Dataset with roughly 300k Triple-Samples. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. It was merged with the Base-Model WhereIsAI/UAE-Large-V1 again to maintain performance on other languages again. - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 1024 tokens - **Similarity Function:** Cosine Similarity - **Documentation:** Sentence Transformers Documentation - **Repository:** Sentence Transformers on GitHub - **Hugging Face:** Sentence Transformers on Hugging Face