전체 검색
AI 모델 2119
- leosamsHelloworldXL_helloworldXL50GPT4V↗
misri
- Qwen3.5-35B-A3B-Claude-Distilled-APEX-GGUF↗
mudler
⚡ Each donation = another big MoE quantized I host 25+ free APEX MoE quantizations as independent research. My only local hardware is an NVIDIA DGX Spark (122 GB unified memory), enough for ~30-50B-class MoEs, but bigger ones (200B+) require rented compute on H100/H200/Blackwell, typically $20-100 per quant. If APEX quants are useful to you, your support directly funds those bigger runs. **APEX (Adaptive Precision for EXpert Models)** quantizations of Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled. Benchmarks coming soon. For reference APEX benchmarks on the same Qwen3.5-MoE architecture, see mudler/Qwen3.5-35B-A3B-APEX-GGUF.
- wav2vec2-large-xlsr-53-hebrew↗
imvladikon
Fine-tuned facebook/wav2vec2-large-xlsr-53 on the several downloaded youtube samples. When using this model, make sure that your speech input is sampled at 16kHz. The model can be used directly (without a language model) as follows:
- Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-NVFP4-GGUF↗
jan1k
NVFP4 quantisations of HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF, built with michaelw9999/advanced-gguf-quantizer (a llama.cpp fork focused on NVFP4/MXFP6 quantization). All six share the same source, protection policy, and architecture profile (`qwen35dense`). They differ only in the calibration data used to compute NVFP4 input scales (or, for v2, the absence of it). Requantised from Q8_K_P, not BF16. Tensors that were q8 in the source go through one extra rounding step; bf16 source tensors requantise cleanly.
- all-mpnet-base-v2↗
sentence-transformers
이것은 sentence-transformers 모델입니다. 이 모델은 문장과 단락을 768차원의 밀집 벡터 공간으로 매핑하며, 클러스터링이나 의미 검색과 같은 작업에 사용할 수 있습니다. sentence-transformers를 사용하지 않는 경우, 다음과 같이 모델을 활용할 수 있습니다. 먼저 입력을 트랜스포머 모델에 통과시킨 뒤, 문맥화된 단어 임베딩 위에 적절한 풀링 연산을 적용해야 합니다. 이 프로젝트는 자기-supervised 대비 학습 목표를 사용하여 매우 큰 문장 수준 데이터셋에서 문장 임베딩 모델을 학습하는 것을 목표로 합니다. 우리는 사전 훈련된 `microsoft/mpnet-base` 모델을 사용하고 1B 개의 문장 쌍 데이터셋에서 파인튜닝을 수행했습니다. 우리는 대비 학습 목표를 사용합니다. 즉, 쌍 중 하나의 문장을 주어졌을 때, 모델은 무작위로 샘플링된 다른 문장들의 집합 중에서 실제로 우리 데이터셋에서 해당 문장과 짝을 이루었던 문장이 어느 것인지 예측해야 합니다.
- Yi-9B↗
01-ai
If you're interested in Yi's adoption of Llama architecture and license usage policy, see Yi's relation with Llama. ⬇️ > 💡 TL;DR > > The Yi series models adopt the same model architecture as Llama but are **NOT** derivatives of Llama. 🔥 2024-07-29 : The Yi Cookbook 1.0 is released, featuring tutorials and examples in both Chinese and English.
- distilcamembert-base-ner↗
cmarkea
We present DistilCamemBERT-NER, which is DistilCamemBERT fine-tuned for the NER (Named Entity Recognition) task for the French language. The work is inspired by Jean-Baptiste/camembert-ner based on the CamemBERT model. The problem of the modelizations based on CamemBERT is at the scaling moment, for the production phase, for example. Indeed, inference cost can be a technological issue. To counteract this effect, we propose this modelization which **divides the inference time by two** with the same consumption power thanks to DistilCamemBERT. This model performance is compared to 2 reference models (see below) with the metric f1 score. For the mean inference time measure, an AMD Ryzen 5 4500U @ 2.3GHz with 6 cores was used:
- encodec_24khz↗
facebook
This model card provides details and information about EnCodec, a state-of-the-art real-time audio codec developed by Meta AI. EnCodec is a high-fidelity audio codec leveraging neural networks. It introduces a streaming encoder-decoder architecture with quantized latent space, trained in an end-to-end fashion. The model simplifies and speeds up training using a single multiscale spectrogram adversary that efficiently reduces artifacts and produces high-quality samples. It also includes a novel loss balancer mechanism that stabilizes training by decoupling the choice of hyperparameters from the typical scale of the loss. Additionally, lightweight Transformer models are used to further compress the obtained representation while maintaining real-time performance. - **Repository:** GitHub Repository - **Paper:** EnCodec: End-to-End Neural Audio Codec
- jebadiah-9b-v2-GGUF↗
frontier-infra
> **Just want to run it?** Download jebadiah-9b-v2-1-GGUF and open it in llama.cpp, Ollama or LM Studio. > > **Which one should I use?** Start with the 9B. It's smaller and faster, and it's what most people run. Pick the 27B if you have the memory and want the higher score (Decision Index Full 55.94 against the 9B's 44.91, board data of 2026-10-15). On Apple silicon, use the MLX builds of the same models. You can try the 4B in the browser first: jebadiah-playground. > > This repo: the 9B v2 GGUF quants (Q4_K_M, Q5_K_M, Q8_0), for llama.cpp, Ollama and LM Studio. **Jeb is a decision model, not a chat model.** Use `jeb serve` or the decide scripts (see Run Jeb locally on jebadiah.ai). In an LM Studio or Ollama chat window it will look wrong. Trying it in a chat window? Use the optional chat profiles: https://github.com/getainode/jebadiah/blob/main/docs/chat-window.md
- wolf-defender-prompt-injection↗
patronus-studio
Explore the integrations above, or see how Personaxis, Wanaku and Mygentic Cello integrate Wolf Defender. Wolf Defender is an open, multilingual classifier that detects prompt injection and jailbreak-style instructions before they reach your LLM. Use it to screen user inputs, retrieved documents, emails, web pages and agent tool outputs, with inference running on your own hardware. All models below were evaluated with the same threshold (`0.5`) and document-scoring protocol: 2,048-token windows, 64-token overlap and normalized Smooth-Max aggregation.