全站搜索

AI 模型 84753

• Kling 3.0 Turbo↗

  快手 · 可灵

  Kling 3.0 Turbo API（APIMart）：快手推出的快速文生视频与图生视频模型，生成延迟低，支持多镜头提示词，时长 3–15 秒。开通会员，API 调用立省20%起。

• c70-h9↗

  ld9466311

• LFM2.5-1.2B-JP↗

  LiquidAI

• LFM2.5-Encoder-230M↗

  LiquidAI

  **LFM2.5-Encoder** is a family of multilingual bidirectional encoders built on the LFM2 architecture, available in two sizes: Both are masked language models with full bidirectional attention, designed to be fine-tuned into task-specific models (classification, token classification, retrieval, reranking, and semantic similarity) across 15 languages, and to run efficiently on-device. > [!NOTE] > 💻 **Demos**: We built the demos below from fine-tuned LFM2.5-Encoders. Each one runs in a CPU-only Hugging Face space: > - **Zero-shot prompt routing** — define your own routing lanes as free text. The model scores the whole prompt against every lane in one pass. > - **Zero-shot policy linting** — check text against your company's rules, written as free text. It scores every token against every rule in one pass. > - **Spell checking** — correct misspellings token by token. > - **PII detection** — spot and remove 40 kinds of personal information across 16 languages. > - **Masked-diffusion text generation** — bonus: run the encoder as a chatbot that generates text by iteratively unmasking instead of left to right.

• Qwen3.8-Flash-Next-REAP320-oQ3e-fp16-DWQ-MTP-Vision-MLX↗

  Litwein

• Qwen3.5-35B-A3B-uncensored-heretic-GGUF↗

  llmfan46

• gemma-4-E2B-it-MLX-6bit↗

  lmstudio-community

  _👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: google **Original model**: gemma-4-E2B-it **MLX quantization**: provided by LM Studio team using mlx_vlm 6-bit quantized version of gemma-4-E2B-it using MLX, optimized for Apple Silicon.

• d_m16↗

  loben0505

• d3-ultra-GGUF↗

  magnitudedev

• decider-0.8b↗

  Mapika

  The smallest decider: a language model that does not generate text. It reads a **state** (a string or any JSON value) and a set of **typed questions** and returns a probability distribution for every question from a single forward pass: Choice (2-255 options, optionally described), Score (2-10 described levels), Noul (probability of yes). No decoding, no parsing, no output outside the options you defined. Same code, same wire format (`POST /v1/systemone`, TypeSafe Jev's format), same training recipe as the 2B: one epoch of `scripts/train.sh full` from `Qwen/Qwen3.5-0.8B-Base` over the full mixture (1.47M examples, 455M tokens, 4.5 h on one GH200). All six repositories share one interface (`decider.infer.Decider`, `POST /v1/systemone` in TypeSafe's format) and one readout: the letter logits at an answer slot, softmaxed over the options. Pick by size and input. Code, data registry, training scripts, the changelog and the per-version history: https://github.com/Mapika/decider.