サイト内検索
AI モデル 84760
- Kroma-v0.3.1-Turbo-OPD-GGUF↗
Abiray
- Qwen2.5 VL 72B Instruct↗
阿里巴巴 · Qwen
Qwen2.5-VLは、花や鳥、魚、昆虫などの一般的な物体の認識に長けています。また、画像内のテキスト、チャート、アイコン、グラフィック、レイアウトの分析にも高い能力を発揮します。
- ivila-row-layoutlm-finetuned-s2vl-v2↗
allenai
- GLM-5.3-Quark-MXFP4-AttnFP8↗
amd
- Flint-40B-A2.5B-8GB-GGUF↗
anik-jha
- MiniMax-H3-PDD-ComfyUI↗
aptech0081
ComfyUI conversions of the official Alibaba PAI MiniMax-H3 PDD acceleration weights. The Ref2VA checkpoints generate video and audio from reference conditioning. **Choose PRUNED INT8 WITH HEADS for the smaller native PDD checkpoint.** This repository also keeps the full INT8 **WITH HEADS** and **WITHOUT HEADS** variants. Both with-heads files contain the merged PDD trunk and 32 video plus 32 audio output heads. They load through native ComfyUI after PR #17157, merged October 18, 2026, without a separate PDD acceleration LoRA or PDD Apply node. Put any baked checkpoint in `ComfyUI/models/diffusion_models/`. Put the two custom-node LoRA files in `ComfyUI/models/pdd_acc/`.
- MedWest-7B↗
Aryanne
- Unlimited-OCR-2-GGUF↗
AtomicChat
- JEV-35B-NVFP4↗
autotrust
> [!IMPORTANT] > **Try AutoTrust/GuruSearch live (new, 11 October 2026).** A recommendation and search demo in which every ranking is a > calibrated System 1 decision, made in about half a second: > * **Recommendation:** the latest headlines from 6 news feeds, ranked by importance. > * **Search:** results from Google News, Bing News and Yahoo News re-ranked by relevance, side by side with the > search engines' own order, plus a short answer with citations. This repository is **autotrust/JEV-35B with its 10,240 routed expert MLPs (40 layers × 256 experts) quantized to NVFP4**. Everything else is the bf16 model unchanged: attention, linear attention, the shared expert, the routers, the vision tower, the MTP layer, the lm_head, the System 1 adapter, the decision head and the temperatures. Below the NVFP4 comparison, the rest of this card is the JEV-35B card; its tables are the bf16 results unless marked otherwise. * **Text: −0.57 on the Decision Index.** All five areas within 1.2 skill points of bf16 (Knowledge 0.422, Language 0.628, Retrieval 0.706, Tools 0.753, Arts 0.413); the largest per-benchmark changes are Home appliance simulator −5.7, CRUXEval −4.7 and GPQA +5.4. * **Images: −0.85 on the vision rebuild**, a small but real loss (paired bootstrap 95 % interval −1.5 to −0.2), mostly on CharXiv charts (−5.3). * **Robot arm: 13 of 20 scenes against 15 of 20.** Four scenes changed outcome (3 lost, 1 gained), within noise (sign test p = 0.63); every grasped cube still reached the tray (13/13). * **Speed:** the same latency as bf16 on one B200 for single requests; the gain is memory (one 32–48 GB GPU is enough). * **Games** (seed 0, one run each, noisy): 2048 largest tile 64 (bf16 32), Snake 5 food (bf16 11), Quick, Draw! 85.9 % on finished sketches (bf16 86.3 %), chess mate-in-one 45 % (bf16 47 %), Connect Four 1 win of 6 (bf16 0).
- MegaBeam-Mistral-7B-512k↗
aws-prototyping
This model, presented in Scaling Context, Not Parameters: Training a Compact 7B Language Model for Efficient Long-Context Processing, is a Long-Context LLM that supports 524,288 tokens in its context. `MegaBeam-Mistral-7B-512k` was trained on Mistral-7B Instruct-v0.2, and can be deployed using various serving frameworks like vLLM and Amazon SageMaker's DJL endpoint. Please refer to our GitRepo for deployment and inference examples. We evaluated `MegaBeam-Mistral-7B-512k` on three long-context benchmarks. For each benchmark, we deployed the `MegaBeam-Mistral-7B-512k` model with vLLM (v0.5.1) on an EC2 instance and obtained LLM responses through the OpenAI API provided by vLLM. The Arize-ai NIAH varies the target random number and introduces a random city for each question, requiring the LLM to extract the random number from various selected context locations.