サイト内検索
AI モデル 84761
- sam2-hiera-small↗
facebook
Repository for SAM 2: Segment Anything in Images and Videos, a foundation model towards solving promptable visual segmentation in images and videos from FAIR. See the SAM 2 paper for more information. SAM2 can be used for automatic mask generation to segment all objects in an image using the `mask-generation` pipeline: SAM2's key strength is its ability to track objects across video frames. Here's how to use it for video segmentation:
- jpn-100mb-after-wc-from-eng-uniform-newlex-before-ckpt500-packed-bfdiso_seed455↗
francesca9805
- tam-100mb-after-wc-loglinear-newlex-after-ckpt500-packed-bfdiso_seed3407↗
francesca9805
- sfm_unfiltered_e2e_misalignment_upsampled_base↗
geodesic-research
- perth-coreml↗
iliasaz
- ViT-B-16-SigLIP-384__webli↗
immich-app
- Sage-A1.5-Q8_0-GGUF↗
InternScience
> [!Note] > This repository contains **GGUF** model weights for Sage-A1.5, quantized to **Q8_0**, for deployment with llama.cpp, Ollama, LM Studio, and other GGUF-compatible runtimes. > > For the original Hugging Face Transformers weights (compatible with Transformers, vLLM, SGLang, etc.), see InternScience/Sage-A1.5. **Sage‑A1.5** is a 35B Mixture‑of‑Experts agentic model based on **Qwen3.6** and **Agents-A1** from Shanghai AI Laboratory, built to advance long-horizon scientific problem solving through adaptive capability composition. Building upon **Agents‑A1**, **Sage‑A1.5** learns not only to solve individual tasks, but also to organize work and revise its approach during execution, highlighting three key capabilities: **Agentic Orchestration, Verification, and Open Scientific Discovery**. First, agentic orchestration extends single-agent execution through task delegation and parallel collaboration among subagents with isolated contexts, enabling complex tasks to be decomposed and addressed concurrently while reducing interference across concurrent subagents. Second, agentic verification strengthens long-horizon reliability through progress checking, evidence validation, and reflective strategy revision, allowing **Sage‑A1.5** to recognize unproductive search paths and pursue alternative approaches. Third, open scientific discovery extends agentic capabilities beyond answering predefined questions to conducting exploratory research, connecting scientific inquiry with interactive analysis and inspectable research artifacts. We hope **Sage‑A1.5** provides the community with an accessible foundation for open scientific discovery, offering a practical path from long-horizon task execution to collaborative, verifiable, and inspectable scientific exploration.
- Qwen3.8-Flash-Next-P48NVFP4-MoESQ↗
ISTA-DASLab
- ThinkingCap-Qwen3.8-27B-abliterated-NVFP4A16↗
IstroSec
A 4-bit weight-only quantization (NVFP4 weights, bf16 activations) of ThinkingCap-Qwen3.8-27B-abliterated, the uncensored variant of bottlecapai/ThinkingCap-Qwen3.8-27B. 20.6 GB, down from 55.6 GB in bf16, at KL 0.0155 against the bf16 model. The weights fit a 24 GB GPU with a little room for KV cache; 32 GB and up is comfortable. vLLM serves it on Ampere and newer (sm80+) with a weight-only kernel: Marlin FP4 on most GPUs (Ampere, Ada, Hopper, RTX 50, DGX Spark) and a dedicated BF16×FP4 kernel on B200/B300. Activations stay bf16, so no GPU computes in FP4 here. **Which build?** The W4A16 build (19.5 GB, KL 0.0260) runs on the same GPUs (vLLM: Marlin, Machete on Hopper) and is 1.1 GB smaller; this build has the lower KL. Speed was not measured for either. With memory to spare, the FP8-BLOCK build (31.3 GB, KL 0.0046) has the lowest KL of the published builds; on Ada GPUs use FP8-DYNAMIC (31.3 GB, KL 0.0068) instead.
- Qwen-3.8-27B-Uncensored↗
junafinity
