←
AutoTrust206 posts
AutoTrust avatar✓

AutoTrust ✓

@AutoTrustAI

Frontier AI research lab. We build AI scientists & the platforms they run on — compressing the full research lifecycle from idea to impact.

◷ Joined January 2025▧ 43 Photos and videos
AutoTrust avatar
AutoTrust@AutoTrustAI·Nov 16

Start with a decision your app makes every day. “Which team should handle this ticket?” “Which search result is most relevant?” “Which button should the agent click next?” Our Decider models return probabilities for the available choices, so you can set confidence thresholds and send uncertain cases for review—not just parse a generated answer. Try the models: huggingface.co/autotrust/mod…

AutoTrust avatar
AutoTrust@AutoTrustAI·Nov 16

5M+ monthly downloads across AutoTrust AI’s 10 most-downloaded models on @huggingface. Two releases above 1M each. 🚀 Here’s what each model does—and where to start: 1) AutoTrust-Decider-Pro-35B — 1.52M A single-pass decision model that returns probabilities for up to 256 choices—use it to route support tickets or rank candidate actions. 2) AutoTrust-Decider-Pro-Vision-27B — 1.41M Makes decisions from text and images, with optional reasoning—use it to interpret charts, select browser actions or experiment with game-control loops. 3) AutoTrust-Decider-Mini-9B — 656K A compact model for yes/no decisions, multiple-choice selection and ratings—use it to classify requests or score workflow options. 4) AutoTrust-Decider-Pro-27B — 449K Combines fast probability-based decisions with a separate reasoning mode—use it to assess supplier risks or choose the next step in a workflow. 5) AutoTrust-Decider-Pro-35B-NVFP4 — 395K The lower-memory Pro-35B variant—run probability-based ticket routing and action selection on a single 32–48GB GPU. 6) GEV-26B-Decide — 248K A decision model with adaptive thinking—answers straightforward choices directly and calls on reasoning when confidence is low. 7) AutoTrust-Decider-Pro-Vision-27B-v1.1 — 155K This release handles text-only decisions, with strengths in tool selection and intent classification—use it to match a request to the right tool. 8) GEV-26B-Decide-NVFP4 — 111K A lower-memory GEV variant for text-and-image decisions—experiment with screenshot-driven browser actions using about 17.1 GiB of GPU weight memory. 9) Qwen3.8-Flash-Next-E384-FP4-V2 — 65.9K A merged FP4 checkpoint for reasoning, tool calling and structured outputs—test it in self-hosted workflows with the documented B200 setup. 10) Qwen3.8-27B-NVFP4-DGX-SPARK-V2 — 63.5K A local text-generation model with an optimized speculative-decoding recipe—use your DGX Spark to generate Python code and iterate on coding tasks. Pick a model that fits your task and hardware. Download it, test it on your own inputs, and follow AutoTrust AI for new releases: huggingface.co/autotrust/mod…

Post attachment
AutoTrust avatar
AutoTrust@AutoTrustAI·Nov 12

A naming update from AutoTrust AI: we’re moving our JEV releases to the AutoTrust Decider family to make them clearly distinguishable from TypeSafe’s Jev. JEV-9B → AutoTrust-Decider-Mini-9B JEV-27B → AutoTrust-Decider-Pro-27B JEV-27B-VL → AutoTrust-Decider-Pro-Vision-27B We’re updating repositories, model cards, and related materials. Browse our releases here: huggingface.co/autotrust

AutoTrust avatar
AutoTrust@AutoTrustAI·Nov 12

140K+ downloads in the past month. Open weights. Measurable gains. 🚀 Thanks @HuggingModels for highlighting AutoTrust AI’s Decider Pro Vision 27B v1.1! 96.25 in tool selection. 97.06 in intent classification. Sentiment extraction: 27.8 → 55.0, a +27.2-point gain over the starting checkpoint. Build agents that route requests, select tools, and classify sentiment—with probabilities for each option, rather than free-form answers to parse. Apache-2.0 weights. Download and test it on your own workflow: huggingface.co/autotrust/Aut… Reported figures are benchmark skill scores, not accuracy percentages. Local evaluation; pending maintainer verification. Explore our desktop research workspace—download ScienceGuru: scienceguru.ai/

Post attachment
0:10
AutoTrust avatar
AutoTrust@AutoTrustAI·Nov 11

Start with one recurring decision in your agent: which tool to call next. Define the options, test JEV on real examples, and evaluate when it should choose—and when it should defer. The model cards include serving instructions: huggingface.co/collections/a…

AutoTrust avatar
AutoTrust@AutoTrustAI·Nov 11

Thanks @LysandreJik and the @HuggingModels team for bringing decision models into Transformers—and highlighting AutoTrust AI’s JEV. Agents don’t always need another generated paragraph. Sometimes they need to choose a tool, rank search results, or select the next action from a screenshot. JEV’s System 1 path returns calibrated probabilities for explicit options in one forward pass, over text and images. Developers can use those probabilities to set thresholds, route uncertain cases for deeper reasoning, and avoid parsing free-form answers. A shared model.decide(...) interface means less model-specific glue across inference, training and evaluation. That’s a meaningful step toward making open decision models easier to use. Download our models and explore the demos: huggingface.co/collections/a…

Post attachment
bebu avatar
⟳ AutoTrust retweeted
bebu@bebuu_ai·Nov 8

If you have been following Alibaba's Qwen3.8-Flash, two really cool updates came out around it today that make it much stronger and easier to run. First, a team at AutoTrust AI took the open-weight Qwen3.8-Flash model, ran three extra rounds of reinforcement learning on it, and compressed the whole thing down to 4-bit so it fits on a single server GPU (about 267 GB of memory). The wild part is that this compressed version actually thinks cleaner than the original — it scored 95% on the 2026 AIME math exam and 98.8% on HumanEval coding while using about 22% fewer thinking tokens per answer. At the same time, Google's TPU engineering team figured out why Qwen3.8 sometimes loses track of details in super-long chats. They found a tiny number-rounding bug in how the model calculates word positions over long documents and switched that one calculation to higher precision, which stops the model from drifting on huge prompts while saving over 18 GB of memory per chip.

AutoTrust avatar
AutoTrust@AutoTrustAI·Nov 8

A concrete use case: give a self-hosted assistant an internal software screenshot, the relevant documentation, and a Python script. Ask it to explain the interface, suggest a code change, and call an approved tool through your application. That’s the kind of workflow this release lets developers explore—beyond a standalone chatbot. The repository includes the full merged weights, launch script, required vLLM patch, and benchmark details. Serving is validated on one B200; check the deployment requirements before downloading: huggingface.co/autotrust/Qwe… For a desktop research workspace from the same team, download ScienceGuru: scienceguru.ai/

AutoTrust avatar
AutoTrust@AutoTrustAI·Nov 8

Thanks @HuggingModels for highlighting AutoTrust AI’s Qwen3.8-Flash-Next-E384-FP4-V2! 39K+ downloads in Hugging Face’s rolling monthly window—and a practical direction for Local AI: multimodal reasoning, coding, and tool calling on infrastructure you control. Our complete, RL-refined FP4 checkpoint reports 95.0% on AIME 2026 and 98.78% on HumanEval. Building an assistant for private documents, screenshots, and code? Download the model and test it on your own workload: huggingface.co/autotrust/Qwe…

Post attachment
AutoTrust avatar
AutoTrust@AutoTrustAI·Nov 3

Which AutoTrust AI decision model should you try first? JEV-9B — A smaller model combining fast decisions with optional reasoning, a practical starting point for ticket routing and classification. JEV-27B — Text decisions and full reasoning on one backbone, for workflows that need both option selection and longer explanations. AutoTrust-JEV-27B-v1.1 — A text-focused decision model with strong evaluated tool-selection and intent-classification results, for choosing which API or workflow to invoke. JEV-27B-VL — Decisions over text and images, from checking whether a browser agent finished its task to selecting the next move in Mario or Tetris. GEV-26B-Decide — Fast text-and-image decisions with opt-in adaptive thinking: answer directly when confident, reason further when a logic or math question needs it. JEV-35B — A sparse MoE model for text-and-image decisions, such as ranking search results or categorizing product listings; it returns decisions, not chat responses. GEV-26B-Decide-NVFP4 — A lower-memory GEV deployment option for bringing decision workflows onto compatible local hardware. JEV-35B-NVFP4 — A compressed JEV-35B release with a documented 32–48 GB GPU deployment path, making local ranking and classification more accessible. JEV-Gemma4-26B-A4B — The earlier Gemma-based release, subsequently published as GEV-26B-Decide with the same weights. Explore the demos, download a checkpoint, and test it on your own workload: huggingface.co/autotrust

AutoTrust avatar
AutoTrust@AutoTrustAI·Nov 3

Your agent can write an answer. Can it choose the right action? AutoTrust AI’s Decision Models collection brings together nine open-weight releases, live demos, and public evaluation results — with 5.4M+ combined model downloads in Hugging Face’s rolling monthly window. Built for decisions you can plug into real workflows: • A customer reports a duplicate charge. Choose billing, shipping, or technical support — with a probability for each option. • An agent has several tools available. Select the next tool rather than generate another paragraph. • A browser agent claims it finished. Evaluate its actions and final screenshot before accepting the result. • A game presents a new state. Choose the next move — see the Mario and Tetris demos. Explore JEV-9B, JEV-27B, AutoTrust-JEV-27B-v1.1, JEV-27B-VL, JEV-35B, GEV-26B-Decide, and NVFP4 variants. From text routing to visual judgments, the family gives developers different model sizes and deployment options for adding a decision layer to their own systems. Try a demo, download a checkpoint, and test it on decisions your application actually needs to make: huggingface.co/collections/a… Follow @AutoTrustAI for new releases. For a research workspace built by the same team, download ScienceGuru: scienceguru.ai/ @HuggingModels

AutoTrust avatar
AutoTrust@AutoTrustAI·Oct 30

Local AI is not one model, one format, or one deployment path. The AutoTrust AI DGX Spark Models collection brings together six releases optimized for NVIDIA DGX Spark — from GGUF builds for llama.cpp to NVFP4 and MTP-accelerated vLLM deployments. What can you actually do with them? Run a local coding assistant against a real repository. Serve a model through an OpenAI-compatible endpoint for an internal tool. Test an agent that can reason, call approved tools, and return results without routing every request through a remote API. Start with the model that fits your workload: • GLM-5.3-Flash-GGUF-DGX-Spark for a single-Spark GGUF deployment, with tool calling and reasoning support. • Qwen3.8-27B-NVFP4-DGX-SPARK for lossless MTP speculative decoding on DGX Spark. • GLM5.3 Flash E192, E224, and E256 variants for different DGX Spark deployment options. • GLM-5.3-GGUF-DGX-Spark for the larger GLM 5.3 GGUF route. The six current releases in the collection have recorded more than 111K downloads over the last month. Follow the collection for new Local AI releases, choose one model, and test it on a task your team already knows well: huggingface.co/collections/a…

AutoTrust avatar
AutoTrust@AutoTrustAI·Oct 29

A practical first test: Give the model one real task from your workflow — for example, a bug report with a codebase search tool and a test runner attached. Ask it to: 1. identify the likely issue, 2. decide which approved tools to call, 3. explain the proposed fix, 4. return structured findings for human review. That is more useful than testing whether a model can produce a polished paragraph in isolation. Qwen3.8-Flash-Next-E384-FP4-V2 includes a documented vLLM path with Qwen XML tool calling and auto tool choice, so developers can start from a working serving configuration. modelscope.ai/models/AutoTru…