The AI OS for scientific discovery. We run the whole research lifecycle — ideas, experiments, IP, funding, publication. Built for world-class science.
Joined January 2025
- Tweets97
- Following27
- Followers2.8K
- Likes118
ScienceGuru retweeted
Qwen3.8-Flash-Next-E384-FP4-V2 is built for work that needs more than a good chat response.
Imagine an engineering agent handling a real bug ticket: it reads the task, reasons through the likely failure path, calls approved search or test tools, drafts an implementation plan, and returns structured findings for a developer to review.
Or use it for math-heavy coding work: work through an algorithmic problem, produce an implementation, and hand the result back to your existing evaluation or test loop.
This is a full merged FP4 checkpoint after three GRPO-style post-training updates with verifiable rewards. It is a complete model release — not a LoRA adapter — with all weights, tokenizer, configs, and MTP files included.
Reported results under the documented evaluation setup:
• AIME 2026: 95.0
• HumanEval: 98.78
• MMLU: 87.37
• C-Eval: 89.97
• Tool calling: 77.88
For teams building coding agents, reasoning workflows, and tool-using systems, V2 provides a ready-to-serve FP4 checkpoint rather than another adapter to integrate.
Validated with vLLM 0.31 on a single B200. The documented serving path includes FP8 KV cache, prefix caching, reasoning parsing, and Qwen XML tool calling.
Download it, run it on a task your team already knows well, and compare the result in your own harness:
huggingface.co/autotrust/Qwe…
ScienceGuru retweeted
Qwen3.8-27B-NVFP4-DGX-SPARK-V2 is here. Most Local AI releases stop at quantization. V2 goes further into the inference loop.
It packages the complete Qwen3.8-27B NVFP4 checkpoint with AutoTrust AI’s 64k MTP runtime recipe for vLLM.
The plugin reduces the draft vocabulary from 248,320 to 64,026 rows and quantizes the draft path, while leaving the target model and verification lm_head untouched.
That means less draft-step memory traffic and more practical speculative decoding for local coding, reasoning, tool-driven workflows, and private internal APIs.
Built for Blackwell hardware, including DGX Spark / GB10 and B200. Download it, install the included plugin, and serve it through an OpenAI-compatible vLLM endpoint.
huggingface.co/autotrust/Qwe…
ScienceGuru retweeted
Train your decision-model using ms-swift: with model-specific losses, automatic two-level temperature calibration and built-in Open-Jev data.
Also capable of converting causal language models into decision models, with generic_decision option.
ScienceGuru retweeted
Glad to see @ModelScope2022 bring decision-model training and inference into ms-swift.
AutoTrust AI’s JEV-27B-VL is now included in the framework’s decision workflow via `--task_type decision`, with dedicated loss support, built-in Open-Jev data, and automatic two-level temperature calibration.
This gives developers a more practical route to fine-tune and run calibrated multimodal decisions—where agents need to choose, score, route, or escalate with probabilities they can use.
Explore ms-swift: github.com/modelscope/ms-swi…
A quick start with ScienceGuru.
Start a chat. Keep your research, code, and data together in one project folder. Customize settings when you need to. Define the goal, materials, and output before work begins. Speak your task, review it, then send.
When it is time to move on, copy a working directory, conversation deeplink, or Markdown and pick up where you left off.
One desktop research workspace for organizing work, defining outcomes, and delivering results.
Download #ScienceGuru: scienceguru.ai
ScienceGuru retweeted
New from AutoTrust AI: Qwen3.8-Flash-Next-E384-FP4-Local.
A compact AutoTrust build of NVIDIA’s Qwen3.8 Flash Next FP4 Local checkpoint, designed for practical local deployment.
Our NAS recipe keeps 384 of 512 routed experts in every decoder and MTP layer, while preserving top-10 routing, shared experts, attention, vision tower, and tokenizer.
Result: 79.78 GiB of weights instead of 95.12 GiB — 16.1% smaller.
In our same-harness tests, code, tool use, math, and vision stay close to the original checkpoint. The tradeoff is lower performance on knowledge-heavy multiple-choice tasks, so use the full 512-expert model when that is the priority.
We also include a lossless MTP speculative-decoding recipe for vLLM 0.31: 308.9 tok/s and 3.34× the no-MTP speed on one B200 at greedy decoding.
Explore the model, benchmarks, files, and vLLM setup:
huggingface.co/autotrust/Qwe…
ScienceGuru retweeted
After Black October, Bring the AI Home.
A month of critical vulnerabilities, AI-agent campaigns, and ultra-low-cost attacks changed the security calculus.
The answer is not to stop using AI. It is to stop sending your most sensitive data across the internet to rent it.
For source code, regulated records, deal information, and other high-value workflows, ask one question:
Does the data go to the model — or does the model come to the data?
With DGX Spark–class hardware and compressed open models, local AI is now practical. Keep the data, model weights, and agents inside one perimeter.
Read the full argument:
autotrust.ai/blog/after-blac…
ScienceGuru retweeted
AutoTrust Decision Models — one collection, from fast local decisions to multimodal agent control.
Every model returns calibrated probabilities for the answer options that matter: route or escalate, pick the next tool, score risk, verify a claim, or decide what action an agent should take next.
Start with the classics:
JEV-9B — compact typed decisions with System 2 reasoning
JEV-27B & JEV-27B v1.1 — our open text decision models
JEV-27B-VL — multimodal decisions across text and images
GEV-26B-Decide — a high-performing general decision model
JEV-35B — larger-scale decision capability
NVFP4 releases — lower-memory deployment options for practical inference
The collection also includes live demos for Mario, Rubik’s Cube, Tetris, and typed decisions, plus the public Decision Index result set.
Together, the models in this collection have now recorded more than 5.4M downloads.
Explore the full AutoTrust Decision Models collection:
huggingface.co/collections/a…
ScienceGuru retweeted
Want to see what open decision models can actually do?
AutoTrust Spaces is our hands-on demo hub: play Mario, Rubik’s Cube, and Tetris with JEV-27B; test typed decisions with JEV-9B; and explore live News and Shorts demos.
Try the demos:
huggingface.co/autotrust/spa…
ScienceGuru retweeted
Top 3 in both Vision and Text categories.
Ahead of TypeSafe JEV in Text.
JEV-27B-VL reached No. 1 on Hugging Face Global Trending.
Now AutoTrust-JEV-27B v1.1 is Top 3 on both Jev Decision Index boards.
Text: tied for #3 with a 68.0 Full Score.
That puts our open 27B model ahead of TypeSafe’s hosted Jev 1.13 — and ahead of Liquid AI’s d1-3B — on the same public Decision Index.
Vision: #3 with a 71.9 Full Score, including 74.4 on the public set and 69.3 on the private set.
It ranks ahead of Perplexity Decider v1.2, vLLM-SR d3, and Cloudflare’s clef-omni.
This is not a one-model spike. It is a model family built for the decision layer of agents: structured probabilities for routing, tool selection, claim checks, next-action choice, and escalation to deeper reasoning when confidence is not enough.
AutoTrust is establishing itself as a clear leader in open decision models.
Open weights. Apache-2.0. Built for local deployment.
Explore the Jev Decision Index:
huggingface.co/spaces/multim…
Download AutoTrust-JEV-27B v1.1:
huggingface.co/autotrust/Aut…
ALT Top 3 in both Vision and Text categories. Ahead of TypeSafe JEV in Text. JEV-27B-VL reached No. 1 on Hugging Face Global Trending. Now AutoTrust-JEV-27B v1.1 is Top 3 on both Jev Decision Index boards. Text: tied for #3 with a 68.0 Full Score. That puts our open 27B model ahead of TypeSafe’s hosted Jev 1.13 — and ahead of Liquid AI’s d1-3B — on the same public Decision Index. Vision: #3 with a 71.9 Full Score, including 74.4 on the public set and 69.3 on the private set. It ranks ahead of Perplexity Decider v1.2, vLLM-SR d3, and Cloudflare’s clef-omni. This is not a one-model spike. It is a model family built for the decision layer of agents: structured probabilities for routing, tool selection, claim checks, next-action choice, and escalation to deeper reasoning when confidence is not enough. AutoTrust is establishing itself as a clear leader in open decision models. Open weights. Apache-2.0. Built for local deployment.
ALT Top 3 in both Vision and Text categories. Ahead of TypeSafe JEV in Text. JEV-27B-VL reached No. 1 on Hugging Face Global Trending. Now AutoTrust-JEV-27B v1.1 is Top 3 on both Jev Decision Index boards. Text: tied for #3 with a 68.0 Full Score. That puts our open 27B model ahead of TypeSafe’s hosted Jev 1.13 — and ahead of Liquid AI’s d1-3B — on the same public Decision Index. Vision: #3 with a 71.9 Full Score, including 74.4 on the public set and 69.3 on the private set. It ranks ahead of Perplexity Decider v1.2, vLLM-SR d3, and Cloudflare’s clef-omni. This is not a one-model spike. It is a model family built for the decision layer of agents: structured probabilities for routing, tool selection, claim checks, next-action choice, and escalation to deeper reasoning when confidence is not enough. AutoTrust is establishing itself as a clear leader in open decision models. Open weights. Apache-2.0. Built for local deployment.
ScienceGuru retweeted
Meet AutoTrust-JEV-27B-v1.1: a 27B text-classification model built for structured decisions. With 5.6k downloads and 166 likes, it's quietly becoming a go-to for teams that need reliable, repeatable classification at scale.
ScienceGuru retweeted
Thank you, @HuggingModels.
AutoTrust-JEV-27B-v1.1 has now passed 16K downloads on Hugging Face.
It is an open 27B decision model for the high-frequency calls inside agent systems: route a request, select a tool, detect an out-of-scope intent, verify a claim, or choose the next action from a fixed set of options.
Instead of producing another paragraph, it returns a probability for every available option — making decisions measurable, routable, and easier to audit.
Apache-2.0. Run it locally with vLLM: 📷huggingface.co/autotrust/Aut…
ScienceGuru retweeted
2/ The model card reports a complete local run of the Decision Index 0.3 public suite:
• Public index: 67.31
• 37 indexed benchmarks
• 140,178 completed scoreable requests
Important context: this is a self-reported local evaluation using the official kit, pending maintainer verification. It is not an official leaderboard placement.
ALT Attachment for Tweet 2 — Original model-card Decision Index public-performance chart.
ScienceGuru retweeted
Meet AutoTrust-JEV-27B v1.1 — a 27B text decision model built for the thousands of small choices inside an AI agent.
Instead of generating a long response, it turns a defined question and its options into probabilities you can act on: choose the right tool, route an out-of-scope request, classify an intent, assess a claim, or select the next API action.
In our complete local run of the Decision Index 0.3 public suite, JEV-27B v1.1 achieved a 67.31 public index across 37 benchmarks and 140,178 completed scoreable requests, with particular strength in tools and automation:
• 96.25 on tool selection
• 97.06 on intent classification with out-of-scope detection
• 93.63 on banking intent classification
• 78.24 on claim verification
Apache-2.0 weights and decision readout are available now on @HuggingModels and @ModelScope2022.
Download on Hugging Face:
huggingface.co/autotrust/Aut…
Download on ModelScope:
modelscope.ai/models/AutoTru…
ScienceGuru retweeted
Try JEV in the browser. ⚡
AutoTrust AI’s JEV Demo is now live on @ModelScope2022 Studios — a hands-on place to explore our multimodal decision-model work.
JEV is designed for the small but critical choices inside AI systems: selecting an option, assigning a score, evaluating confidence, and deciding what an agent should do next.
Open the demo, try it with your own prompts, and follow AutoTrust Labs on ModelScope for new models, demos, and decision-AI updates.
JEV Demo:
modelscope.ai/studios/AutoTr…
ScienceGuru retweeted
🚀 JEV-27B-VL from @AutoTrustAI is now live on Novita AI!
Launching as a partner ⚡
🎁 Free for 14 days.
A 27B vision-language model for decisions over text and images.
• Yes/no, ratings, or multiple-choice decisions
• Probabilities for each option
• Optional reasoning for harder decisions
ScienceGuru retweeted
Explore the Decision API 👇
docs.novita.ai/api-reference…
ScienceGuru retweeted
Great to launch with our partner @novita_labs.
JEV-27B-VL is now live on Novita AI, bringing AutoTrust AI’s open 27B multimodal decision model to developers through a production-ready API.
Send text or images. Receive calibrated probabilities for yes/no decisions, 0–5 scoring, or multiple-choice selection. Use fast System 1 decisions for high-volume routing and action loops, then enable System 2 reasoning when a harder decision needs more thought.
A practical fit for visual QA, document and chart review, computer-use workflows, content ranking, and confidence-gated agents.
Try JEV-27B-VL free for 14 days on Novita AI:
docs.novita.ai/api-reference…
🚀 JEV-27B-VL from @AutoTrustAI is now live on Novita AI!
Launching as a partner ⚡
🎁 Free for 14 days.
A 27B vision-language model for decisions over text and images.
• Yes/no, ratings, or multiple-choice decisions
• Probabilities for each option
• Optional reasoning for harder decisions
ScienceGuru retweeted
Meet GEV-26B-Decide: a 26B text-classification model that blends system-one intuition with system-two reasoning. It outputs typed decisions with calibrated probabilities, making AI choices more transparent and trustworthy.
