We collaborated with @NVIDIAAI on early access post-training. Spoiler alert: It's an incredible model to train!
Technical blog: fastino.ai/blog/nvidia-ne…
Today we’re launching the Fastino Training API for supervised fine-tuning and reinforcement learning.
The Fastino Training API includes day-zero support for @NVIDIAAI Nemotron 3.5 Super VL, alongside Nemotron 3.5 Lightning.
Our API gives ML and research teams low-level control over post-training without requiring them to provision GPUs or operate separate training and generation systems.
A few highlights:
• Write your own SFT and RL loops in Python
• Train with importance sampling, PPO, CISPO, or DRO
• Run grouped sampling with token log probabilities
• Save and resume adapter and optimizer checkpoints
• Pay per token processed, not per GPU hour
• Spend 25% to 85% less than Tinker’s published rates
• Migrate existing Tinker workloads by changing only the server address and API key
Along with the Training API, we’re releasing two start-of-the-art open weight models fine-tuned on NVIDIA Nemotron 3.5 Super VL, specialized for finance and healthcare. Together, they improved performance across all 15 held-out benchmarks we measured.
And for a limited time, we’re offering discounted pricing on training for NVIDIA Nemotron 3.5 Super VL through the Fastino Training API.
Try it now: agent.fastino.ai
@george_onx@NVIDIAAI People need to realise how big of a deal this is. This is THE CHEAPEST training api in the world. LITERALLY a no-brainer to use this.🔥
This is huge.
This is THE cheapest training API in the world 🤯. @DhruvAtreja1 taking Fastino Labs to the moon.
To all my researcher friends, hop on this it’s a no brainer. You’ll get more GPU hours and flops for your dollar
We collaborated with @NVIDIAAI on early access post-training. Spoiler alert: It's an incredible model to train!
Technical blog: fastino.ai/blog/nvidia-ne…
@CompleteSkeptic Call me crazy but I’m lowkey feeling proud that Diogo Almeida posted a graph with GLiDE being ranked # 2 even if this is the context hahah
much love. really big fan of your work at TypeSafe AI 🩷🙏
x.com/singularity_bl…
Artificial Analysis officially ranked GLiDE as the # 2 Decision Model in the WORLD 🤯🤯🤯
Trained a SOTA foundational model that is # 2 in the world according to the holy grail benchmark, Artificial Analysis. Lifetime personal bucket list item ✅
What a life 🤯
Artificial Analysis officially ranked GLiDE as the # 2 Decision Model in the WORLD 🤯🤯🤯
Trained a SOTA foundational model that is # 2 in the world according to the holy grail benchmark, Artificial Analysis. Lifetime personal bucket list item ✅
What a life 🤯
Great to see GLiDE at #2, and we have a huge update coming out this week
Seeing the model perform this well on a completely independent evaluation shows just how strong the model is
Is seems adaptive thinking is a big reason why:
-GLiDE first calculates a fast probability distribution -If the leading answer is uncertain, reasoning turns on -That reasoning is incorporated into the final probabilities
Easy decisions stay fast, harder decisions get extra compute. This is especially useful for knowledge, reasoning and complex tool routing, where most decision models fail
We will be releasing the weights and a full rundown on how we trained the model with our training api
Try it through the Fastino API with code USE_GLIDE for free credits.
Introducing the Artificial Analysis Decision Index, benchmarking decision models across classification, tool calling, knowledge and reasoning. Jev leads among decision models; language models such as Claude Haiku 5.5 still deliver higher accuracy, but at much higher cost and
Trained a foundational model that beat OpenAl and officially ranks # 2 in the world according to Artificial Analysis 🤯🤯
This is your reminder that you can do anything you set your mind to.
Fastino GLiDE will be # 1 soon. 👀
Major credits to the entire @fastinoAI team.
Introducing the Artificial Analysis Decision Index, benchmarking decision models across classification, tool calling, knowledge and reasoning. Jev leads among decision models; language models such as Claude Haiku 5.5 still deliver higher accuracy, but at much higher cost and
8 Followers 538 FollowingLeading the @Dassault3DS "AI FOR QA" initiative worldwide🙂🙏
Implementation of AI harness and training/fine-tuning/redteaming of LLM and SLM.
844 Followers 227 FollowingResearch Fellow at @Harvard | Building agentic AI Scientists with AutoScientists, ClawInstitute and ToolUniverse @ScientistTools
156K Followers 78 FollowingSane + 🌶️ takes in an insane AI world... AI capabilities researcher: co-created RLHF/ChatGPT @ @openai now trying to right the wrong 🤭 (ceo @typesafeai)
7K Followers 1K Followingregressing linearly on a daily basis. wife guy who does retrieval. research @mixedbreadai, prev answerdotai - dms work randomly, responses might be very slow
981 Followers 60 FollowingCo-Founder https://t.co/wJA3UPQim9 (every job on earth) | Former CS PhD student @ Stanford, advised by @jure. AI for social good | Formerly ML Data Scientist @Airbnb
53K Followers 221 Followingidiot. cuda og, harvard val, morgan prize, society of fellows, 1 hilbert problem so far, creating friendly, SAFE, delightful, supergenius ..things @anthropicai
106K Followers 954 FollowingOpen model research, founder, director @trillium_labs. Prev. co-led Olmo at Ai2.
Writes @interconnectsai, wrote https://t.co/alRXKINTwE
844 Followers 227 FollowingResearch Fellow at @Harvard | Building agentic AI Scientists with AutoScientists, ClawInstitute and ToolUniverse @ScientistTools
23K Followers 1K FollowingThe sea is the sea
The old man is an old man
The boy is a boy and the fish is a fish
The sharks are all sharks no better and no worse
733K Followers 2K FollowingTour: https://t.co/0EvFPCAWq7 My show https://t.co/vU0FN5Npky, Stand Up https://t.co/lYWunjjmw8 Podcast https://t.co/ifaVHHqvrd Book https://t.co/zdHM2ncpCD
1.4M Followers 485 FollowingProfessor, Evolutionary Behavioral Scientist, Author. Opinions are mine alone. Retweets do not necessarily imply an endorsement.
508K Followers 1K FollowingIsaiah 26:3-4. Co-founder and CEO of @petersonacademy. Founder of @theliondiet for autoimmunity/chronic disease. @fuller_research