←
Victoria X Lin1,515 posts
Victoria X Lin avatar

Victoria X Lin

@VictoriaLinML

MTS @thinkymachines | Native Multimodal Intelligence Prev: @AIatMeta @SFResearch • PhD @uwcse

◷ Joined December 2010▧ 65 Photos and videos
Victoria X Lin avatar
Victoria X Lin@VictoriaLinML·Nov 6

✨Thrilled to introduce Inkling 2 Small 594B-17B(A). It is a strong multimodal agentic model with native vision capability. We invite you to try the model out through Tinker, and open-weights w/ Apache 2.0 license is coming next week. thinkingmachines.ai/news/ink…

Post attachment

Introducing Inkling 2 Small. Scoring 31 on the AA Intelligence Index, it's a big jump over its predecessor. Inkling 2 Small is available for fine-tuning and inference on Tinker today, with full weight release planned soon. thinkingmachines.ai/news/ink…

Sebastian Raschka avatar
⟳ Victoria X Lin retweeted
Sebastian Raschka@rasbt·Nov 14

Inkling 2 Small took a while... but it's more interesting than I initially thought! Using attention residuals (like Kimi K3), but without the linear-attention hybrid. Food for discussion for the end-of-the-year architecture trends analysis!

Post attachment
NVIDIA AI avatar
⟳ Victoria X Lin retweeted
NVIDIA AI@NVIDIAAI·Nov 13

Congrats @thinkymachines team on Inkling 2 Small! A 594B model pretrained in just 68 hours with NVIDIA NVFP4 on GB300 NVL72 racks. Read how the team made low-precision training work at this scale. 👇

Training with fewer bits is faster, but quantization error can interfere with learning. Today on Connectionism, we detail how we trained Inkling 2 Small with a native 4-bit forward pass from the first step of pretraining through the final RL rollout. thinkingmachines.ai/blog/end…

Jack Cook avatar
⟳ Victoria X Lin retweeted
Jack Cook@jackcookjack·Nov 13

Inkling 2 Small is our first model trained partly in NVFP4, with a mixed-precision recipe that enables a great tradeoff between speed and accuracy. Check out our new post to see how we did it, and the lessons we learned along the way!

Training with fewer bits is faster, but quantization error can interfere with learning. Today on Connectionism, we detail how we trained Inkling 2 Small with a native 4-bit forward pass from the first step of pretraining through the final RL rollout. thinkingmachines.ai/blog/end…

Horace He avatar
⟳ Victoria X Lin retweeted
Horace He@cHHillee·Nov 13

I'll be giving a talk tomorrow at the SGLang Summit at 10am! Oftentimes, I find explanations in ML infra to be unsatisfying. A common failure mode is that they'll explain the *literal* tradeoffs but fail to provide a mental model for how to reason about the choice. This talk won't explain everything about inference (only 15 minutes!), but I'll provide two mental models I've found useful when reasoning about inference, and I hope you find them useful too :)

Post attachment
Songlin Yang avatar
⟳ Victoria X Lin retweeted
Songlin Yang@SonglinYang4·Nov 12

Meet Inkling 2 Small! We’ve tweaked the architecture a bit since the last generation, adding attention residuals (with a q/k/v split), gated attention, dynamic attention sink, dynamic shortconv, value norm and more. Don’t ask me “linear attention wen"

Inkling 2 Small’s weights are now available for download on HuggingFace under an Apache 2.0 license. Make Inkling your own! huggingface.co/thinkingmachi…

SGLang avatar
⟳ Victoria X Lin retweeted
SGLang@sgl_project·Nov 12

Inkling 2 Small brings stronger agentic coding, vision, and knowledge work on the same efficient backbone. On Day 0, we made Inkling 2 Small fast to serve and practical to fine-tune: · 576 tok/s per user at batch 1 on NVIDIA Vera Rubin · 123 tok/s per user at batch 192 · Text and vision RL with Miles on just 8 Blackwell GPUs · NVIDIA Vera Rubin, Blackwell, Hopper, AMD MI350X / MI355X and Google TPU v7x

0:10

Inkling 2 Small’s weights are now available for download on HuggingFace under an Apache 2.0 license. Make Inkling your own! huggingface.co/thinkingmachi…

Luke Drago avatar
⟳ Victoria X Lin retweeted
Luke Drago@luke_drago_·Nov 10

We're hiring policy researchers at Thinking Machines. Quick 🧵 on why I think this role is something folks in AI policy should consider applying to:

Thinking Machines avatar
⟳ Victoria X Lin retweeted
Thinking Machines@thinkymachines·Nov 9

Boot up Inkling 2 Small on @OpenRouter, see what it can do.

Inkling 2 Small from @thinkymachines is free on OpenRouter for a limited time. It pairs vision with agentic coding, using visual feedback to build and refine websites, games, and 3D designs. Use it at $0 inside agentic harnesses like Claude Code, Codex and Hermes Agent. openrouter.ai/thinkingmachin…

0:47
Horace He avatar
⟳ Victoria X Lin retweeted
Horace He@cHHillee·Nov 5

Our infra has really improved quite a bit since the last time we released a model - this one took just under 3 days to pretrain! Also, it's quite cheap on Tinker (0.30/1.00/1.50 for in/out/train)! Hope you guys find this model great for customization purposes :)

Introducing Inkling 2 Small. Scoring 31 on the AA Intelligence Index, it's a big jump over its predecessor. Inkling 2 Small is available for fine-tuning and inference on Tinker today, with full weight release planned soon. thinkingmachines.ai/news/ink…

ARC Prize avatar
⟳ Victoria X Lin retweeted
ARC Prize@arcprize·Nov 6

Inkling 2 Small from @thinkymachines on ARC-AGI (Verified): - ARC-AGI-2: 81.7%, $0.27/task - ARC-AGI-1: 96.5%, $0.08/task It outperforms every open-weight model we've evaluated on both ARC-AGI-1 & ARC-AGI-2. Thinking Machines plans to release its full weights next week.

Post attachment