Peter G
Psxmaster
AI & ML interests
None yet
Recent Activity
new activity about 7 hours ago
deepseek-ai/DeepSeek-V4.1-Flash-1017:Did you know that you can run this model with 24 GB of VRAM and 64 GB of RAM? reacted to Banaxi-Tech's post with π₯ 1 day ago
KV1 updates:
We at https://huggingface.co/klein-ml have finished stage 1 of KV1 1.2B, we don't think we will need additional stages.
KV1 2.6B is near the midpoint of training, going well so far, its going to be our most agentic model yet.
We have released Klein Code Bench https://huggingface.co/datasets/klein-ml/klein-code-bench, a benchmark testing whether models can build complete projects from scratch. It contains a easy, intermediate, hard and max subset.
Here are some benchmarks of the current KV1 1.2B
It retains 75.8% of FP16 intelligence.
We are also announcing that we at https://huggingface.co/klein-ml are working on Klein 24B A2B which will be our first model featuring ternary weight quantization. reacted to XiaofengAlg's post with π₯ 1 day ago
π MechVQA: a 4B open VLM that beats GPT-5 on mechanical engineering drawings (ICML 2026)
We release MechVQA β the first comprehensive benchmark and training resource for multimodal LLMs on mechanical engineering drawings β plus MechVL, a 4B domain-specialized VLM trained with SFT β DAPO RL self-play.
π The benchmark: 13,515 bilingual (δΈ/EN) QA pairs over 3,371 unique drawings, covering 10 subcategories β dimension & annotation, assembly relationship, geometric calculation, anomaly detection, consistency judgment, projection & multi-view, structure understanding, identification & counting, item localization, text & table. Train/validation splits are image-hash disjoint and decontaminated against the public eval benchmark.
π The model: MechVL-4B-RL (Qwen3-VL-4B-Instruct β full-param SFT β two-stage DAPO self-play) reaches 84.85 total on MechVQA β ahead of every closed-source model we evaluated: GLM-4.6V 78.91 Β· Gemini-3-Pro-Preview 77.28 Β· MechVL-4B-SFT 76.36 Β· GPT-5 75.44. Reward = accuracy (LLM-as-a-judge) + format + quality; ablations show DAPO > GRPO > GSPO.
π All open (Apache-2.0), with full curation lineage, SHA-256 manifests and a LLaMA-Factory-ready dataset_info.json:
β’ Dataset: https://huggingface.co/datasets/XiaofengAlg/MechVQA
β’ RL checkpoint: https://huggingface.co/XiaofengAlg/MechVL-4B-RL
β’ SFT checkpoint: https://huggingface.co/XiaofengAlg/MechVL-4B-SFT
β’ Demo: https://huggingface.co/spaces/XiaofengAlg/mechvqa-project
β’ Paper: https://arxiv.org/abs/2605.30794
We hope MechVQA helps the community move beyond natural-image VQA into real industrial document understanding β feedback and contributions welcome!Organizations
None yet