Open-Weight Models

DermFM-Zero is a dermatology vision–language foundation model. It pairs a PanDerm ViT-L/16 vision encoder with native-resolution input (NaViT patch-and-pack) and a PubMedBERT-256 text encoder pretrained on a Derm1M knowledge tree (KEP), aligned on 517,455 public dermatology image–text pairs with multi-aspect knowledge contrastive learning (MAKE) and knowledge distillation. It performs zero-shot diagnosis and cross-modal retrieval, serves as a backbone for multimodal fine-tuning and VQA, and yields interpretable concepts through sparse autoencoders. Across extensive benchmarks and three multinational reader studies, DermFM-Zero achieves state-of-the-art zero-shot performance while improving…

Model

Discrepancy_Calculus

Convergent Intelligence

A Referential Introduction to the Measure-Theoretic Framework for Singular Analysis and Structure-Aware Machine Learning Roy C March 2026 We present the core definitions, axioms, and principal theorems of Discrepancy Calculus (DISC) — a measure-theoretic framework that treats singularities as primary mathematical structure rather than pathology. The central object is the discrepancy operator, which quantifies the mismatch between integration and differentiation on metric-measure spaces; classical calculus is recovered as a degenerate smooth limit. We state the eight axioms of DISC, prove the Mesh Fundamental Identity (the DISC replacement for the Fundamental Theorem of Calculus), introduce…

DriveTwinLLM is an instruction-tuned, physics-grounded automotive diagnostic language model built on top of Qwen/Qwen2.5-3B-Instruct. It was fine-tuned using LoRA on NVIDIA B200 GPU hardware (180 GB VRAM) to achieve 98.13% evaluation token accuracy on real-world vehicle trouble codes, live ECU telemetry, and OEM service manuals. The model enforces strict zero-hallucination guardrails and features a specialized Dual-Persona Architecture: - Diagnostic computer scan fee ($90 – $130) - Certified shop labor ($120/hr flat-rate standard) - Strictly refuses unmonitored sensors (transmission fluid temperature, TPMS, cabin humidity) and invalid codes (P9999), redirecting the user to monitored engine…

Model · Text generation

DualMind_Methodolgy

Convergent Intelligence

Roy C Abstract. We present a four-stage pipeline for producing small language models (1.7B parameters) that exhibit self-critiquing dual-cognition reasoning from a 30B-parameter teacher. The pipeline chains: (1) proof-weighted knowledge distillation from three teacher variants (Instruct, Thinking, Coder) of Qwen3-30B-A3B, each producing distinct capability profiles in the student; (2) Topological Knowledge Distillation (TKD), which uses the Discrepancy Calculus (DISC) framework to decompose the teacher's output distribution into smooth, jump, and singular-continuous components via bounded variation theory, allocating training capacity to structural boundaries that standard KD smears across…

This is a frozen snapshot of CL, EDOS Engineering's experimental continual-learning chatbot, deployed under the persona "Hades." CL learns while it runs by editing the model's original quantized weight tensors in place. Its training is self-directed: the model selects its own training corpus, decides what is important, and is then trained on what it selected. It reads new AI research papers in full, judges which findings matter, writes the training text itself as attributed reviews, and marks which of them to learn and how strongly. It also learns from conversation. It uses no LoRA, adapter or side network. This export is the live model after 1,091 online learning updates, merged into one…

This is the model card for the EVHost fusion classifier that pairs with the Evo2 evolutionary language model for viral host prediction. The checkpoint file evhostbest.pt contains the trained FusionClassifier weights and all hyperparameters required for inference. The 211-dim genomic-feature vector is the post-CPB-compression representation fed to the fusion MLP. Pre-CPB-compression dimensionality is 1149 (CUB 64 + dinuc 16 + CPB 256 + AA 20 + bridge-dinuc 16 + adaptation 24 + zoonotic 7 + Evo2-projection 512 = 1915 → fused 1149). See src/evhost/models/fusion.py for the implementation. - Not a clinical diagnostic tool. Do not use for patient-level decision-making or pathogen identification…

This repository hosts pretrained EdenGNN checkpoints and reference configuration files associated with the paper Efficient equivariant framework for universal charge density prediction. EdenGNN (Equivariant Density Graph Neural Network) predicts charge densities from atomic structures and can be coupled with downstream DFT workflows for electronic-structure calculations. The config.yaml files stored in this repository are for reference only. They are not plug-and-play configuration files and must be modified based on the user's own environment before use. In particular, users should update paths, software-specific templates, dataset locations, checkpoint paths, output directories, and…

Model · Robotics

FastWAM-TDAA

Xizhou Bu

本仓保存 RoboTwin 实测模型、TDAA codec、原始结果和 4,000 个视频。 在 FastWAM 中接入预训练 TDAA version3bin24 编解码器，将 [32,14] 动作块编码为 [8,16] latent。策略在 latent 空间做 flow matching，再解码为 32 步绝对关节动作。decoder 使用任务向量和由已执行动作历史的 DCT24 特征生成的 phase；每个 episode 重置历史。 frozen 控制整个 TDAA codec，FastWAM 策略仍参与训练。联合训练额外加入动作重构与进度预测损失。动作 token 从 32 个变为 8 个，仅表示动作表示压缩；本次没有端到端加速测量。 - TDAA codec 与配置：codec.pt、config.json、metadata.json、datasetstatistics.json、taskembeddings.json，来自 80,000 步 AE。 代码仓的下载工具按固定版本获取文件并校验 SHA-256。在代码仓安装环境后运行： 权重保存到 checkpoints/released/{official,tdaafrozen}/step002725.pt。Wan VAE/T5/tokenizer 等基础模型、训练数据和 RoboTwin 仿真资产需另外准备，详见 GitHub 复现说明。本次不包含 optimizer/scheduler 完整训练状态。 以下为 FastWAM 基线与 TDAA Frozen=True 两组实测训练的共同设置，已与各自保存的…

Meridian.AI is a finance-specialized language model that continuously fine-tunes a Qwen2.5-0.5B backbone every hour on 25+ finance and math datasets, using Elastic Weight Consolidation (EWC) to prevent catastrophic forgetting across training sessions. The entire pipeline runs unattended on free GitHub Actions infrastructure — no GPUs. The deployed checkpoint is a standard Qwen2 model — trustremotecode=True is not required. Inputs are formatted with the ### Instruction: / ### Response: template used during training. A weighted streaming mix of 25+ finance and instruction datasets, including gbharti/finance-alpaca, sujet-ai/Sujet-Finance-Instruct-177k, nvidia/OpenMathInstruct-2…

Model · Text classification

Firebird-ModernBERT-512-RW

Noumenon, Inc.

Firebird-ModernBERT-512-RW is an experimental post-trained variant of It is a ~149M parameter ModernBERT binary classifier for distinguishing: - 0 — HUMAN The maximum sequence length is 512 tokens. This checkpoint was produced through reward-weighted classifier post-training. The original Firebird checkpoint was kept frozen as a reference model. Training examples were scored by the original classifier, difficult examples received larger loss weights, and the post-trained model was constrained against the frozen reference using a KL penalty. L = weightedcrossentropy + beta KL(reference || policy) Hard human examples received greater weighting than ordinary examples because one goal of the…

A weight-space combination of two independent abliterations of the same base model, produced by different teams with different methods. The two edits turn out to lie in nearly orthogonal directions, so applying both removes the refusals that each one leaves behind — the combination is more thoroughly decensored than either parent, with no fine-tuning and no gradient steps. This card documents what was done and why it works at the weight level. It does not report harmful- capability evaluations, and standard capability benchmarks (MMLU, etc.) have not been run — see Why Q80 is the base to requantize from. Both parents are FP8 (e4m3) native. Q80 (int8 + one fp16 scale per 32 weights)…

압축 가능성 라벨로 게이트를 학습한 액션 양자화(ATQ) 체크포인트다. 하나의 정책이 미세(1x) 디코더와 압축 디코더를 함께 갖고, VLM 라벨에서 배운 conf 가 둘 중 어느 군을 쓸지 고른다. 라우터는 그 군 안에서 horizon 만 고른다. (VLM 전용, 접촉 열 없음 · 16,286행 · 1,693에피 · stride 16) moeexperthorizons = [16, 9, 5, 8] · confthreshold(tau) = 0.55 · discreteactiondims = [6] (그리퍼는 절대 명령이라 · actionmergereduction = sum 회전 병합은 SO(3) 다(rotationmergespec 이 config 에 있다). 압축 블록의 회전 다시 정규화한다. scipy 대조 각도 오차 1e-14도. LIBERO 는 5 fine 스텝마다 재계획한다. 압축 행 하나는 fine 액션 2~3개의 합이므로 같은 배속이 되고, 배속을 움직이는 손잡이는 conf 게이트 하나다: 넘으므로 OSC 팔 컨트롤러의 입력 클립을 제거한 조건에서 평가했다(그리퍼 그대로). 게이트는 벤치마크가 실제로 깨지는 순서를 따른다 -- 압축에 강한 liberoobject 를 가장 많이 압축하고, 2배에서 -0.160 으로 무너지는 liberospatial 은 거의 압축하지 않는다. 브랜치 jimin-dev-label-gated.…

압축 가능성 라벨로 게이트를 학습한 액션 양자화(ATQ) 체크포인트다. 하나의 정책이 미세(1x) 디코더와 압축 디코더를 함께 갖고, VLM 라벨에서 배운 conf 가 둘 중 어느 군을 쓸지 고른다. 라우터는 그 군 안에서 horizon 만 고른다. (VLM 전용, 접촉 열 없음 · 16,286행 · 1,693에피 · stride 16) moeexperthorizons = [16, 7, 3, 8] · confthreshold(tau) = 0.55 · discreteactiondims = [6] (그리퍼는 절대 명령이라 · actionmergereduction = sum 회전 병합은 SO(3) 다(rotationmergespec 이 config 에 있다). 압축 블록의 회전 다시 정규화한다. scipy 대조 각도 오차 1e-14도. LIBERO 는 5 fine 스텝마다 재계획한다. 압축 행 하나는 fine 액션 2~3개의 합이므로 같은 배속이 되고, 배속을 움직이는 손잡이는 conf 게이트 하나다: 넘으므로 OSC 팔 컨트롤러의 입력 클립을 제거한 조건에서 평가했다(그리퍼 그대로). 게이트는 벤치마크가 실제로 깨지는 순서를 따른다 -- 압축에 강한 liberoobject 를 가장 많이 압축하고, 2배에서 -0.160 으로 무너지는 liberospatial 은 거의 압축하지 않는다. 브랜치 jimin-dev-label-gated.…

Model

HPC-Quantize

None

HPC-Quantize is an experimental, MIT-licensed quantization engine for aggressively compressing large language models into extremely low-bit formats, with a particular focus on Q2-class quantization. Instead of choosing a quantization candidate solely from its local reconstruction error, HPC generates competing reconstructions, represents them in a compact discrete state space, models interactions between neighboring blocks, and performs a global sequence optimization before writing the final GGUF. The current production path is entirely classical. Earlier versions explored quantum-inspired state and measurement formulations; the current implementation uses a sequential Sieve, bounded state…

arabic - handwritten-text-recognition - htr - ocr - historical-manuscripts - kraken libraryname: kraken arman-kraken-ocr is a Kraken OCR/HTR model for line-level recognition of handwritten Arabic manuscripts. The model is based on the Muharaf-trained Kraken checkpoint muharafrecbest.mlmodel and was subsequently fine-tuned on the ArMan dataset for historical Arabic manuscript recognition. This checkpoint is a fine-tuned derivative of the Arabic HTR model trained on the Muharaf Corpus: The model was fine-tuned on ArMan as part of our work on historical Arabic manuscript HTR and the AraMS-28k dataset. If you use AraMS-28k in your research, please cite: If you use RefLAM or its annotation…

Model · Text generation

Huihui-NeoHorse-1-4B-abliterated-GGUF

Huihui.ai

This is an uncensored version of TokenRhythm/NeoHorse-1-4B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. Layers 5-17 are being ablated (0-based indexing). The MTP and Visual components were extracted from the original Qwen/Qwen3.5-4B and can provide excellent support. Use the latest llama.cpp, - Risk of Sensitive or Controversial Outputs: This model’s safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate content. Users should exercise caution and rigorously review generated…