Open-Weight Models

OpenESM d20 model trained on ClimbMix. This repository contains the pretraining checkpoint without optimizer state conversion. - model.ckpt: Lightning checkpoint. - modelingesm.py: standalone model and checkpoint loader. - tokenizer/tokenizer.pkl: serialized ESM tokenizer. - tokenizer/tokenbytes.pt: token byte table for BPB evaluation. The 520M label describes the model parameter count. Training token counts are intentionally omitted from the repository name and file names. The code and checkpoint format are maintained in the

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…

From Semantic Understanding through Visual Foresight to Action EWAM is a unified embodied model that jointly processes vision-language, future-video, and action tokens in a single flow-matching Diffusion Transformer. Without any explicit stage design, the action stream learns a depth-wise division of labor: shallow layers retrieve instruction and current-scene semantics from the vision-language expert, intermediate layers shift toward predicted future-frame representations, and deep layers are dominated by action self-attention for motor refinement. Real-robot results on Franka, Dobot, and Unitree G1-D are reported in the technical report. Each checkpoint is a DeepSpeed-style directory…

The two pretrained models the EasyOCR en reader uses, converted from the official.pth files to.safetensors. Nothing was retrained or modified: every tensor is identical, in value and dtype, to the original, and the key names (including the module. prefix) are unchanged. SHA256SUMS lists the same values: sha256sum -c SHA256SUMS. Converted from the official EasyOCR release assets (EasyOCR's own MD5 values in easyocr/config.py are shown): Conversion: torch.load(..., weightsonly=True) of the state dict, then safetensors.torch.savefile. The saved file was loaded back and compared tensor by tensor with the original (all equal). An EasyOCR reader fed these tensors returned the same boxes, text and…

Model · Robotics

EasyWAM-Hidden-Wan22

OpenMOSS

This repository hosts released EasyWAM-Hidden checkpoints built on Wan2.2-TI2V-5B. EasyWAM-Hidden uses a separate Action DiT conditioned one-way on intermediate Video DiT features. Inference retains future-video prediction to provide the hidden visual conditioning. The checkpoints are trained with the EasyWAM codebase. The LoRA checkpoint uses rank 128 (alpha 128) on the backbone Video DiT target modules. Other trainable EasyWAM modules are stored in the same checkpoint, so it must be loaded with the matching lora task recipe. Task success rate (%) under the EasyWAM LIBERO evaluation protocol. All results use stateposition: sequence; higher is better. Models using the same Wan2.2-TI2V-5B…

Model · Robotics

EasyWAM-MoT-Wan22

OpenMOSS

This repository hosts released EasyWAM-MoT checkpoints built on Wan2.2-TI2V-5B. EasyWAM-MoT uses separate Video DiT and Action DiT experts whose tokens interact through mixed self-attention. At inference time, it predicts actions without generating future video. The checkpoints are trained with the EasyWAM codebase. The LoRA checkpoint uses rank 128 (alpha 128) on the backbone Video DiT target modules. Other trainable EasyWAM modules are stored in the same checkpoint, so it must be loaded with the matching lora task recipe. Task success rate (%) under the EasyWAM LIBERO evaluation protocol. All results use stateposition: sequence; higher is better. Models using the same Wan2.2-TI2V-5B…

Model · Robotics

EasyWAM-Unified-Wan22

OpenMOSS

This repository hosts released EasyWAM-Unified checkpoints built on Wan2.2-TI2V-5B. EasyWAM-Unified uses a single Video DiT to jointly represent and denoise video and action tokens, coupling both modalities bidirectionally through the same self-attention layers. The checkpoints are trained with the EasyWAM codebase. The LoRA checkpoint uses rank 128 (alpha 128) on the backbone Video DiT target modules. Other trainable EasyWAM modules are stored in the same checkpoint, so it must be loaded with the matching lora task recipe. Task success rate (%) under the EasyWAM LIBERO evaluation protocol. All results use stateposition: sequence; higher is better. Models using the same Wan2.2-TI2V-5B…

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…

A frozen embedding encoder. A 9.66M trainable reader. Speech transcription without encoder fine-tuning. Embed2ASR reuses the representations of an audio embedding model for speech recognition. The audio tower of Google's EmbeddingGemma 2 stays frozen and unmodified. We take its pre-pooling lasthiddenstate (1536-d temporal features, 25 frames per second; not the final pooled embedding vector) and decode it with a GRU-CTC reader of 9,655,172 trainable parameters. About 314.5M parameters are loaded for inference (304,824,608 frozen encoder + 9,655,172 reader). Languages: Taiwanese Mandarin, English and Mandarin-English code-switching. This is representation reuse, not a new ASR backbone…

Model · Feature extraction

EmbeddingGemma-2-GGUF

Nguyen Quoc Vinh

Community GGUF quantizations of google/embeddinggemma-2. If this GGUF made your day easier, a coffee would make mine. I build and test these releases myself. Your coffee helps keep me going. Thank you for supporting this work. EmbeddingGemma 2 is a multilingual, multimodal embedding model from Google DeepMind. It maps text and code, images, video, and audio into a shared 768-dimensional vector space and has an 8,192-token shared context window. The upstream checkpoint has a 270M-parameter text path plus optional vision and audio encoders. This release contains a quantized text backbone and a shared BF16 vision/audio projector. Text, image, and audio inputs returned normalized…

MTPLX-branded multi-token-prediction model for Apple Silicon (MLX). Forged with MTPLX Forge from EryriLabs/Ornith-1.5-35B-A3B-BigBang-MTP. See mtplxruntime.json for the full verification record. See LICENSE.

weighted/imatrix quants of https://huggingface.co/pinkachu/Estopia-13B-32k For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/Estopia-13B-32k-GGUF If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 See…

Model

EvSpark

Dinghao

Drafter checkpoints for EvSpark: a small distilled drafter that accelerates single-stream Evo2 7B (StripedHyena2) generation while staying distributionally lossless. Numbers: Evo2 7B bf16, single stream, RTX 4090, 48 genomic prompts × 1024 tokens, 3 training seeds. One checkpoint serves any decode-time draft length γ′ ≤ training γ (exact causal prefix; no retraining). Beyond 7B: the same drafter recipe retrained for Evo2 20B / 40B reaches 2.18–2.46× (real-43) and 2.51–2.78× (all-48) on one H20 (SDPA), and a predictor-guided regulatory-DNA design workflow sees a median 1.57× complete-design speedup over a calibrated batched native baseline (see paper). All four files are single-layer L27…

Model · Video text to text

EventLens-4B

Guowen Zhang

EventLens-4B is a video-language model developed through event-structure reinforcement learning and multi-teacher on-policy distillation (MT-OPD). Built on Qwen3-VL-4B-Instruct, it learns to recognize event boundaries, progression, and relations, alongside temporal grounding and video question answering. The model is part of EventLens: Event-Structure Reinforcement Learning for Video Understanding, developed by AIM3 Lab, Renmin University of China, and Kling AI. Selected results reported in the EventLens paper, compared with the corresponding pretrained backbone under the shared 256-frame protocol. QVHighlights, ActivityNet, and Charades-STA use mIoU. E.T. Bench and VinoGround use their…

Model · Video text to text

EventLens-8B

Guowen Zhang

EventLens-8B is a video-language model developed through event-structure reinforcement learning and multi-teacher on-policy distillation (MT-OPD). Built on Qwen3-VL-8B-Instruct, it learns to recognize event boundaries, progression, and relations, alongside temporal grounding and video question answering. The model is part of EventLens: Event-Structure Reinforcement Learning for Video Understanding, developed by AIM3 Lab, Renmin University of China, and Kling AI. Selected results reported in the EventLens paper, compared with the corresponding pretrained backbone under the shared 256-frame protocol. QVHighlights, ActivityNet, and Charades-STA use mIoU. E.T. Bench and VinoGround use their…

The trained EvoSteer orchestrator as a complete model: the trained LoRA adapter (rank 64, alpha 128 on qproj, kproj, vproj, oproj, outproj and inprojqkv) is merged into the Qwen3.5-9B weights. The merged layers are stored in float32. The LoRA update is about 0.06% of the weight norm, and rounding the merged layers to bfloat16 would discard most of it, so load the model in float32 to reproduce the trained orchestrator exactly; all other layers are the unchanged bfloat16 base weights. evosteerheads.safetensors holds the learned value and flow heads of the same checkpoint (heads. and the published value snapshot publishedvalue.).

This repository contains the weights and tokenizer for bert-base-uncased fully fine-tuned on SQuAD v1.1 (Stanford Question Answering Dataset) for extractive question answering. The model was adapted using end-to-end full fine-tuning with a differential two-learning-rate optimizer scheme as part of an academic comparative study on BERT adaptation paradigms. The model was trained on a deterministic subsample of SQuAD v1.1 (rajpurkar/squad): - Task Head (QA outputs, 1,538 params): Learning rate = 1e-3 Evaluation was performed on the complete official SQuAD v1.1 validation split (10,570 examples, spanning 10,753 feature windows) using an optimized post-processing pipeline (top-15 start/end…