Find open-source science resources

This repository contains Chemistry fine-tuned Qwen3-4B checkpoints from the local SciKnowEval-style generalization setup.

👋 Join our LiGHT community. 📖 Check out the MeditronFO blog and MeditronFO preprint. 🔜 If you are a clinician join the MOOVE initiative here.

Sexo-FR is a French-language conversational language model that provides reliable, caring, and evidence-based sexual health information (information en santé sexuelle). It is part of a French public-health initiative whose goal is to make trustworthy sexual-health information more accessible to the…

👋 Join our LiGHT community. 📖 Check out the MeditronFO blog and MeditronFO preprint. 🔜 If you are a clinician join the MOOVE initiative here.

Gravity-bio-16B-A3B is a biology-focus midtrained model derived from Gravity-16B-A3B-Base. It uses the same sparse Mixture-of-Experts (MoE) architecture and tokenizer as Gravity-16B-A3B-Base, with additional midtraining for biological understanding on TheBioCollection corpus.

Molexar-10M Base is the unconditional base model for Molexar, a unified multimodal molecular foundation model for drug design. It is trained as an autoregressive molecular language model over Fragment-SELFIES, a BRICS-fragment molecular language with validity-preserving decoding and…

Molexar-10M Omni is the universal multi-condition model for Molexar, a unified multimodal molecular foundation model for drug design. It starts from fairydance/molexar-10m-base and is supervised fine-tuned to generate Fragment-SELFIES molecules under scalar molecular-property,…

GRamma-12B is a 12-billion-parameter instruction-tuned language model specialized for the Greek medical domain. It is built on top of Gemma 3 12B Instruct and adapted through parameter-efficient fine-tuning on a collection of Greek and bilingual medical question-answering data.

QLoRA adapter for Llama-3.1-8B-Instruct, fine-tuned on PubMedQA for yes / no / maybe biomedical question answering (run5).

BioMatrix is a multimodal biological foundation model that natively integrates 1D sequences, 3D structures, and natural language for both molecules and proteins within a single decoder-only architecture.

A domain-adapted clinical LLM fine-tuned on synthetic Indian medical Q&A records using QLoRA (4-bit quantization) with Unsloth 2x speedup. Built to power the conversational AI layer.

ProtGPT3-MSA is a multiple-sequence, homolog-conditioned autoregressive protein language model. It is part of the ProtGPT3 family, an open-source suite of promptable and aligned protein language models for protein sequence generation.

KAU-BioMedLLM is a research prototype for source-grounded biomedical variant interpretation. The current public release contains the LoRA adapter and documentation for a guarded report-generation system built around a curated biomedical evidence panel, citation enforcement, and abstention when…

## Important Notice If you are using GENERator for sequence generation, please ensure that the length of each input sequence is a multiple of 6. This can be achieved by either: 1. Padding the sequence on the left with 'A' (left padding); 2. Truncating the sequence from the left (left truncation).

Medical-GPT-OSS-Swallow-120B is a medical-domain language model based on tokyotech-llm/GPT-OSS-Swallow-120B-RL-v0.1. It is designed to support research and development toward safe and trustworthy AI for Japanese clinical settings.

Medical-Qwen3-Swallow-30B-A3B is a medical-domain language model based on tokyotech-llm/Qwen3-Swallow-30B-A3B-RL-v0.2. It is designed to support research and development toward safe and trustworthy AI for Japanese clinical settings.

For a convenient overview and download list, visit our model page for this model.

gemma4-12b-bioinfo is a fine-tuned Gemma 4 12B instruction model for bioinformatics, genomics, and computational biology question answering.

modelid = "DuanYi/R3LMHepG2"

![Language: English]()

> VIDRAFT FINAL-Bench — chemistry-specialized 218B MoE, served via the DELPHI 5-Phase inference cascade.

HealthJudge is a domain-adapted helpfulness evaluator for health-related Community Notes. It is designed to judge whether a note provides helpful context for a potentially misleading social-media post, following the Community Notes helpfulness criteria.

## Model Description ProtGPT3-112M is a single-sequence autoregressive protein language model for protein sequence generation. It is the smallest model in the ProtGPT3 family, an open-source suite of promptable and aligned protein language models ranging from 112M to 10B parameters.

ProtGPT3-10B is a single-sequence autoregressive protein language model for protein sequence generation. It is the largest model in the ProtGPT3 family, an open-source suite of promptable and aligned protein language models ranging from 112M to 10B parameters.

!Protein-ligand interaction header

A HuggingFace-compatible repackaging of PlasmidGPT (Shao, 2024) — a GPT-2-style decoder pretrained on 153k engineered plasmid sequences from Addgene. Loadable with standard AutoModelForCausalLM and AutoTokenizer. Used as the base for PlasmidGPT-SFT and PlasmidGPT-GRPO.

Target-Conditioned Molecular Ideation Model for Drug Discovery Research

Genos-m is a foundation model for human-associated microbial genomes. It is trained to model microbial DNA sequences at single-nucleotide resolution and supports ultra-long genomic contexts up to one million tokens.

Qwen3-8B-syco_med-gated-attention-FT is a plug-and-play gated attention weight released for AI safety research.

LoRA fine-tune of Qwen3.5-9B on synthetic clinical triage Q&A pairs generated from PubMed Central open-access papers. The model is specialized for emergency-medicine decision-making: triaging patients, applying clinical decision rules, and generating protocol-grounded triage recommendations.

Gemma 4 E2B fine-tuned on 225K drug–target pairs for novel small-molecule generation.

MedPsy-4B is a state-of-the-art, text-only medical and healthcare language model purpose-built for edge deployment. Built on top of Qwen3-4B-Thinking-2507 and post-trained with a multi-stage pipeline (supervised fine-tuning + reinforcement learning) on curated medical data, it surpasses models…

MedPsy-1.7B is a state-of-the-art, text-only medical and healthcare language model purpose-built for edge and smartphone deployment. Built on top of Qwen3-1.7B (operated in thinking mode, i.e. with enable_thinking=True) and post-trained with a multi-stage pipeline (supervised fine-tuning +…

Duchifat-2.3-Instruct is a state-of-the-art, instruction-tuned Large Language Model developed by TopAI. As the flagship of the Duchifat series, this model represents a fundamental breakthrough in how Hebrew is processed, reasoned, and generated in the LLM era.

Fine-tuned version of google/gemma-4-E4B-it across three professional domains — Medical, Legal, and Finance — using QLoRA (4-bit NF4) with Optuna-tuned hyperparameters, trained on Kaggle T4 GPU.

L1 (Learning Unit 1) is the first language model from Lunit and Lunit Consortium, purpose-built for the medical domain. Derived from Gravity-16B-A3B-Base, L1 is designed for clinical reasoning and decision support.

# or·a·cle /ˈôrəkəl/ — a source of wise counsel; one who provides authoritative knowledge. From Latin ōrāculum, meaning divine announcement. In computer science, an oracle is a black box that always returns the correct answer — you don't ask it how it knows, you ask and it answers.

Vortex Scientific is a from-scratch AI model family designed for deep scientific reasoning. Built from the ground up with a novel hybrid state-space + attention architecture, optimized for consumer laptop hardware (Apple Silicon MacBooks and Nvidia 4060 laptop GPUs).

This repository contains the model presented in D3LM: A Discrete DNA Diffusion Language Model for Bidirectional DNA Understanding and Generation.

A compact protein language model distilled from ProtGPT2 using complementary-regularizer distillation---a method that combines uncertainty-aware position weighting with calibration-aware label smoothing to achieve 31% better perplexity than standard knowledge distillation at 3.8x compression.

A compact protein language model distilled from ProtGPT2 using complementary-regularizer distillation---a method that combines uncertainty-aware position weighting with calibration-aware label smoothing to achieve 54% better perplexity than standard knowledge distillation at 9.4x compression.

A compact protein language model distilled from ProtGPT2 using complementary-regularizer distillation---a method that combines uncertainty-aware position weighting with calibration-aware label smoothing to achieve 87% better perplexity than standard knowledge distillation at 20x compression.

From Inquiry to Decision: Building Trustworthy Medical AI