Find open-source science resources

Base model: google/gemma-4-26b-it Architecture: MoE — 26B total / ≈4B active parameters (1 shared expert + 8 routed from a pool of 128 per MoE layer, 30 MoE layers) Method: Activation-directed expert surgery — 128 → 64 experts per layer (50% reduction) Quantization: Q4KM (≈9.7 GB on disk) Tags:…

# 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.

darkknight25/deepseek-16b-medical-GPT is a fine-tuned version of deepseek-ai/deepseek-l6b-moe-chat, optimized for medical question answering, reasoning, and clinical summarization using QLoRA and open-access healthcare datasets.

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 87% better perplexity than standard knowledge distillation at 20x compression.

# ChemGPT 1.2B ChemGPT is based on the GPT-Neo model and was introduced in the paper Neural Scaling of Deep Chemical Models.

# ChemGPT 19M ChemGPT is based on the GPT-Neo model and was introduced in the paper Neural Scaling of Deep Chemical Models.

# ChemGPT 4.7M ChemGPT is based on the GPT-Neo model and was introduced in the paper Neural Scaling of Deep Chemical Models.

InstaNovo-P is a specialized transformer-based model for de novo peptide sequencing from phosphoproteomics mass spectrometry data. This model is specifically trained and optimized for identifying phosphorylated peptides and their modification sites.

# InstaNovo: De novo Peptide Sequencing Model ## Model Description

# InstaNovo: De novo Peptide Sequencing Model ## Model Description

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.

中文版说明

HuatuoGPT-o1-7B

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.

Welcome to the repository for Nidum-Limitless-Gemma-2B-GGUF, an advanced language model that provides unrestricted and versatile responses across a wide range of topics. This version is designed for maximum flexibility, allowing you to run it on both CPU and GPU.

Abstract:

Using llama.cpp release b5466 for quantization.

Dans-PersonalityEngine-V1.3.0-24b Dans-PersonalityEngine-V1.3.0-24b ⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢀⠀⠄⠀⡂⠀⠁⡄⢀⠁⢀⣈⡄⠌⠐⠠⠤⠄⡀⠀⠀⠀⠀⠀⠀⠀⠀⠀ ⠀⠀⠀⠀⠀⠀⠀⠀⡄⠆⠀⢠⠀⠛⣸⣄⣶⣾⡷⡾⠘⠃⢀⠀⣴⠀⡄⠰⢆⣠⠘⠰⠀⡀⠀⠀⠀⠀⠀ ⠀⠀⠀⠀⠀⠀⠀⠀⠀⠃⠀⡋⢀⣤⡿⠟⠋⠁⠀⡠⠤⢇⠋⠀⠈⠃⢀⠀⠈⡡⠤⠀⠀⠁⢄⠀⠀⠀⠀ ⠀⠀⠀⠀⠀⠁⡂⠀⠀⣀⣔⣧⠟⠋⠀⢀⡄⠀⠪⣀⡂⢁⠛⢆⠀⠀⠀⢎⢀⠄⢡⠢⠛⠠⡀⠀⠄⠀⠀ ⠀⠀⡀⠡⢑⠌⠈⣧⣮⢾⢏⠁⠀⠀⡀⠠⠦⠈⠀⠞⠑⠁⠀⠀⢧⡄⠈⡜⠷⠒⢸⡇⠐⠇⠿⠈⣖⠂⠀…

Dans-PersonalityEngine-V1.2.0-24b ⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢀⠀⠄⠀⡂⠀⠁⡄⢀⠁⢀⣈⡄⠌⠐⠠⠤⠄⡀⠀⠀⠀⠀⠀⠀⠀⠀⠀ ⠀⠀⠀⠀⠀⠀⠀⠀⡄⠆⠀⢠⠀⠛⣸⣄⣶⣾⡷⡾⠘⠃⢀⠀⣴⠀⡄⠰⢆⣠⠘⠰⠀⡀⠀⠀⠀⠀⠀ ⠀⠀⠀⠀⠀⠀⠀⠀⠀⠃⠀⡋⢀⣤⡿⠟⠋⠁⠀⡠⠤⢇⠋⠀⠈⠃⢀⠀⠈⡡⠤⠀⠀⠁⢄⠀⠀⠀⠀ ⠀⠀⠀⠀⠀⠁⡂⠀⠀⣀⣔⣧⠟⠋⠀⢀⡄⠀⠪⣀⡂⢁⠛⢆⠀⠀⠀⢎⢀⠄⢡⠢⠛⠠⡀⠀⠄⠀⠀ ⠀⠀⡀⠡⢑⠌⠈⣧⣮⢾⢏⠁⠀⠀⡀⠠⠦⠈⠀⠞⠑⠁⠀⠀⢧⡄⠈⡜⠷⠒⢸⡇⠐⠇⠿⠈⣖⠂⠀ ⠀⢌⠀⠤⠀⢠⣞⣾⡗⠁⠀⠈⠁⢨⡼⠀⠀⠀⢀⠀⣀⡤⣄⠄⠈⢻⡇⠀⠐⣠⠜⠑⠁⠀⣀⡔⡿⠨⡄…

A domain-optimized reasoning model built on DeepSeek-R1-Distill-Qwen-32B, refined through a multi-stage pipeline of GPTQ quantization-aware training and QLoRA fine-tuning. Achieves 84% on MedQA — within 4 points of GPT-4o — in a ~20GB package that fits on a single L40/L40s GPU.

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.

Apertus-70B-MeditronFO is a 70B-parameter medical specialist LLM, produced by supervised fine-tuning of Apertus-70B-Instruct on the Fully Open Meditron Corpus.

InstaNovoPlus is a diffusion-based model for de novo peptide sequencing from mass spectrometry data. This model leverages multinomial diffusion for accurate, database-free peptide identification for large-scale proteomics experiments.

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

Target-Conditioned Molecular Ideation Model for Drug Discovery Research