サイト内検索
AI モデル 84761
- PatronusAI_-_Llama-3-Patronus-Lynx-8B-Instruct-v1.1-gguf↗
RichardErkhov
- Qwen3.5-0.8B-heretic↗
saidutta69
- HOT-Step-CPP-StableStep↗
scragnog
- Qwen3-4B-GGUF↗
second-state
- roberta-large-nli-mean-tokens↗
sentence-transformers
- ChemBERTa-zinc-base-v1↗
seyonec
Deep learning for chemistry and materials science remains a novel field with lots of potiential. However, the popularity of transfer learning based methods in areas such as NLP and computer vision have not yet been effectively developed in computational chemistry + machine learning. Using HuggingFace's suite of models and the ByteLevel tokenizer, we are able to train on a large corpus of 100k SMILES strings from a commonly known benchmark dataset, ZINC. Training RoBERTa over 5 epochs, the model achieves a decent loss of 0.398, but may likely continue to decline if trained for a larger number of epochs. The model can predict tokens within a SMILES sequence/molecule, allowing for variants of a molecule within discoverable chemical space to be predicted. By applying the representations of functional groups and atoms learned by the model, we can try to tackle problems of toxicity, solubility, drug-likeness, and synthesis accessibility on smaller datasets using the learned representations as features for graph convolution and attention models on the graph structure of molecules, as well as fine-tuning of BERT. Finally, we propose the use of attention visualization as a helpful tool for chemistry practitioners and students to quickly identify important substructures in various chemical properties.
- A.X-3.1-Light↗
skt
- Llama3.1-elm-turbo-4B-instruct↗
slicexai
- Bielik-11B-v2.0-Instruct-GGUF↗
speakleash
- Semantic-Bridge-Comfy↗
t8star
本仓库发布两份 **MiniMax H3 CONDITIONING 语义适配器**的 T8 Compat 封装,供支持 Semantic Bridge 的 ComfyUI 节点读取。它们不是 H3 主模型、LoRA、文本编码器、高清放大器或加速模型,不替代现有 H3 主模型、CLIP 和 VAE,也不需要下载 SenseNova 教师模型。 > 状态说明(2026-09-17):转换模型已发布。T8 本地实现及正式核心目录同步已完成,Bridge和受影响范围443项CPU回归、5份实际Core工作流校验及指定两段共8秒双MODEL/Relay机械验证通过;仍为EXP,集中画面与生成对白/歌唱/接缝人审待。全仓扩大诊断因基线已有失败而保留未完成记录,不能冒称整仓全绿。新节点代码尚未推送GitHub/发布Registry;下载这些权重不会给已发布的v1.83.0自动增加节点。使用前确认安装版本确实包含下列节点,重启ComfyUI载入;本地交付或模型发布不等于人审验收及公开节点版本发布。 用途定位来自上游描述,不是所有提示词的效果保证。先用原版 0.10 做对照;动作场景可以单独试 BUNNY。**BUNNY 是另一份独立训练权重,不是第一份模型的转换版。两者不要串联作用在同一份 CONDITIONING 上。**
