willow-alpha-gguf
— Исследования — Бенчмаркинг — Эксперименты по предварительной подготовке — Эксперименты по тонкой настройке — Разработка модели малого...
Метка: causal-lm
IDA_Edge
IDA Edge is the lightweight native computational body of the IDA family. It is not a generic chatbot,...
GPT-X2-125M-CIx-Long-Context
This model is a custom-code derivative of AxiomicLabs/GPT-X2-125M, adapted for experimental long-context causal language modeling and architecture research....
nanowhale-100m-base
A small ~110M parameter language model implementing the DeepSeek-V4 architecture from scratch. This is the pretrained base model...
FinAI
Meridian.AI is a finance-specialized language model that continuously fine-tunes a Qwen2.5-0.5B backbone every hour on 25+ finance and...
ruGPT3XL
A 1.3B-parameter GPT-2-style language model for Russian, converted from the original ai-forever/rugpt3xl Megatron-LM checkpoint into a native HuggingFace...
Stentor-Big
Stentor-Big is a direct expansion of the original Stentor-30M model developed by Kai Izumoto (StentorLabs). The architecture was...
Binary-Addition-LLM-POC
A tiny tokenizer-free / bit-level (base-2) calculator proof of concept. This repository ships custom modeling.py / configuration.py, so...
lumichats-v1.1
— 💬 Enhanced Conversational Abilities: Fine-tuned on FineTome-100k for natural, engaging dialogue — 🚀 Efficient & Fast: —...
Qwerky-Optimized-Llama3.1-Mamba-0.2-8B-Instruct
This is a hybrid Mamba-Transformer model based on the Llama 3.1 architecture, distilled from Llama 3.3 70B into...