intellix
Intellix is a high-capacity, fine-tuned large language model (LLM) designed specifically for enterprise-grade applications. The model was fine-tuned...
Метка: sft
Nova-Qwen-14B-LoRA
LoRA adapter for Qwen2.5-14B-Instruct, fine-tuned on GPT-4o conversations to create a warm, creative, and intelligent conversational model. Target...
LFM2.5-1.2B-Instruct-mobile-actions
Тонкая настройка LoRA LiquidAI/LFM2.5-1.2B — Инструкция по Google/мобильным действиям для вызова функции на устройстве на Android. Модель переводит...
Asterisk-135M
Asterisk is a research implementation that combines the ASPP (Adjacency-Structured Parallel Propagation) operator with standard attention mechanisms to...
functiongemma-hermes-3k-ft
This model is a fine-tuned version of Google’s FunctionGemma (270M), trained on a curated subset of the Hermes...
gpt-oss-20b-clinical-cot-gguf
Этот репозиторий предоставляет GGUF сборки клинической модели рассуждений, которая была точно настроена из unsloth/gpt-oss-20b-BF16. На медицинские вопросы дается...
smallcoder-303m
SmallCoder is a 303M parameter LLaMA-style language model trained from scratch for code generation and algorithmic reasoning. This...
Qwen-3B-Intent-Microplan-v2
“Local-first 3B model for VR / game companions that outputs strict {dialog, intent, microplan} JSON from a CONTEXT...
LiquidAI-LFM2-1.2B-Extract-ja-pii-finetuned
LiquidAI/LFM2-1.2B-Extract finetuned on Japanese content to output JSON with PII. The model should output only single json with...
lfm2-vl-furigana-ocr
This model is a fine-tuned version of LiquidAI/LFM2-VL-1.6B. It has been trained using TRL. — PEFT 0.17.1 —...