gemma-4-12B-agentic-fable5-composer2.5-v2-nvfp4
> Original fine-tune by yuxinlu1 (gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2); this repo is an NVFP4 (MLX) requant for fast local inference on...
> Original fine-tune by yuxinlu1 (gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2); this repo is an NVFP4 (MLX) requant for fast local inference on...
Qwen-AgentWorld-35B-A3B-GPTQ-Pro-Int4 is a GPTQ-quantized checkpoint intended for efficient GPU inference, published by groxaxo. It is intended for open-source...
INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED...
This is a highly optimized, lightweight (270M parameters) function-calling model fine-tuned on top of google/functiongemma-270m-it. It is specifically...
Project page: athena.openscientist.ai · Code: mims-harvard/ATHENA ATHENA-R1 is an AI agent for treatment reasoning, trained through reinforcement learning...
~ 69M-параметр глубины — повторяющийся чат и модель использования инструмента. Он был переоборудован из ванильного основания ламы в...
Версия quantifiée en GGUF (Q4KM) de gemma-4-E2B-it-uncensored-agentic, un modèle ajusté spécifiquement pour les tâches agentiques complexes, l’utilisation d’...
KoHRM-Text-1.4B is a scratch-pretrained Korean/English/code/terminal/tool-use model built from the sapientinc/HRM-Text PrefixLM training stack. This is not a continued...
This repository contains the merged SkillFlow Supervisor model weights. — Code: https://github.com/beita6969/SkillFlow — Dataset: https://huggingface.co/datasets/beita6969/SkillFlow-Dataset — Base model:...
LoRA adapter fine-tuned from google/gemma-4-26B-A4B-it on Hermes Reasoning Tool Use dataset — 10K subset of tool-calling conversations with...