AstraGPTCoder-7B
Custom Architecture · Custom BPE Tokenizer · Reasoning Fine-Tuned on Dual RTX 4090 Every layer of AstraGPT-7B was...
Custom Architecture · Custom BPE Tokenizer · Reasoning Fine-Tuned on Dual RTX 4090 Every layer of AstraGPT-7B was...
ConicAI LLM Model is a parameter-efficient fine-tuned coding assistant built using LoRA on top of Qwen2.5-Coder. It is...
Cyber-Quack-14B — это специализированная тонкая настройка архитектуры Qwen2.5-14B, оптимизированная для операций Red Team, помощи в тестировании на проникновение...
3-4x fewer tokens than OmniLottie (CVPR 2026) for generating Lottie animations. Now with character animation support. AnimTOON is...
A specialized Chinese private equity fund analysis model, fine-tuned from Qwen2.5-3B-Instruct using QLoRA knowledge distillation. MachFund-1 is trained...
Important update: we recently discovered that the checkpoint uploaded previously was from an intermediate training step and did...
A 7B code model fine-tuned on 235 Laravel 13.x instruction-to-code pairs with Laravel Boost guidelines baked into training....
Production-ready merged model (base + LoRA fused into 16-bit weights). Trained on a single NVIDIA A40 (44 GB)...
INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED...
OpenSWE is the largest fully transparent framework for SWE agent training in Python, comprising 45,320 executable Docker environments...