Qwen3-4B-Base-GRPO
Qwen3-4B-Base-GRPO — это контрольная точка после RL, обученная с помощью фреймворка verl. Он начинается с Qwen3-4B-Base и применяет...
Qwen3-4B-Base-GRPO — это контрольная точка после RL, обученная с помощью фреймворка verl. Он начинается с Qwen3-4B-Base и применяет...
Полная SFT-тонкая настройка google/gemma-4-E4B-it на полном наборе данных с открытым исходным кодом GLM-5.1-1000000x (~614k разговоров), обученная с помощью...
This model was converted to GGUF format from Surpem/Supertron1-4B using llama.cpp via the ggml.ai’s GGUF-my-repo space. Refer to...
Luna is a conversational AI model designed for immersive roleplay (RP) and natural chatting. It has been carefully...
This model is a fine-tuned version of meta-llama/Llama-3.2-3B-Instruct trained on the openai/gsm8k dataset. It has been trained to...
Модель Türkçe matematik problemlerini çözmek için SFT GRPO ile тонкой настройки edilmiş. — Базовая модель: unsloth/Qwen3-4B-Base — Eğitim:...
Qwen3-4B-SFT is a reasoning-focused model derived from Qwen3-4B-Base via full-parameter fine-tuning on the verl framework. There is a...
— Method: GPTQ — Bits: 4 — Group size: 128 — descact: False — damppercent: 0.1 — Calibration...
IntelliTeX is an experimental Small Language Model (SLM) study for converting English, spoken-style math descriptions into a single...
> VibeThinker-1.5B is a 1.5‑billion‑parameter dense language model from WeiboAI, fine‑tuned from Qwen2.5-Math-1.5B and purpose‑built for competitive math...