Introducing a new LLM model from Project Fluently. The goal of this model is to improve the base model by training it on diverse datasets. This model is obtained by SFT and GRPO training and step-by-step merging. — Developed by: @fluently — Model type: Causal Language Models (Qwen3ForCausalLM, LM Transformer) — Number of Parameters: 1.7B — Number of Paramaters (Non-Embedding): 1.4B — Number of Layers: 28 — Number of Attention Heads (GQA): 16 for Q and 8 for KV — Context Length: 32,768 — License: Apache-2.0 Here provides a code snippet with applychattemplate to show you how to load the tokenizer and model and how to generate contents. For local use, applications such as Ollama, LMStudio, MLX-LM, llama.cpp, and KTransformers have also supported Qwen3. > [!TIP] > The enablethinking` switch is also available in APIs created by SGLang and vLLM. By default, Qwen3 has thinking capabilities enabled, similar to QwQ-32B. This means the model will use its reasoning abilities to enhance the quality of generated responses. For example, when explicitly setting enablethinking=True or leaving it as the default value in tokenizer.applychattemplate`, the model will engage its thinking mode. In this…
Модальности:
Генерация текста
Области применения:
Генерация кода Диалог / чат
Задача: Генерация текста
Автор: fluently
Теги: qwen3, fluently, fluently-lm, trained, merged, sft, trl, unsloth
Лайков: 3 | Загрузок: 82
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
