osieosie/tmax-qwen3-4b-sft-20260317-100k-asst-loss-e1-lr2e-6

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:4BQuant:BF16Ctx Length:32kPublished:Mar 19, 2026Architecture:Transformer Warm

The osieosie/tmax-qwen3-4b-sft-20260317-100k-asst-loss-e1-lr2e-6 is a 4 billion parameter instruction-tuned causal language model, fine-tuned from a Qwen3 base model. This model was trained using Supervised Fine-Tuning (SFT) with the TRL library. It is designed for general text generation tasks, leveraging its fine-tuned capabilities to respond to user prompts.

Loading preview...

Model Overview

The osieosie/tmax-qwen3-4b-sft-20260317-100k-asst-loss-e1-lr2e-6 is a 4 billion parameter language model, fine-tuned from a Qwen3 base architecture. This model has undergone Supervised Fine-Tuning (SFT) using the Hugging Face TRL library, indicating a focus on improving its ability to follow instructions and generate coherent responses.

Key Capabilities

  • Instruction Following: Optimized through SFT to better understand and respond to user prompts.
  • Text Generation: Capable of generating human-like text based on given instructions.
  • TRL Framework: Developed using the TRL (Transformers Reinforcement Learning) library, which is commonly used for fine-tuning large language models.

Training Details

The model was trained with specific versions of key frameworks:

  • TRL: 0.29.0
  • Transformers: 5.3.0
  • PyTorch: 2.8.0
  • Datasets: 4.6.1
  • Tokenizers: 0.22.2

Good For

  • General Conversational AI: Suitable for applications requiring a model to engage in dialogue and answer questions.
  • Instruction-based Tasks: Effective for tasks where clear instructions are provided, such as summarization, question answering, or content creation based on specific prompts.