MINZIK77/lm-sft-tulu-3b-ckpts

TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 14, 2026Architecture:Transformer Featherless Exclusive Cold

MINZIK77/lm-sft-tulu-3b-ckpts is a 3.1 billion parameter language model fine-tuned from Qwen/Qwen2.5-3B-Instruct with a context length of 32768 tokens. This model was trained using Supervised Fine-Tuning (SFT) via the TRL framework. It is designed for general text generation tasks, leveraging the capabilities of its base Qwen2.5-3B-Instruct architecture.

Loading preview...

Model Overview

MINZIK77/lm-sft-tulu-3b-ckpts is a 3.1 billion parameter language model, fine-tuned from the robust Qwen/Qwen2.5-3B-Instruct base model. It features a substantial context length of 32768 tokens, making it suitable for processing longer inputs and generating extended responses. The model was developed using Supervised Fine-Tuning (SFT) techniques, leveraging the TRL (Transformers Reinforcement Learning) framework.

Key Capabilities

  • Instruction Following: Inherits and refines the instruction-following capabilities of its Qwen2.5-3B-Instruct base.
  • Text Generation: Capable of generating coherent and contextually relevant text based on user prompts.
  • Extended Context: Benefits from a 32K token context window, allowing for more detailed and comprehensive interactions.

Training Details

The model underwent a Supervised Fine-Tuning (SFT) process. The training utilized specific versions of popular machine learning frameworks:

  • TRL: 1.7.1
  • Transformers: 4.57.6
  • Pytorch: 2.10.0
  • Datasets: 4.7.0
  • Tokenizers: 0.22.2

Good For

  • General-purpose text generation tasks.
  • Applications requiring a model with a relatively small parameter count but a large context window.
  • Developers looking for a fine-tuned Qwen2.5-3B-Instruct variant for specific SFT-driven use cases.