KKHYA/qwen3-1.7b-fft-if

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:2BQuant:BF16Ctx Length:32kPublished:May 24, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

The KKHYA/qwen3-1.7b-fft-if model is a 2 billion parameter language model, fine-tuned from Qwen/Qwen3-1.7B. It was trained on a diverse set of datasets including mft_tulu3_personas_if, mft_oasst1, mft_oasst2, mft_coconot, mft_aya, and mft_daring_anteater. This model is designed for general language generation tasks, leveraging its fine-tuning on multiple instruction-following and conversational datasets.

Loading preview...

Model Overview

This model, KKHYA/qwen3-1.7b-fft-if, is a fine-tuned variant of the 2 billion parameter Qwen3-1.7B base model. It has been specifically adapted through further training on a combination of diverse datasets, aiming to enhance its conversational and instruction-following capabilities.

Key Training Details

The model underwent fine-tuning using a comprehensive set of datasets, including:

  • mft_tulu3_personas_if
  • mft_oasst1
  • mft_oasst2
  • mft_coconot
  • mft_aya
  • mft_daring_anteater

Training was conducted with a learning rate of 1e-05, a total batch size of 128, and utilized a cosine learning rate scheduler over 2 epochs. The optimizer used was ADAMW_TORCH_FUSED.

Potential Use Cases

Given its fine-tuning on instruction-following and conversational datasets, this model is likely suitable for:

  • General-purpose text generation: Creating coherent and contextually relevant text.
  • Instruction following: Responding to prompts and instructions effectively.
  • Conversational AI: Engaging in dialogue and generating human-like responses.