miiikiik/Qwen3-8B-music-movie-coa-sft-v2

TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 15, 2026License:otherArchitecture:Transformer Featherless Exclusive Cold

The miiikiik/Qwen3-8B-music-movie-coa-sft-v2 is an 8 billion parameter Qwen3 model, fine-tuned from a previous music-oriented version on the movie_coa_sft_v2 dataset. This model is specialized for tasks related to movie content, building upon its foundational capabilities in music. It features a context length of 32768 tokens, making it suitable for processing extensive textual inputs in its domain.

Loading preview...

Model Overview

The miiikiik/Qwen3-8B-music-movie-coa-sft-v2 is an 8 billion parameter language model based on the Qwen3 architecture. It is a fine-tuned iteration of a prior model, specifically adapted from Qwen3-8B-music-coa-sft.

Key Specialization

This model has undergone further fine-tuning on the movie_coa_sft_v2 dataset, indicating a specialization in processing and generating content related to movies. Its previous iteration focused on music, suggesting a potential for nuanced understanding across entertainment domains.

Training Details

The fine-tuning process utilized the following hyperparameters:

  • Learning Rate: 1e-05
  • Batch Size: 2 (train), 8 (eval) with 4 gradient accumulation steps, resulting in a total effective batch size of 64.
  • Optimizer: AdamW with betas=(0.9, 0.999) and epsilon=1e-08.
  • Scheduler: Cosine learning rate scheduler with a 0.1 warmup ratio.
  • Epochs: 3.0

Intended Use Cases

Given its fine-tuning on movie-related data, this model is likely best suited for applications involving:

  • Movie content analysis
  • Generating movie-related text
  • Understanding movie plots, characters, or reviews

Further details on specific intended uses and limitations are not provided in the original model card.