KhaledAshraf/qwen3-finetuned

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.8BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 18, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

KhaledAshraf/qwen3-finetuned is a fine-tuned version of the Qwen3-0.6B causal language model, developed by KhaledAshraf. This compact model, with 0.8 billion parameters and a 32768-token context length, was fine-tuned on an unspecified dataset. It demonstrates a validation loss of 2.0026, indicating its performance on the evaluation set. This model is suitable for applications requiring a smaller, efficient language model derived from the Qwen3 architecture.

Loading preview...

Model Overview

KhaledAshraf/qwen3-finetuned is a specialized language model derived from the Qwen3-0.6B architecture. This version has been fine-tuned by KhaledAshraf, resulting in a model with 0.8 billion parameters and a substantial 32768-token context length. The fine-tuning process involved an unspecified dataset, and the model achieved a validation loss of 2.0026 on its evaluation set.

Key Characteristics

  • Base Model: Qwen/Qwen3-0.6B
  • Parameter Count: 0.8 billion
  • Context Length: 32768 tokens
  • Training Objective: Achieved a final validation loss of 2.0026 after 3 epochs.
  • Training Hyperparameters: Utilized a learning rate of 2e-05, a train batch size of 2 (total batch size 16 with gradient accumulation), and the AdamW_TORCH_FUSED optimizer.

Intended Use Cases

Given its compact size and fine-tuned nature, this model is suitable for:

  • Applications requiring a smaller, efficient language model.
  • Scenarios where the Qwen3 architecture is preferred, but a custom fine-tuning is beneficial.
  • Further experimentation or fine-tuning on specific, domain-relevant datasets.