ferrazzipietro/Qwen3-1.7B-reas-int-065

TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:2BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 3, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The ferrazzipietro/Qwen3-1.7B-reas-int-065 model is a 2 billion parameter language model, fine-tuned from the Qwen/Qwen3-1.7B architecture. It features a 32768 token context length, making it suitable for tasks requiring extensive contextual understanding. This model is a specialized iteration of the Qwen3-1.7B base, though its specific differentiation for reasoning or other tasks is not detailed in the available information.

Loading preview...

Model Overview

ferrazzipietro/Qwen3-1.7B-reas-int-065 is a 2 billion parameter language model derived from the Qwen/Qwen3-1.7B base model. It supports a substantial context length of 32768 tokens, allowing it to process and generate longer sequences of text. The model has undergone fine-tuning, though the specific dataset used for this process is not disclosed in the available documentation.

Training Details

The fine-tuning process for this model involved specific hyperparameters:

  • Learning Rate: 5e-06
  • Batch Sizes: train_batch_size of 4, eval_batch_size of 256
  • Gradient Accumulation: 8 steps, leading to a total_train_batch_size of 64
  • Optimizer: ADAMW_TORCH with betas=(0.9, 0.95) and epsilon=1e-12
  • LR Scheduler: Cosine type with a warmup ratio of 0.1
  • Epochs: Trained for 1 epoch

The training utilized a multi-GPU setup with 2 devices. The model was developed using Transformers 4.57.0, Pytorch 2.14.0+cu130, Datasets 5.0.1, and Tokenizers 0.22.2.

Intended Uses and Limitations

Specific intended uses and limitations are not detailed in the provided model card. Users should conduct their own evaluations to determine suitability for particular applications, especially given the unspecified fine-tuning dataset.

Finetunes
5 models