yusuf229/mam-turkish-790m

TEXT GENERATIONConcurrent Unit Cost:1Model Size:0.79BQuant:BF16Context Size:32kPublished:May 26, 2026Architecture:Transformer0.0K Featherless Exclusive Cold

The yusuf229/mam-turkish-790m model is a language model trained from scratch, though specific architectural details and parameter count are not provided. It was developed by yusuf229. The model's primary characteristics and intended use cases are not detailed in the available information, making its specific differentiators and optimal applications currently unknown.

Loading preview...

Overview

The yusuf229/mam-turkish-790m model is a language model that was trained from scratch. Specific details regarding its architecture, parameter count, and the dataset used for training are not provided in the available documentation.

Training Details

The model was trained using the following hyperparameters:

  • Learning Rate: 4e-05
  • Training Batch Size: 4
  • Evaluation Batch Size: 8
  • Seed: 42
  • Optimizer: ADAMW_BNB with betas=(0.9, 0.999) and epsilon=1e-08
  • LR Scheduler Type: Linear
  • Training Steps: 25000

Framework Versions

The training process utilized:

  • Transformers 5.12.1
  • Pytorch 2.11.0+cu128
  • Datasets 4.0.0
  • Tokenizers 0.22.2

Intended Uses & Limitations

Currently, there is no specific information available regarding the model's intended uses, limitations, or evaluation data. Users should exercise caution and conduct their own evaluations before deploying this model for specific applications, as its capabilities and performance characteristics are not yet documented.