menik1126/OVD-Math-1-data-FR-Step600-Historical

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 20, 2026Architecture:Transformer Featherless Exclusive Cold

The menik1126/OVD-Math-1-data-FR-Step600-Historical model is a 1.5 billion parameter language model from the OVD collection, specifically representing the historical 1-data experiment at step 600. It is designed for inference tasks and includes its tokenizer. This model is part of a series focused on specific data configurations and training steps, offering insights into the OVD project's development.

Loading preview...

Model Overview

This model, menik1126/OVD-Math-1-data-FR-Step600-Historical, is a 1.5 billion parameter language model. It represents a specific historical snapshot from the OVD collection, corresponding to the "1-data full" experiment at training step 600. The model includes both its inference weights and tokenizer.

Key Characteristics

  • Parameter Count: 1.5 billion parameters.
  • Context Length: 32768 tokens.
  • Origin: Part of the broader OVD collection by menik1126.
  • Purpose: Provides a historical reference point for the 1-data experiment within the OVD project.

Use Cases

This model is particularly useful for:

  • Research and Analysis: Studying the performance and characteristics of the OVD project at a specific training stage.
  • Historical Benchmarking: Comparing the evolution of the OVD models over different training steps and data configurations.
  • Inference: Utilizing the model for general language inference tasks, given its historical context.

Finetunes
1 models