yuq-zhou/2026-05-o-b0p3-a1p0-gc1p0-exp-td4p0-tw10p0-mbz-r1-7

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 11, 2026Architecture:Transformer Featherless Exclusive Cold

The yuq-zhou/2026-05-o-b0p3-a1p0-gc1p0-exp-td4p0-tw10p0-mbz-r1-7 is a 7.6 billion parameter causal language model developed by yuq-zhou. This model is provided as a standard HuggingFace checkpoint, primarily serving as a research artifact backup. Its specific architecture and training details are not publicly detailed, suggesting its use for internal research or experimental purposes. Developers can integrate it using AutoModelForCausalLM.from_pretrained for further experimentation.

Loading preview...

Model Overview

The yuq-zhou/2026-05-o-b0p3-a1p0-gc1p0-exp-td4p0-tw10p0-mbz-r1-7 is a 7.6 billion parameter causal language model. It is presented as a standard HuggingFace checkpoint, making it compatible with AutoModelForCausalLM.from_pretrained for easy integration into existing workflows.

Key Characteristics

  • Parameter Count: 7.6 billion parameters.
  • Context Length: Supports a context window of 32,768 tokens.
  • Format: Provided in a standard HuggingFace format, ensuring broad compatibility with the HuggingFace ecosystem.

Intended Use

This model is primarily designated as a research artifact backup. This suggests its main purpose is for internal research, experimental validation, or as a snapshot of a development phase. Specific performance metrics, training datasets, or fine-tuning objectives are not detailed in the available documentation.

When to Consider This Model

  • Research and Experimentation: Ideal for researchers or developers looking to explore a 7.6B parameter model with a substantial context window, particularly if its specific experimental lineage aligns with their research interests.
  • Baseline for Custom Fine-tuning: Can serve as a base model for further fine-tuning on domain-specific datasets, given its standard HuggingFace format.

Due to the limited public documentation, users should approach this model with the understanding that it is an experimental artifact. Detailed performance characteristics and specific use case optimizations are not provided.

Finetunes
2 models