Model Stock merge
According to the model card, the model was merged with the Model Stock method using MathGenie/MathCoder2-Llama-3-8B as base and bfloat16 dtype.
Open Source Model Profile · sethuiyer
Llamaverse-3.1-8B-Instruct
Llamaverse-3.1-8B-Instruct is an 8.03B-parameter Llama merge from sethuiyer. Its model card documents a Model Stock merge on a MathCoder2 base.
- Publisher
- sethuiyer
- Task
- text-generation
- Model type
- llama
- License
- llama3.1
- Library
- transformers
- Publication status
- Approved for indexing
Model overview
Llamaverse-3.1-8B-Instruct is published by sethuiyer as a text-generation model. Safetensors metadata reports 8,030,261,248 parameters, with LlamaForCausalLM and model type llama. According to the model card, it merges MathCoder2-Llama-3-8B with 10 specialized models using Model Stock.
Recorded capabilities
Ten-model merge list
The model card lists 10 merged models, including NVIDIA OpenMath2, Hercules-6.1, Lumimaid, UltraMedical, storytelling, Samantha, LewdPlay, Refueled, Instruct-Coder, and Skywork-o1 variants.
Multidisciplinary publisher description
The publisher describes the result as a unified multidisciplinary model covering mathematics, biomedical diagnostics, storytelling, and coding.
Use cases in the source record
- Instruction-style text generation across the mathematical, coding, biomedical, and storytelling domains named in the model card.
- Experiments with the publisher-mentioned Divine Intellect preset, as documented in the model card.
Limitations and unknowns
- No evaluation results were extracted from this record.
- No context-window value was extracted from this record.
- Provider state is historical snapshot data, not independently refreshed current availability.
- Capability and compatibility claims, including the Divine Intellect preset note, are publisher statements and were not independently verified.
Source and provenance
Source: sethuiyer/Llamaverse-3.1-8B-Instruct
Captured: Unknown. Processed: 2026-09-07T19:35:30.178575+00:00.
Llamaverse 8B A Unified Multidisciplinary Language Model Llamaverse-3.1-8B-Instruct is a state-of-the-art language model built on the foundation of MathCoder2-Llama-3-8B, pretrained on MathCode-Pile. This dataset, which embeds mathematical reasoning steps in natural language and code, provides a rock-solid foundation for advanced logical reasoning. By merging MathCoder2 with 10 specialized models using the Model Stock merge method, Llamaverse-3.1-8B-Instruct becomes an unparalleled polymath, excelling in mathematics, biomedical diagnostics, storytelling, coding, and more. This model was merged using the Model Stock merge method usin…
F001F002F003F004F005F006F007F009F010F011F012F013F014F015