25 lines
809 B
Markdown
25 lines
809 B
Markdown
---
|
|
license: apache-2.0
|
|
language:
|
|
- en
|
|
base_model:
|
|
- theprint/theprint-moe-8x3-0126
|
|
pipeline_tag: text-generation
|
|
tags:
|
|
- moe
|
|
- llama
|
|
---
|
|
<img src="theprint_18b_moe.png" width="420" />
|
|
|
|
# theprint-MoE-8x3-0126-GGUF
|
|
|
|
An 18B parameter Mixture of Experts model combining 8 specialized 3B experts, with 2 experts activated per token by default (configurable up to 4 at inference).
|
|
|
|
## Architecture
|
|
- Base model: theprint/GeneralChat-Llama3.2-3B (provides shared attention layers)
|
|
- Total parameters: ~18B
|
|
- Active parameters: ~5B (2 experts) or ~9B (4 experts)
|
|
- Gate mode: Hidden (prompt-based router initialization)
|
|
|
|
## Full Model
|
|
For more information about this model, including access to the safetensor files, please see [theprint/theprint-moe-8x3-0126](https://huggingface.co/theprint/theprint-moe-8x3-0126). |