metadata
base_model: anthonym21/Eve-2-MoE-NanoSQL-272M
tags:
- gguf
- quantized
- moe
- eve-2
license: apache-2.0
Eve-2-MoE-NanoSQL-272M - GGUF
GGUF quantizations of anthonym21/Eve-2-MoE-NanoSQL-272M.
Quantization Variants
| Quantization | Filename | Size |
|---|---|---|
| Q8_0 | Eve-2-MoE-NanoSQL-272M-Q8_0.gguf | 290.9 MB |
| Q4_K_M | Eve-2-MoE-NanoSQL-272M-Q4_K_M.gguf | 189.5 MB |
Usage with Ollama
ollama run anthonym21/eve-2-moe-nanosql-272m
Usage with llama.cpp
llama-cli -m Eve-2-MoE-NanoSQL-272M-Q4_K_M.gguf -p "Your prompt here"
Architecture
- Type: DeepSeek-style Mixture of Experts (MoE)
- Parameters: 272M total
- Layers: 12
- Hidden dim: 512
- Experts: 8 routed (top-2) + 1 shared per layer
- Context: 2048 tokens
- Tokenizer: GPT-2
Parent Model
This is a quantized version of anthonym21/Eve-2-MoE-NanoSQL-272M.