File size: 2,036 Bytes
616b8e9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 | {
"name": "Lumina-Lite-2.2B Optimized Autoregressive Transformer",
"layers": [
{
"type": "Embedding",
"params": {
"num_embeddings": 50272,
"embedding_dim": 2048
}
},
{
"type": "TransformerBlock",
"params": {
"layers": 28,
"hidden_size": 2048,
"num_attention_heads": 16,
"num_key_value_heads": 4,
"head_dim": 128,
"mlp_intermediate_size": 5504,
"normalization": "RMSNorm",
"activation": "SwiGLU",
"positional_encoding": "RoPE (Rotary Positional Embeddings)",
"attention_type": "Grouped-Query Attention (GQA)"
}
},
{
"type": "Linear",
"params": {
"in_features": 2048,
"out_features": 5504,
"description": "SwiGLU Gate and Up Projection"
}
},
{
"type": "Linear",
"params": {
"in_features": 5504,
"out_features": 2048,
"description": "MLP Down Projection"
}
},
{
"type": "RMSNorm",
"params": {
"normalized_shape": 2048,
"eps": 0.00001
}
},
{
"type": "Linear",
"params": {
"in_features": 2048,
"out_features": 50272,
"bias": false,
"description": "Language Modeling Head"
}
}
],
"explanation": "Lumina-Lite-2.2B utilizes a 'deep-and-narrow' topology to optimize for high-throughput within a 6GB VRAM limit. The implementation of Grouped-Query Attention (GQA) reduces the KV cache footprint by a factor of 4 compared to multi-head attention, enabling longer context windows and larger batch sizes on consumer hardware. SwiGLU activation and RMSNorm provide superior gradient flow and training stability over standard GeLU/LayerNorm, while RoPE ensures the model maintains spatial awareness of tokens without absolute position bias. The architecture is specifically designed to facilitate 4-bit NF4 quantization, making it highly efficient for deployment via bitsandbytes or AutoGPTQ."
} |