Add config.json

config.json

@@ -0,0 +1,81 @@
+{
+  "name": "HFMT-8 (High-Fidelity Multimodal Transformer)",
+  "layers": [
+    {
+      "type": "Conv2d",
+      "params": {
+        "in_channels": 3,
+        "out_channels": 1152,
+        "kernel_size": 14,
+        "stride": 14,
+        "note": "SigLIP-style Patch Embedding for high-resolution input"
+      }
+    },
+    {
+      "type": "TransformerBlock",
+      "params": {
+        "hidden_size": 1152,
+        "num_heads": 16,
+        "mlp_ratio": 4,
+        "activation": "GELU",
+        "note": "SigLIP SO400M Vision Encoder Backbone"
+      }
+    },
+    {
+      "type": "Conv2d",
+      "params": {
+        "in_channels": 1152,
+        "out_channels": 1152,
+        "kernel_size": 2,
+        "stride": 2,
+        "note": "Adaptive Patch-Merging for 50% Visual Token Reduction"
+      }
+    },
+    {
+      "type": "Linear",
+      "params": {
+        "in_features": 1152,
+        "out_features": 4096,
+        "note": "Cross-Modal Projection Bridge to LLM Latent Space"
+      }
+    },
+    {
+      "type": "TransformerBlock",
+      "params": {
+        "hidden_size": 4096,
+        "num_attention_heads": 32,
+        "num_key_value_groups": 8,
+        "attention_type": "Grouped-Query Attention (GQA)",
+        "positional_encoding": "RoPE (Rotary)",
+        "note": "Llama-3 Decoder Block with 4-bit NF4 Quantization Support"
+      }
+    },
+    {
+      "type": "Linear",
+      "params": {
+        "in_features": 4096,
+        "out_features": 14336,
+        "activation": "SwiGLU",
+        "note": "Gated Linear Unit for Enhanced Representational Capacity"
+      }
+    },
+    {
+      "type": "RMSNorm",
+      "params": {
+        "normalized_shape": 4096,
+        "eps": 0.00001,
+        "note": "Pre-block Normalization for Numerical Stability"
+      }
+    },
+    {
+      "type": "Linear",
+      "params": {
+        "in_features": 4096,
+        "out_features": 128256,
+        "bias": false,
+        "note": "Language Modeling Head (Uncensored Configuration)"
+      }
+    }
+  ],
+  "explanation": "The HFMT-8 architecture is designed to balance multimodal reasoning with extreme memory efficiency for 8GB VRAM environments. By utilizing SigLIP for vision, we achieve better zero-shot alignment than CLIP with fewer parameters. The 'C-Abstractor' via patch-merging reduces visual tokens significantly, preventing KV-cache explosion during multimodal tasks. The LLM backbone utilizes Grouped-Query Attention (GQA) to minimize the memory footprint of the attention mechanism by a factor of 4, and the transition to 4-bit NF4 quantization ensures the 8B parameter model fits comfortably within 4.5GB, leaving ample room for the visual buffer and context window."
+}