Upload README.md with huggingface_hub

README.md

@@ -61,20 +61,20 @@ Most existing community quantizations are generated by automated bots that apply
 
 Also, don't confuse **APEX-I-MiniPlus (Standard)** with a generic baseline APEX-I-Mini. Traditional APEX-I-Mini drops core experts aggressively to 2-bit `IQ2_S` and leaves `output.weight` at 3-bit `Q3_K_M`, which creates a noticeable perplexity hit on complex reasoning tasks. Standard MiniPlus avoids that degradation floor while keeping boundary layers in linear `Q3_K` for single-cycle vectorized AVX2 CPU dequantization (hitting 23 to 26+ tok/s on DDR4 laptops), while protecting output in `Q6_K` and routers in `F32`.
 
-To put the numbers in perspective: this cuts nearly **2 GB off a flat 3-bit quant** (~15.6 GB), and weighs only about **~1 GB more than a generic APEX-I-Mini** (~12.5 GB). For that single extra gigabyte of VRAM, you get a massive jump in reasoning and syntactic stability while maximizing CPU/RAM execution throughput.
+To put the numbers in perspective: this cuts nearly **2 GB off a flat 3-bit quant** (approx. 15.6 GB), and weighs only about **approx. 1 GB more than a generic APEX-I-Mini** (approx. 12.5 GB). For that single extra gigabyte of VRAM, you get a massive jump in reasoning and syntactic stability while maximizing CPU/RAM execution throughput.
 
 Take a look at the tensor-by-tensor comparison table below to inspect the exact architectural differences and see why this specific allocation is optimal. That's specifically what this was built for:
 
 | Architectural Component | Generic Automated Quants (Flat `Q3_K_S` / `IQ3_S`) | Generic APEX-I-Mini (Baseline Recipe) | Our Handcrafted APEX-I-MiniPlus (Standard / IsValorum) | Perceived Quality & Real-World Impact |
 | :--- | :--- | :--- | :--- | :--- |
-| **Output Head (`output.weight`)** | Flat **`IQ3_S` / `Q3_K_S`** (~3.44 BPW) | Inherits base type **`Q3_K_M`** (~3.44 BPW unarmored) | **`Q6_K`** (~6.56 BPW uncompromised) | **Eliminates Syntax & Vocabulary Hallucinations:** Low-bit output heads cause tokenizer classification noise, breaking code indentation, brackets (`{}`, `[]`), math symbols, and domain terms. `Q6_K` preserves near-FP16 output classification. |
-| **Expert Routers (`ffn_gate_inp.weight`)** | Blindly quantized to 3-bit / unoptimized | Inherits base type **`Q3_K_M`** (~3.44 BPW compressed) | **`F32` uncompressed** (32.0 BPW, 2 MB/layer) | **Zero Router Drift:** In micro-expert models, even minuscule quantization errors in router logits misdirect tokens to wrong experts. Retaining uncompressed `F32` guarantees 100% routing fidelity with virtually zero memory overhead (~80 MB total). |
+| **Output Head (`output.weight`)** | Flat **`IQ3_S` / `Q3_K_S`** (approx. 3.44 BPW) | Inherits base type **`Q3_K_M`** (approx. 3.44 BPW unarmored) | **`Q6_K`** (approx. 6.56 BPW uncompromised) | **Eliminates Syntax & Vocabulary Hallucinations:** Low-bit output heads cause tokenizer classification noise, breaking code indentation, brackets (`{}`, `[]`), math symbols, and domain terms. `Q6_K` preserves near-FP16 output classification. |
+| **Expert Routers (`ffn_gate_inp.weight`)** | Blindly quantized to 3-bit / unoptimized | Inherits base type **`Q3_K_M`** (approx. 3.44 BPW compressed) | **`F32` uncompressed** (32.0 BPW, 2 MB/layer) | **Zero Router Drift:** In micro-expert models, even minuscule quantization errors in router logits misdirect tokens to wrong experts. Retaining uncompressed `F32` guarantees 100% routing fidelity with virtually zero memory overhead (approx. 80 MB total). |
 | **Attention & Language (`attn_output`, `attn_qkv`)** | Flat **`IQ3_S` / `Q3_K_S`** | **`Q3_K`** on 34 middle layers (L3–36), **`Q4_K`** on 6 edge layers | **`Q6_K` for `attn_output`**, **`Q3_K` / `Q4_K`** + `imatrix` | **Contextual Precision & CPU Throughput:** Combines uncompromised `Q6_K` for the output projection with fast vectorized linear blocks for attention, balancing retrieval accuracy with maximum token streaming speed on CPU/RAM. |
 | **Attention Gates (`attn_gate.weight`)** | Blindly compressed to 3-bit | Compressed to **`Q3_K`** (middle) / **`Q4_K`** (edges) | **`Q8_0`** (8.50 BPW) | **Attention Head Stability:** Attention gates modulate query-key routing across hybrid attention layers. Keeping them in 8-bit prevents attention crosstalk and hallucination over long contexts. |
 | **Shared Foundation Expert (`ffn_*_shexp`)** | Flat **`IQ3_S` / `Q3_K_S`** (3.44 BPW) | Linear **`Q4_K`** (middle) / **`Q5_K`** (edges) | Linear **`Q4_K`** (middle) / **`Q5_K`** (edges) + `imatrix` | **Foundational Knowledge Stability:** Keeps the universal pathway in high-fidelity linear blocks, eliminating quantization drift while maintaining rapid single-cycle dequantization. |
 | **Core MoE Layers (Middle: 10–29)** | Flat **`IQ3_S` / `Q3_K_S`** (uniform bit-rate across all layers) | Aggressive **`IQ2_S` (2.50 BPW)** | **`IQ3_XXS` (3.06 BPW) + calibrated `imatrix`** | **Above the Quality Threshold:** Generic 2-bit `IQ2_S` baselines drop below the critical quality floor for 35B MoEs, resulting in perplexity spikes on reasoning tasks. Our `IQ3_XXS` with imatrix achieves deep compression (272 MiB → 98 MiB per block) without sacrificing logic. |
 | **Edge MoE Layers (Layers 0–9 & 30–39)** | Flat **`IQ3_S` / `Q3_K_S`** (no layer-wise gradient) | `Q3_K` (limited to first/last 5 layers only: L0–4, L35–39) | **`Q3_K` (expanded to 10 input & 10 output layers)** | **AVX2 Single-Cycle Speed:** Expanded 10+10 layer protection using linear `Q3_K` blocks enables single-cycle vectorized AVX2 CPU dequantization, unlocking **23 to 26+ tok/s** on budget DDR4 laptops. |
-| **Multimodal Vision (`mmproj`)** | Often omitted, or left as uncompressed **`FP16` (~900 MB)** | Often omitted or separate uncompressed `FP16` | **Bundled `Q8_0` (582 MB)** with **27 critical F32/F16 fallbacks** | **Saves ~320 MB VRAM with Zero Loss:** Handcrafted quantization preserves normalization and bias tensors in F32/F16, ensuring razor-sharp OCR, DOM viewport reading, and coordinate detection without visual noise. |
+| **Multimodal Vision (`mmproj`)** | Often omitted, or left as uncompressed **`FP16` (approx. 900 MB)** | Often omitted or separate uncompressed `FP16` | **Bundled `Q8_0` (582 MB)** with **27 critical F32/F16 fallbacks** | **Saves approx. 320 MB VRAM with Zero Loss:** Handcrafted quantization preserves normalization and bias tensors in F32/F16, ensuring razor-sharp OCR, DOM viewport reading, and coordinate detection without visual noise. |
 | **Normalization & Biases** | Often degraded | Standard | **`F32` uncompressed** | **Numerical Stability:** Prevents cumulative floating-point underflow/overflow across deep 40-layer computation. |
 
 ---
@@ -83,7 +83,7 @@ Take a look at the tensor-by-tensor comparison table below to inspect the exact
 ## 👁️ Bundled Q8_0 High-Precision Vision Projector
 
 Unlike text-only MoEs, Nex-N2.5-mini is designed for computer use, visual grounding, and multi-modal interaction. 
-- Rather than leaving users to search for external FP16 projectors (~900 MB), this repository bundles the official projector quantized to **`Q8_0` (610 MB / 582 MiB)**.
+- Rather than leaving users to search for external FP16 projectors (approx. 900 MB), this repository bundles the official projector quantized to **`Q8_0` (610 MB / 582 MiB)**.
 - Delivers near-lossless visual recognition while saving VRAM.
 
 ---