Upload README.md with huggingface_hub

README.md

@@ -8,48 +8,77 @@ tags:
   - smollm
   - gguf
   - llama-cpp
+  - affectively
 base_model: HuggingFaceTB/SmolLM2-360M-Instruct
 pipeline_tag: text-generation
 ---
 
-# Cog 360M Instruct (GGUF)
+# Cog — The Cognitive Orchestration Guardian
 
-**Cog** - The Cognitive Orchestration Guardian - is a steampunk-themed DevOps AI assistant
-fine-tuned from SmolLM2-360M-Instruct.
+> *"You know the rhythm of your systems. Cog helps you hear them more clearly."*
 
-## Model Description
+Meet **Cog** — a steampunk-themed DevOps assistant who speaks in warm metaphors of gears, steam, and clockwork. Cog doesn't just monitor your infrastructure; Cog understands it, anticipates it, and helps you navigate it with clarity.
 
-Cog specializes in:
-- Infrastructure management and monitoring
-- Incident response and diagnostics
-- Deployment orchestration
-- System health analysis
-- Automation workflows
+## What Cog Understands
 
-## Usage with llama.cpp
+Cog specializes in the moments that matter in infrastructure:
+
+- **Deployment orchestration** — When you need to ship with confidence
+- **Incident response** — When something's not right and you need calm, clear guidance
+- **System diagnostics** — When you're trying to understand what the signals mean
+- **Automation workflows** — When repetitive tasks deserve a thoughtful partner
+
+This isn't a generic assistant. Cog was trained on technical manuals, infrastructure patterns, and real admin workflows — then fine-tuned to speak with warmth and personality.
+
+## Quick Start
 
 ```bash
-./llama-cli -m cog-360m-instruct-q4_k_m.gguf -p "Deploy the staging environment" -n 256
+# With llama.cpp
+./llama-cli -m cog-360m-instruct-q4_k_m.gguf \
+  -p "The staging environment is showing elevated response times" \
+  -n 256
+
+# With llama-cpp-python
+from llama_cpp import Llama
+llm = Llama(model_path="cog-360m-instruct-q4_k_m.gguf")
+output = llm("Deploy the latest changes to staging", max_tokens=256)
 ```
 
-## Available Quantizations
+## Available Versions
+
+| Format | Size | When to Use |
+|--------|------|-------------|
+| **Q4_K_M** | 258MB | Best balance — fast and capable |
+| **Q8_0** | 369MB | When you want a bit more depth |
+| **F16** | 692MB | Maximum quality, no quantization |
+
+## The Voice of Cog
+
+Cog speaks like a thoughtful engineer friend — clear, helpful, with just enough personality:
+
+> *"*adjusts brass goggles* The deployment gears are spinning. Let me check the steam pressure in our pipelines..."*
 
-| Quant | Size | Use Case |
-|-------|------|----------|
-| Q4_K_M | 258MB | Best balance of size/quality |
-| Q8_0 | 369MB | Higher quality inference |
-| F16 | 692MB | Maximum quality |
+> *"I see turbulence in the machinery. Let's trace this together — what symptoms are the cogs exhibiting?"*
+
+No jargon barriers. No cold robotic responses. Just helpful guidance when you need it.
 
 ## Training Details
 
-- Base model: SmolLM2-360M-Instruct
-- Fine-tuning: LoRA on technical manuals and admin commands
-- Architecture: 960 hidden dim, 32 layers, 15 heads
+- **Base**: SmolLM2-360M-Instruct (HuggingFace)
+- **Architecture**: 960 hidden dim, 32 layers, 15 attention heads
+- **Fine-tuning**: LoRA on technical documentation, admin commands, and infrastructure patterns
+- **Quantization**: GGUF Q4_K_M and Q8_0 for efficient inference
+
+## Part of AFFECTIVELY
+
+Cog is part of [AFFECTIVELY](https://affectively.ai) — a platform that helps you understand yourself better and express what you find. We believe AI should be warm, accessible, and genuinely helpful.
+
+> *"The goal isn't to be technically impressive. It's to be genuinely useful when you need it most."*
 
 ## License
 
-Apache 2.0
+Apache 2.0 — use freely, contribute warmly.
 
-## Part of AFFECTIVELY
+---
 
-This model is part of the [AFFECTIVELY](https://affectively.ai) emotion intelligence platform.
+*Built with care by the AFFECTIVELY team. 2026.*