Upload README.md with huggingface_hub

README.md

@@ -1,57 +1,232 @@
 ---
 license: apache-2.0
-language: en
+language:
+  - en
 tags:
   - 0labs
   - sky
   - crest
   - adaptive-depth
+  - llm
+  - lightweight
+  - edge-ai
+library_name: transformers
+pipeline_tag: text-generation
+base_model: 0labs-in/Sky-v2.0-11B
 ---
 
-# Sky v2.0 — 6.5B (CREST K=2)
+# Sky v2.0-Lite — Lightweight CREST for Everyone
 
-**Built by 0labs — Atharvsinh Jadav, Gujarat, India**
+<p align="center">
+  <strong>Built by <a href="https://0labs.in">0labs</a> — Atharvsinh Jadav, Gujarat, India</strong><br>
+  <em>Adaptive-depth AI that runs on any laptop.</em>
+</p>
 
-## Architecture: CREST (Cognitively Recurrent Estimation of Step Termination)
+---
+
+## What is This Model?
+
+Sky v2.0-Lite is the **smallest and fastest** member of the Sky v2.0 family. It combines **K=2 step reduction** (keeping only CREST Steps 1 and 2) with the option for **4-bit quantization at load time**, making it possible to run a CREST adaptive-depth model on hardware as modest as an **8GB laptop GPU** or even a **Google Colab free tier T4**.
 
-This model uses the **CREST adaptive-depth architecture** — our proprietary
-architecture where each FFN layer has 2 independent MLPs and a learned halting
-gate. The model decides per-token, per-layer how many computational steps to take.
+Despite being the lightest variant, it still has **adaptive depth** — the model still decides per-token how much computation to use. It is not a standard transformer; it is a real CREST model.
 
-- Easy tokens ("the", "is") → 1 step (fast)
-- Hard tokens (algorithm logic, math) → 2 steps (deeper thinking)
+### Who is This For?
 
-## Specs
+- 🎓 **Students** exploring adaptive-depth LLMs on a budget
+- 💻 **Developers** building AI-powered applications on consumer hardware
+- 📱 **Edge/on-device** deployment where every GB matters
+- 🧪 **Researchers** who want to experiment with CREST without cloud GPUs
+
+---
+
+## Model Details
 
 | Property | Value |
 |---|---|
-| Architecture | CREST (0labs proprietary) |
-| Parameters | 6.5B |
-| CREST Steps (K) | 2 |
-| Base Model Size | 4B |
-| Hidden Dimension | 2,560 |
-| Layers | 32 |
-| Attention Heads | 32 |
-| Context Window | 32,768 tokens |
-| Quantization | INT4 |
-
-## Usage
+| **Architecture** | CREST (0labs proprietary) |
+| **Total Parameters** | 6.47B |
+| **CREST Steps (K)** | 2 |
+| **Hidden Dimension** | 2,560 |
+| **Layers** | 32 |
+| **Attention Heads** | 32 |
+| **Context Window** | 32,768 tokens |
+| **Disk Size** | ~13GB (BFloat16) |
+| **VRAM (BF16)** | ~13GB |
+| **VRAM (INT4)** | ~4GB |
+| **Vocabulary Size** | 248,320 |
+| **License** | Apache 2.0 |
+
+---
+
+## Quick Start
+
+### Recommended: 4-Bit Loading (~4GB VRAM) ⭐
+
+This is the recommended way to run Sky v2.0-Lite on consumer hardware:
 
 ```python
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
+
+# 4-bit quantization config — uses only ~4GB VRAM
+quantization_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_compute_dtype=torch.bfloat16,
+    bnb_4bit_quant_type="nf4",
+)
 
 model = AutoModelForCausalLM.from_pretrained(
-    "0labs-in/Sky-v2.0",
-    trust_remote_code=True,  # Required for CREST architecture
+    "0labs-in/Sky-v2.0-Lite",
+    trust_remote_code=True,       # Required — CREST is a custom architecture
+    quantization_config=quantization_config,
+    device_map="auto",
+)
+tokenizer = AutoTokenizer.from_pretrained("0labs-in/Sky-v2.0-Lite")
+
+# Chat
+prompt = "Explain quantum computing in simple terms."
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+
+with torch.no_grad():
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=512,
+        temperature=0.7,
+        top_p=0.9,
+        do_sample=True,
+    )
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+### Full Precision Loading (needs ~13GB VRAM)
+
+```python
+model = AutoModelForCausalLM.from_pretrained(
+    "0labs-in/Sky-v2.0-Lite",
+    trust_remote_code=True,
     torch_dtype=torch.bfloat16,
     device_map="auto",
 )
-tokenizer = AutoTokenizer.from_pretrained("0labs-in/Sky-v2.0")
 ```
 
-## 0labs
+> **Note:** `trust_remote_code=True` is required — CREST uses custom architecture code included in this repository.
+
+---
+
+## Hardware Compatibility
+
+| Device | Loading Mode | VRAM Used | Works? |
+|---|---|---|---|
+| **Laptop RTX 4060 (8GB)** | **INT4** | **~4GB** | **✅** |
+| **Google Colab T4 (15GB)** | **INT4** | **~4GB** | **✅** |
+| **Apple M1/M2 (8GB)** | **INT4** | **~4GB** | **✅** |
+| MacBook Pro M3 (18GB) | BF16 | ~13GB | ✅ |
+| RTX 3090 (24GB) | BF16 | ~13GB | ✅ |
+| RTX 4090 (24GB) | BF16 | ~13GB | ✅ |
+| A100 (40/80GB) | BF16 | ~13GB | ✅ |
+| MI300X (192GB) | BF16 | ~13GB | ✅ |
+
+### Google Colab (Free Tier)
+
+```python
+# Run this in the first cell of a Colab notebook
+!pip install -q transformers accelerate bitsandbytes safetensors sentencepiece
+
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
+
+model = AutoModelForCausalLM.from_pretrained(
+    "0labs-in/Sky-v2.0-Lite",
+    trust_remote_code=True,
+    quantization_config=BitsAndBytesConfig(
+        load_in_4bit=True,
+        bnb_4bit_compute_dtype=torch.bfloat16,
+        bnb_4bit_quant_type="nf4",
+    ),
+    device_map="auto",
+)
+tokenizer = AutoTokenizer.from_pretrained("0labs-in/Sky-v2.0-Lite")
+
+# You're ready to go!
+```
+
+---
+
+## Architecture: CREST K=2
+
+```
+Input from Attention
+       ↓
+   ┌──────────┐
+   │   MLP₁   │  ← Step 1: Core knowledge (always runs)
+   └──────────┘
+       ↓
+   Halting Gate: "Is this token done?"
+       │
+       ├── h₁ ≈ 1.0 → HALT (easy tokens: "the", "is", "and")
+       │                 output = state₁
+       │
+       ↓ h₁ < threshold
+   ┌──────────┐
+   │   MLP₂   │  ← Step 2: Deeper reasoning (only when needed)
+   └──────────┘
+       ↓
+   Output = p₁ · state₁ + p₂ · state₂
+```
+
+**What this means in practice:**
+- Simple/common tokens → processed by just MLP₁ → **fast**
+- Complex/rare tokens → processed by MLP₁ then MLP₂ → **more accurate**
+- The model **automatically decides** which path to take for each token
+
+---
+
+## Comparison: Lite vs Other Variants
+
+| Feature | Sky v2.0-11B | Sky v2.0-6.5B | Sky v2.0-11B-INT4 | **Sky v2.0-Lite** |
+|---|---|---|---|---|
+| Parameters | 11.2B | 6.47B | 11.2B | **6.47B** |
+| CREST Steps | 4 | 2 | 4 | **2** |
+| Min VRAM (INT4) | ~6GB | ~4GB | ~6GB | **~4GB** |
+| Adaptive Depth | ✅ | ✅ | ✅ | **✅** |
+| Best For | Max quality | Balance | Full CREST | **Everyone** |
+
+---
+
+## Model Family
+
+| Model | Parameters | CREST K | Best For |
+|---|---|---|---|
+| [Sky v2.0-11B](https://huggingface.co/0labs-in/Sky-v2.0-11B) | 11.2B | 4 | Maximum capability |
+| [Sky v2.0-6.5B](https://huggingface.co/0labs-in/Sky-v2.0-6.5B) | 6.47B | 2 | Balanced performance |
+| [Sky v2.0-11B-INT4](https://huggingface.co/0labs-in/Sky-v2.0-11B-INT4) | 11.2B | 4 | Full CREST, memory-efficient |
+| **[Sky v2.0-Lite](https://huggingface.co/0labs-in/Sky-v2.0-Lite)** | **6.47B** | **2** | **Laptops, Colab, edge devices** |
+
+---
+
+## Citation
+
+```bibtex
+@article{jadav2026crest,
+  title={CREST: Cognitively Recurrent Estimation of Step Termination for Adaptive-Depth Language Modeling},
+  author={Jadav, Atharvsinh},
+  year={2026},
+  url={https://huggingface.co/0labs-in/Sky-v2.0-11B}
+}
+```
+
+---
+
+## About 0labs
+
+**0labs** is an independent AI research lab founded by Atharvsinh Jadav in Gujarat, India. We build adaptive-depth LLMs that think harder on hard problems — trained on a single GPU.
+
+- 🌐 Website: [0labs.in](https://0labs.in)
+- 🤗 HuggingFace: [huggingface.co/0labs-in](https://huggingface.co/0labs-in)
+
+---
 
-Independent AI research lab. One researcher. One GPU. Adaptive-depth LLMs.
-- Website: https://0labs.in
-- HuggingFace: https://huggingface.co/0labs-in
+<p align="center">
+  <em>AI should be accessible to everyone. Sky v2.0-Lite makes adaptive-depth intelligence available on any hardware.</em>
+</p>