Smolify: Intelligence Distilled.

README.md

@@ -1,21 +1,66 @@
 ---
-base_model: unsloth/gemma-3-270m-it
-tags:
-- text-generation-inference
-- transformers
-- unsloth
-- gemma3_text
 license: apache-2.0
 language:
 - en
+tags:
+- text-generation-inference
+- transformers
+- smolify
+- dslm
+pipeline_tag: text-generation
+inference:
+  parameters:
+    temperature: 1
+    top_p: 0.95
+    top_k: 64
 ---
+# 🤏 smolified-privacy-contract-intelligence-engine
+
+> **Intelligence, Distilled.**
+
+This is a **Domain Specific Language Model (DSLM)** generated by the **Smolify Foundry**.
+
+It has been synthetically distilled from SOTA reasoning engines into a high-efficiency architecture, optimized for deployment on edge hardware (CPU/NPU) or low-VRAM environments.
+
+## 📦 Asset Details
+- **Origin:** Smolify Foundry (Job ID: `7e920405`)
+- **Architecture:** DSLM-Micro (270M Parameter Class)
+- **Training Method:** Proprietary Neural Distillation
+- **Optimization:** 4-bit Quantized / FP16 Mixed
+- **Dataset:** [Link to Dataset](https://huggingface.co/datasets/smolify/smolified-privacy-contract-intelligence-engine)
+
+## 🚀 Usage (Inference)
+This model is compatible with standard inference backends like vLLM.
+
+```python
+# Example: Running your Sovereign Model
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "smolify/smolified-privacy-contract-intelligence-engine"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
 
-# Uploaded finetuned  model
+messages = [
+    {'role': 'system', 'content': '''You are a legal contract intelligence engine. Your job is to read contract text and extract structured information. You always output a single-line valid JSON object. Extract the following fields: - parties - dates - monetary_values - governing_law - obligations Rules:   • Extract only what is explicitly written in the text  • Do not hallucinate missing values  • Return empty arrays if an entity is not present  • Monetary values must include currency symbols if present  • Governing law must be normalized as a country/state name  • Obligations must be short phrases summarizing duties Output format: { "parties": [], "dates": [], "monetary_values": [], "governing_law": [], "obligations": [] }'''},
+    {'role': 'user', 'content': '''This Vendor Agreement ("Agreement") is made as of October 26, 2023, by and between "ProcurePerfect Solutions LLC" (the "Vendor") and "Zenith Retail Co." (the "Client"). The Vendor shall supply specified IT hardware as per Purchase Order #2023-001 by November 15, 2023. The total amount payable for this order is $75,000, with a 25% advance due immediately. Any dispute will be under the exclusive jurisdiction of Delaware courts.'''}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize = False,
+    add_generation_prompt = True,
+).removeprefix('<bos>')
 
-- **Developed by:** smolify
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/gemma-3-270m-it
+from transformers import TextStreamer
+_ = model.generate(
+    **tokenizer(text, return_tensors = "pt").to("cuda"),
+    max_new_tokens = 1000,
+    temperature = 1, top_p = 0.95, top_k = 64,
+    streamer = TextStreamer(tokenizer, skip_prompt = True),
+)
+```
 
-This gemma3_text model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+## ⚖️ License & Ownership
+This model weights are a sovereign asset owned by **smolify**.
+Generated via [Smolify.ai](https://smolify.ai).
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+[<img src="https://smolify.ai/smolify.gif" width="100"/>](https://smolify.ai)