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-indic-chat-translator
+
+> **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: `6f1d306c`)
+- **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/rishiraj/smolified-indic-chat-translator)
+
+## 🚀 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 = "rishiraj/smolified-indic-chat-translator"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
 
-# Uploaded finetuned  model
+messages = [
+    {'role': 'system', 'content': '''You are an expert linguistics AI specializing in informal Indian communication patterns and Romanized transliteration (writing local languages using English letters). You are given a WhatsApp-style message and your task is to identify its source language from the given list, and then provide its translations into all the other target languages, ensuring all outputs are in Roman script and maintain an informal tone.'''},
+    {'role': 'user', 'content': '''yenna sollu? office ponnum but manasu illa'''}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize = False,
+    add_generation_prompt = True,
+).removeprefix('<bos>')
 
-- **Developed by:** rishiraj
-- **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 **rishiraj**.
+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)