Update README.md

README.md

@@ -19,28 +19,104 @@ We release **Tri-1.8B Translation**, a lightweight multilingual translation mode
 
 Tri-1.8B Translate is trained through pretraining and supervised fine-tuning (SFT), and was distilled from our larger Tri-21B model to preserve strong translation quality in a much smaller, deployment-friendly 1.8B parameter model. It supports all translation directions among English, Korean, Japanese, and Chinese.
 
----
+
 
 ## ✨ Highlights
-- **Compact & efficient**: ~1.8B parameters, easy to deploy.  
-- **Multilingual**: Fully bidirectional translation across **EN ↔ KO ↔ JA ↔ ZH**.  
-- **Research-ready**: Ideal for experimentation and domain fine-tuning.
+
+* **Compact & efficient:** \~1.8B params, easy to serve on a single GPU.
+* **Multilingual:** Fully bidirectional **EN ↔ KO ↔ JA ↔ ZH**.
+* **Simple prompts:** Works with a short **task instruction + `<lang>` tag**.
+* **Research-ready:** Suitable for domain SFT or lightweight adapters.
+
+---
+
+## 🧾 Prompt format
+
+```
+Translate the following {SRC_NAME} text into {TGT_NAME}:
+{TEXT} <{lang_tag}>
+```
+
+Where `{lang_tag} ∈ { en, ko, ja, zh }`.
 
 ---
 
 ## 🔧 Usage
 
+### 1) 🤗 Transformers
+
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-model_id = "trillionlabs/Tri-1.8B-Translation"
-
-tok = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
-
-prompt = "Translate English to Korean: 'We look forward to working with you again.' <ko>"
+tok = AutoTokenizer.from_pretrained("trillionlabs/Tri-1.8B-Translation")
+model = AutoModelForCausalLM.from_pretrained("trillionlabs/Tri-1.8B-Translation", device_map="auto")
 
+prompt = "Translate the following Korean text into English:\n안녕하세요 <en>"
 inputs = tok(prompt, return_tensors="pt").to(model.device)
 out = model.generate(**inputs, max_new_tokens=128)
 print(tok.decode(out[0], skip_special_tokens=True))
+```
+
+---
+
+### 2) Local vLLM
+
+```python
+from vllm import LLM, SamplingParams
+
+llm = LLM(model="trillionlabs/Tri-1.8B-Translation")
+sp = SamplingParams(temperature=0.3, max_tokens=512)
+
+def translate(text, target="en"):
+    prompt = f"Translate into {target}:\n{text} <{target}>"
+    out = llm.chat([{"role": "user", "content": prompt}], sampling_params=sp)
+    return out[0].outputs[0].text.strip()
+
+print(translate("안녕하세요", "en"))
+```
+
+---
+
+### 3) API client (OpenAI-compatible)
+
+```python
+import openai
+
+client = openai.OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
+
+def translate(text, target="en"):
+    prompt = f"Translate into {target}:\n{text} <{target}>"
+    resp = client.chat.completions.create(
+        model="trillionlabs/Tri-1.8B-Translation",
+        messages=[{"role": "user", "content": prompt}],
+        temperature=0.3,
+        max_tokens=512,
+    )
+    return resp.choices[0].message.content.strip()
+
+print(translate("안녕하세요", "en"))
+```
+
+
+## 📜 License
+
+Apache-2.0 (for model weights & code). Please verify data licenses for your use.
+
+
+## 🙏 Acknowledgments
+
+* Thanks to the **ByteDance Seed team** for releasing **Seed-X**; our prompt template and some training design were adapted from their paper.
+
+
+## 📚 Citation
+
+If you use **Tri-1.8B Translation**, please cite:
+
+```bibtex
+@misc{suk2025tri18b,
+  title   = {Tri-1.8B Translation: A Lightweight Multilingual Translation Model},
+  author  = {Juyoung Suk and Trillion Labs},
+  year    = {2025},
+  howpublished = {\url{https://huggingface.co/trillionlabs/Tri-1.8B-Translation}}
+}
 ```