Update README.md

README.md

@@ -1,77 +1,101 @@
 ---
 tags:
-- text-generation
+    - text-generation
 license: cc-by-nc-sa-4.0
 language:
-- ko
+    - ko
 base_model: yanolja/KoSOLAR-10.7B-v0.1
 pipeline_tag: text-generation
+datasets:
+    - nlpai-lab/kullm-v2
 ---
 
 # **DataVortexS-10.7B-v0.1**
-<img src="./DataVortex.png" alt="DataVortex" style="height: 8em;">
-
-## **License**
 
-[cc-by-nc-sa-4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/)
+<img src="./DataVortex.png" alt="DataVortex" style="height: 8em;">
 
 ## **Model Details**
 
 ### **Base Model**
-[yanolja/KoSOLAR-10.7B-v0.1](https://huggingface.co/yanolja/KoSOLAR-10.7B-v0.1)  
+
+[yanolja/KoSOLAR-10.7B-v0.1](https://huggingface.co/yanolja/KoSOLAR-10.7B-v0.1)
 
 ### **Trained On**
-H100 80GB 1ea
+
+-   **OS**: Ubuntu 20.04
+-   **GPU**: H100 80GB 1ea
+-   **transformers**: v4.36.2
+
+### **Dataset**
+
+-   [nlpai-lab/kullm-v2](https://huggingface.co/datasets/nlpai-lab/kullm-v2) - 152k rows
 
 ### **Instruction format**
 
-It follows **(No Input) Alpaca** format.
+It follows **Alpaca** format.
+
+E.g.
+
+```python
+text = """\
+당신은 사람들이 정보를 찾을 수 있도록 도와주는 인공지능 비서입니다.
+
+### Instruction:
+대한민국의 수도는 어디야?
+
+### Response:
+대한민국의 수도는 서울입니다.
+
+### Instruction:
+서울 인구는 총 몇 명이야?
+"""
+```
 
 ## **Model Benchmark**
 
 ### **Ko-LLM-Leaderboard**
 
-On Benchmarking...
+On Benchmarking ...
+
+| Model                                | Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
+| ------------------------------------ | ------- | ------ | ------------ | ------- | ------------- | --------------- |
+| Edentns/DataVortexM-7B-Instruct-v0.1 | 39.81   | 34.13  | 42.35        | 38.73   | 45.46         | 38.37           |
+| **Edentns/DataVortexS-10.7B-v0.1**           | **0**   | **0**  | **0**        | **0**   | **0**         | **0**           |
 
-# **Implementation Code**
+## **Implementation Code**
 
-Since, chat_template already contains insturction format above.
+This model contains the chat_template instruction format.  
 You can use the code below.
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-device = "cuda"
+device = "cuda" # the device to load the model onto
 
-model = AutoModelForCausalLM.from_pretrained("Edentns/DataVortexS-10.7B-v0.1", device_map=device)
+model = AutoModelForCausalLM.from_pretrained("Edentns/DataVortexS-10.7B-v0.1")
 tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-v0.1")
 
 messages = [
-    { "role": "user", "content": "대한민국의 수도는 어디야?" }
+    {"role": "system", "content": "당신은 사람들이 정보를 찾을 수 있도록 도와주는 인공지능 비서입니다."},
+    {"role": "user", "content": "대한민국의 수도는 어디야?"},
+    {"role": "assistant", "content": "대한민국의 수도는 서울입니다."},
+    {"role": "user", "content": "서울 인구는 총 몇 명이야?"}
 ]
 
-encoded = tokenizer.apply_chat_template(
-    messages,
-    add_generation_prompt=True,
-    return_tensors="pt",
-    return_token_type_ids=False
-).to(device)
-
-decoded = model.generate(
-    input_ids=encoded,
-    temperature=0.2,
-    top_p=0.9,
-    repetition_penalty=1.2,
-    do_sample=True,
-    max_length=4096,
-    eos_token_id=tokenizer.eos_token_id,
-    pad_token_id=tokenizer.eos_token_id
-)
-decoded = decoded[0][encoded.shape[1]:decoded[0].shape[-1]]
-decoded_text = tokenizer.decode(decoded, skip_special_tokens=True)
-print(decoded_text)
+encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
+
+model_inputs = encodeds.to(device)
+model.to(device)
+
+generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
+decoded = tokenizer.batch_decode(generated_ids)
+print(decoded[0])
 ```
 
+## **License**
+
+The model is licensed under the [cc-by-nc-sa-4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) license, which allows others to copy, modify, and share the work non-commercially, as long as they give appropriate credit and distribute any derivative works under the same license.
+
 <div align="center">
     <a href="https://edentns.com/">
         <img src="./Logo.png" alt="Logo" style="height: 3em;">