uploaded readme

README.md

@@ -0,0 +1,157 @@
+Quantization made by Richard Erkhov.
+
+[Github](https://github.com/RichardErkhov)
+
+[Discord](https://discord.gg/pvy7H8DZMG)
+
+[Request more models](https://github.com/RichardErkhov/quant_request)
+
+
+DataVortexS-10.7B-dpo-v1.2 - GGUF
+- Model creator: https://huggingface.co/Edentns/
+- Original model: https://huggingface.co/Edentns/DataVortexS-10.7B-dpo-v1.2/
+
+
+| Name | Quant method | Size |
+| ---- | ---- | ---- |
+| [DataVortexS-10.7B-dpo-v1.2.Q2_K.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexS-10.7B-dpo-v1.2-gguf/blob/main/DataVortexS-10.7B-dpo-v1.2.Q2_K.gguf) | Q2_K | 3.73GB |
+| [DataVortexS-10.7B-dpo-v1.2.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexS-10.7B-dpo-v1.2-gguf/blob/main/DataVortexS-10.7B-dpo-v1.2.IQ3_XS.gguf) | IQ3_XS | 4.14GB |
+| [DataVortexS-10.7B-dpo-v1.2.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexS-10.7B-dpo-v1.2-gguf/blob/main/DataVortexS-10.7B-dpo-v1.2.IQ3_S.gguf) | IQ3_S | 4.37GB |
+| [DataVortexS-10.7B-dpo-v1.2.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexS-10.7B-dpo-v1.2-gguf/blob/main/DataVortexS-10.7B-dpo-v1.2.Q3_K_S.gguf) | Q3_K_S | 4.34GB |
+| [DataVortexS-10.7B-dpo-v1.2.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexS-10.7B-dpo-v1.2-gguf/blob/main/DataVortexS-10.7B-dpo-v1.2.IQ3_M.gguf) | IQ3_M | 4.51GB |
+| [DataVortexS-10.7B-dpo-v1.2.Q3_K.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexS-10.7B-dpo-v1.2-gguf/blob/main/DataVortexS-10.7B-dpo-v1.2.Q3_K.gguf) | Q3_K | 4.84GB |
+| [DataVortexS-10.7B-dpo-v1.2.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexS-10.7B-dpo-v1.2-gguf/blob/main/DataVortexS-10.7B-dpo-v1.2.Q3_K_M.gguf) | Q3_K_M | 4.84GB |
+| [DataVortexS-10.7B-dpo-v1.2.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexS-10.7B-dpo-v1.2-gguf/blob/main/DataVortexS-10.7B-dpo-v1.2.Q3_K_L.gguf) | Q3_K_L | 5.26GB |
+| [DataVortexS-10.7B-dpo-v1.2.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexS-10.7B-dpo-v1.2-gguf/blob/main/DataVortexS-10.7B-dpo-v1.2.IQ4_XS.gguf) | IQ4_XS | 5.43GB |
+| [DataVortexS-10.7B-dpo-v1.2.Q4_0.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexS-10.7B-dpo-v1.2-gguf/blob/main/DataVortexS-10.7B-dpo-v1.2.Q4_0.gguf) | Q4_0 | 5.66GB |
+| [DataVortexS-10.7B-dpo-v1.2.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexS-10.7B-dpo-v1.2-gguf/blob/main/DataVortexS-10.7B-dpo-v1.2.IQ4_NL.gguf) | IQ4_NL | 5.72GB |
+| [DataVortexS-10.7B-dpo-v1.2.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexS-10.7B-dpo-v1.2-gguf/blob/main/DataVortexS-10.7B-dpo-v1.2.Q4_K_S.gguf) | Q4_K_S | 5.7GB |
+| [DataVortexS-10.7B-dpo-v1.2.Q4_K.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexS-10.7B-dpo-v1.2-gguf/blob/main/DataVortexS-10.7B-dpo-v1.2.Q4_K.gguf) | Q4_K | 6.02GB |
+| [DataVortexS-10.7B-dpo-v1.2.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexS-10.7B-dpo-v1.2-gguf/blob/main/DataVortexS-10.7B-dpo-v1.2.Q4_K_M.gguf) | Q4_K_M | 6.02GB |
+| [DataVortexS-10.7B-dpo-v1.2.Q4_1.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexS-10.7B-dpo-v1.2-gguf/blob/main/DataVortexS-10.7B-dpo-v1.2.Q4_1.gguf) | Q4_1 | 6.27GB |
+| [DataVortexS-10.7B-dpo-v1.2.Q5_0.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexS-10.7B-dpo-v1.2-gguf/blob/main/DataVortexS-10.7B-dpo-v1.2.Q5_0.gguf) | Q5_0 | 6.89GB |
+| [DataVortexS-10.7B-dpo-v1.2.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexS-10.7B-dpo-v1.2-gguf/blob/main/DataVortexS-10.7B-dpo-v1.2.Q5_K_S.gguf) | Q5_K_S | 6.89GB |
+| [DataVortexS-10.7B-dpo-v1.2.Q5_K.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexS-10.7B-dpo-v1.2-gguf/blob/main/DataVortexS-10.7B-dpo-v1.2.Q5_K.gguf) | Q5_K | 7.08GB |
+| [DataVortexS-10.7B-dpo-v1.2.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexS-10.7B-dpo-v1.2-gguf/blob/main/DataVortexS-10.7B-dpo-v1.2.Q5_K_M.gguf) | Q5_K_M | 7.08GB |
+| [DataVortexS-10.7B-dpo-v1.2.Q5_1.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexS-10.7B-dpo-v1.2-gguf/blob/main/DataVortexS-10.7B-dpo-v1.2.Q5_1.gguf) | Q5_1 | 7.51GB |
+| [DataVortexS-10.7B-dpo-v1.2.Q6_K.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexS-10.7B-dpo-v1.2-gguf/blob/main/DataVortexS-10.7B-dpo-v1.2.Q6_K.gguf) | Q6_K | 8.2GB |
+| [DataVortexS-10.7B-dpo-v1.2.Q8_0.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexS-10.7B-dpo-v1.2-gguf/blob/main/DataVortexS-10.7B-dpo-v1.2.Q8_0.gguf) | Q8_0 | 10.62GB |
+
+
+
+
+Original model description:
+---
+tags:
+    - text-generation
+license: cc-by-nc-sa-4.0
+language:
+    - ko
+base_model: megastudy/M-SOLAR-10.7B-v1.3
+pipeline_tag: text-generation
+---
+
+# **DataVortexS-10.7B-dpo-v1.2**
+
+<img src="./DataVortex.png" alt="DataVortex" style="height: 8em;">
+
+## Our Team
+
+| Research & Engineering | Product Management |
+| :--------------------: | :----------------: |
+|     Kwangseok Yang     |   Seunghyun Choi   |
+|     Jeongwon Choi      |    Hyoseok Choi    |
+
+## **Model Details**
+
+### **Base Model**
+
+[megastudy/M-SOLAR-10.7B-v1.3](https://huggingface.co/megastudy/M-SOLAR-10.7B-v1.3)
+
+### **Trained On**
+
+-   **OS**: Ubuntu 22.04
+-   **GPU**: H100 80GB 4ea
+-   **transformers**: v4.36.2
+
+### **Instruction format**
+
+It follows **Alpaca (Chat)** format.
+
+E.g.
+
+```python
+text = """\
+### System:
+당신은 사람들이 정보를 찾을 수 있도록 도와주는 인공지능 비서입니다.
+
+### User:
+대한민국의 수도는 어디야?
+
+### Assistant:
+대한민국의 수도는 서울입니다.
+
+### User:
+서울 인구는 총 몇 명이야?
+"""
+```
+
+## **Model Benchmark**
+
+### **[Ko LM Eval Harness](https://github.com/Beomi/ko-lm-evaluation-harness)**
+
+| Task             |       0-shot |       5-shot |      10-shot |     50-shot |
+| :--------------- | -----------: | -----------: | -----------: | ----------: |
+| kobest_boolq     |      0.86665 |     0.932254 |     0.940132 |    0.941561 |
+| kobest_copa      |     0.723415 |     0.780594 |     0.778814 |     0.79982 |
+| kobest_hellaswag |     0.471639 |     0.466883 |     0.472548 |    0.488648 |
+| kobest_sentineg  |      0.78514 |     0.964734 |     0.972281 |    0.972289 |
+| **Average**      | **0.711711** | **0.786116** | **0.790944** | **0.80058** |
+
+### **[Ko-LLM-Leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)**
+
+| Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
+| ------: | -----: | -----------: | ------: | ------------: | --------------: |
+|   56.53 |  52.73 |        64.83 |   52.99 |         58.36 |           53.72 |
+
+## **Implementation Code**
+
+This model contains the chat_template instruction format.  
+You can use the code below.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+device = "cuda" # the device to load the model onto
+
+model = AutoModelForCausalLM.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.2")
+tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.2")
+
+messages = [
+    {"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?"}
+]
+
+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;">
+    </a>
+</div>
+
+