Fix README.md

README.md

@@ -1,40 +1,25 @@
 ---
+base_model: beomi/OPEN-SOLAR-KO-10.7B
+license: apache-2.0
+pipeline_tag: text-generation
+language:
+  - en
+  - ko
 tags:
-- autotrain
-- text-generation
-widget:
-- text: "I love AutoTrain because "
-license: other
+  - finetuned
+  - text-generation
+datasets:
+  - royboy0416/ko-alpaca
+inference: false
+model_type: mixtral
 ---
+# Model Card for OPEN-SOLAR-KO-10.7B-S-Core
 
-# Model Trained Using AutoTrain
+## Model Details
 
-This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
+* **Base Model**: [beomi/OPEN-SOLAR-KO-10.7B](https://huggingface.co/beomi/OPEN-SOLAR-KO-10.7B)
 
-# Usage
+## Dataset Details
 
-```python
-
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-model_path = "PATH_TO_THIS_REPO"
-
-tokenizer = AutoTokenizer.from_pretrained(model_path)
-model = AutoModelForCausalLM.from_pretrained(
-    model_path,
-    device_map="auto",
-    torch_dtype='auto'
-).eval()
-
-# Prompt content: "hi"
-messages = [
-    {"role": "user", "content": "hi"}
-]
-
-input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
-output_ids = model.generate(input_ids.to('cuda'))
-response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
-
-# Model response: "Hello! How can I assist you today?"
-print(response)
-```
+### Used Datasets
+- royboy0416/ko-alpaca