Create README.md

README.md

@@ -0,0 +1,65 @@
+---
+datasets:
+- osyvokon/zno
+- byebyebye/ukr-wiki-qa-v1
+- byebyebye/ukr-wiki-qa-v2
+language:
+- uk
+---
+## Introduction
+kodkobzar13B is a generative model that was trained on Ukrainian Wikipedia data and Ukrainian language rules. It has knowledge of Ukrainian history, language, literature and culture.
+
+## Model Information
+This model is based on [vicuna-13b-v1.5](https://huggingface.co/lmsys/vicuna-13b-v1.5).
+
+## Model Usage
+
+Use the following prompt template: <br>
+USER: {input} ASSISTANT: 
+
+We recommend using next configurations:
+
+<b>Temperature:</b> 0.8 <br>
+<b>Top-p:</b> 0.95
+
+### Inference
+
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+model_path="ponoma16/kodkobzar13B_x2_lit_history_lang_finetuned-merged"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(
+                            model_load_path,
+                            low_cpu_mem_usage=True,
+                            torch_dtype=torch.float16,
+                            device_map='auto',
+                        )
+model.eval()
+
+prompt = "Яке місто в Україні називають найромантичнішим?"
+
+PROMPT_TEMPLATE = """USER: {prompt} ASSISTANT: """
+
+input_ids = tokenizer(
+                prompt,
+                return_tensors="pt",
+                truncation=True,
+            ).input_ids.cuda()
+outputs = model.generate(
+            input_ids=input_ids,
+            do_sample=True,
+            top_p=0.95,
+            max_new_tokens=150,
+            temperature=0.8,
+        )
+prediction = tokenizer.batch_decode(outputs.cpu().numpy(), skip_special_tokens=True)[0]
+print(prediction)
+```
+
+
+## Contact
+
+If you have any inquiries, please feel free to raise an issue or reach out to us via email at: mariiaponomarenko10@gmail.com, benjamin.ye@me.com. 
+We're here to assist you!"