Update README.md

README.md

@@ -1,3 +1,11 @@
+---
+license: apache-2.0
+language:
+- en
+library_name: transformers
+thumbnail: "https://huggingface.co/HyperbeeAI/Tulpar-7b-v0/resolve/main/tulpar.png"
+---
+
 <p align="center">
   <img src="https://huggingface.co/HyperbeeAI/Tulpar-7b-v0/resolve/main/tulpar.png" width="360" height="360" >
 </p>
@@ -19,13 +27,13 @@ You can run inference with both of the following prompts:
 ```python
 prompt = f"### User: {input_text}\n\n### Assistant:\n"
 inputs = tokenizer(prompt, return_tensors="pt")
-output = model.generate(**inputs, **generation_config)
+output = model.generate(**inputs, do_sample=True, top_p=0.95, top_k=0, max_new_tokens=512)
 ```
 
 ```python
 prompt = f"Question: {input_text}\n\nAnswer:"
 inputs = tokenizer(prompt, return_tensors="pt")
-output = model.generate(**inputs, **generation_config)
+output = model.generate(**inputs, do_sample=True, top_p=0.95, top_k=0, max_new_tokens=512)
 ```
 
 
@@ -81,5 +89,4 @@ BigBenchHard results:
 |**Average**| |0.3754
 
 # Ethical Considerations and Limitations
-Tulpar is a technology with potential risks and limitations. This model is finetuned only in English and all language-related scenarios are not covered. As Hyperbee.ai, we neither guarantee ethical, accurate, unbiased, objective responses nor endorse its outputs. Before deploying this model, you are advised to make safety tests for your use case.  
-
+Tulpar is a technology with potential risks and limitations. This model is finetuned only in English and all language-related scenarios are not covered. As Hyperbee.ai, we neither guarantee ethical, accurate, unbiased, objective responses nor endorse its outputs. Before deploying this model, you are advised to make safety tests for your use case.