Update README.md

README.md

@@ -97,7 +97,7 @@ It achieves the following results on the evaluation set:
 
 ## Model description
 
-For more information, see the mode card of the [base model](https://huggingface.co/LemiSt/SmolLM-135M-de). This adapter was trained using qlora at rank 32 with alpha 16, applying a dataset of around 200k german chat samples for two epochs.
+For more information, see the model card of the [base model](https://huggingface.co/LemiSt/SmolLM-135M-de). This adapter was trained using qlora at rank 32 with alpha 16, applying a dataset of around 200k german chat samples for two epochs.
 
 ## Intended uses & limitations
 
@@ -116,7 +116,7 @@ messages = [
   {"role": "user", "content": "Wie viele Hände hat ein normaler Mensch?"}
 ]
 inputs = tokenizer.apply_chat_template(messages, tokenize=True, return_tensors="pt", add_generation_prompt=True).to(device)
-outputs = model.generate(inputs, max_new_tokens=256, do_sample=True, temperature=0.3, top_p=0.9, repetition_penalty=1.2)
+outputs = model.generate(inputs, max_new_tokens=256, do_sample=True, temperature=0.4, top_p=0.9, repetition_penalty=1.1, top_k=512)
 print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))
 ```
 ## Training and evaluation data