Update README.md

README.md

@@ -3,13 +3,15 @@ library_name: transformers
 tags: []
 ---
 
+*There currently is an issue with the **model generating random reserved special tokens (like "<|reserved_special_token_49|>") at the end**. Please use with `skip_special_tokens=true`. We will update once we found the reason for this behaviour. If you found a solution, plesae let us know!*.
+
 # Llama 3 DiscoLM German 8b v0.1 Experimental
 
 <p align="center"><img src="disco_llama.webp" width="400"></p>
 
 # Introduction
 
-**Llama 3 DiscoLM German 8b v0.1 Experimental** is an experimental Llama 3 based version of DiscoLM German.
+**Llama 3 DiscoLM German 8b v0.1 Experimental** is an experimental Llama 3 based version of [DiscoLM German](https://huggingface.co/DiscoResearch/DiscoLM_German_7b_v1).
 
 This is an experimental release and not intended for production use. The model is still in development and will be updated with new features and improvements in the future.
 
@@ -43,6 +45,46 @@ model.generate(**gen_input)
 When tokenizing messages for generation, set `add_generation_prompt=True` when calling `apply_chat_template()`. This will append `<|im_start|>assistant\n` to your prompt, to ensure
 that the model continues with an assistant response.
 
+# Example Code for Inference
+
+```python
+model_id = "DiscoResearch/Llama3_DiscoLM_German_8b_v0.1_experimental"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+
+messages = [
+    {"role": "system", "content": "Du bist ein hilfreicher Assistent."},
+    {"role": "user", "content": "Wer bist du?"},
+]
+
+input_ids = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    return_tensors="pt"
+).to(model.device)
+
+terminators = [
+    tokenizer.eos_token_id,
+    tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
+
+outputs = model.generate(
+    input_ids,
+    max_new_tokens=256,
+    eos_token_id=terminators,
+    do_sample=True,
+    temperature=0.6,
+    top_p=0.9,
+)
+response = outputs[0][input_ids.shape[-1]:]
+print(tokenizer.decode(response, skip_special_tokens=True))
+```
+
 
 # Limitations & Biases