Update README.md

README.md

@@ -368,6 +368,42 @@ After installing `mistral_inference`, a `mistral-chat` CLI command should be ava
 mistral-chat $HOME/mistral_models/8B-Instruct --instruct --max_tokens 256
 ```
 
+### Passkey detection
+
+```py
+from mistral_inference.transformer import Transformer
+from pathlib import Path
+import json
+from mistral_inference.generate import generate
+from huggingface_hub import hf_hub_download
+
+from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
+from mistral_common.protocol.instruct.messages import UserMessage
+from mistral_common.protocol.instruct.request import ChatCompletionRequest
+
+def load_passkey_request() -> ChatCompletionRequest:
+    passkey_file = hf_hub_download(repo_id="mistralai/Ministral-8B-Instruct-2410", filename="passkey_example.json")
+
+    with open(passkey_file, "r") as f:
+        data = json.load(f)
+
+    message_content = data["messages"][0]["content"]
+    return ChatCompletionRequest(messages=[UserMessage(content=message_content)])
+
+tokenizer = MistralTokenizer.from_file(f"{mistral_models_path}/tekken.json")
+model = Transformer.from_folder(mistral_models_path, softmax_fp32=False)
+
+completion_request = load_passkey_request()
+
+tokens = tokenizer.encode_chat_completion(completion_request).tokens
+
+out_tokens, _ = generate([tokens], model, max_tokens=64, temperature=0.0, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id)
+result = tokenizer.instruct_tokenizer.tokenizer.decode(out_tokens[0])
+
+print(result)
+```
+
+
 ### Instruct following
 
 ```py
@@ -402,9 +438,13 @@ from mistral_inference.generate import generate
 from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
 from mistral_common.protocol.instruct.messages import UserMessage
 from mistral_common.protocol.instruct.request import ChatCompletionRequest
+from mistral_common.tokens.tokenizers.tekken import SpecialTokenPolicy
 
 
 tokenizer = MistralTokenizer.from_file(f"{mistral_models_path}/tekken.json")
+tekken = tokenizer.instruct_tokenizer.tokenizer
+tekken.special_token_policy = SpecialTokenPolicy.IGNORE
+
 model = Transformer.from_folder(mistral_models_path)
 
 completion_request = ChatCompletionRequest(