Update README.md

README.md

@@ -97,7 +97,7 @@ messages = [
     },
 ]
 
-outputs = llm.chat(messages, sampling_params=sampling_params)
+outputs = llm.generate(messages, sampling_params=sampling_params)
 
 print(outputs[0].outputs[0].text)
 ```
@@ -136,26 +136,31 @@ from mistral_inference.transformer import Transformer
 from mistral_inference.generate import generate
 
 from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
-from mistral_common.protocol.instruct.messages import UserMessage, TextChunk, ImageURLChunk
-from mistral_common.protocol.instruct.request import CompletionRequest
+from mistral_common.protocol.instruct.messages import TextChunk, ImageURLChunk
 
+mistral_models_path = "/mnt/vast/shared/william/pixtral_pretrain_release"
 tokenizer = MistralTokenizer.from_file(f"{mistral_models_path}/tekken.json")
 model = Transformer.from_folder(mistral_models_path)
 
 url = "https://huggingface.co/datasets/patrickvonplaten/random_img/resolve/main/yosemite.png"
 prompt = "The above image presents a"
 
-completion_request = CompletionRequest(prompt=[UserMessage(content=[ImageURLChunk(image_url=url), TextChunk(text=prompt)])])
+user_content = [ImageURLChunk(image_url=url), TextChunk(text=prompt)]
 
-encoded = tokenizer.encode_chat_completion(completion_request)
+tokens, images = tokenizer.instruct_tokenizer.encode_user_content(user_content, False)
 
-images = encoded.images
-tokens = encoded.tokens
-
-out_tokens, _ = generate([tokens], model, images=[images], max_tokens=256, temperature=0.35, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id)
+out_tokens, _ = generate(
+    [tokens],
+    model,
+    images=[images],
+    max_tokens=256,
+    temperature=0.35,
+    eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id,
+)
 result = tokenizer.decode(out_tokens[0])
 
-print(result)
+print("Prompt:", prompt)
+print("Completion:", result)
 ```
 
 ## Limitations