Update README.md

README.md

@@ -170,8 +170,8 @@ Install the latest transformers (>4.40)
 from transformers import AutoModelForCausalLM, AutoTokenizer
 device = "cuda" # the device to load the model onto
 # use bfloat16 to ensure the best performance.
-model = AutoModelForCausalLM.from_pretrained("SeaLLMs/SeaLLM-7B-v2.5", torch_dtype=torch.bfloat16, device_map=device)
-tokenizer = AutoTokenizer.from_pretrained("SeaLLMs/SeaLLM-7B-v2.5")
+model = AutoModelForCausalLM.from_pretrained("SorawitChok/SeaLLM-7B-v2.5-AWQ", torch_dtype=torch.bfloat16, device_map=device)
+tokenizer = AutoTokenizer.from_pretrained("SorawitChok/SeaLLM-7B-v2.5-AWQ")
 messages = [
     {"role": "system", "content": "You are a helpful assistant."},
     {"role": "user", "content": "Hello world"},
@@ -207,7 +207,10 @@ def seallm_chat_convo_format(conversations, add_assistant_prefix: bool, system_p
 sparams = SamplingParams(temperature=0.1, max_tokens=1024, stop=['<eos>', '<|im_start|>'])
 llm = LLM("SorawitChok/SeaLLM-7B-v2.5-AWQ", quantization="AWQ")
 
-message = "Explain general relativity in details."
+message = [
+            {"role": "user", "content": "Explain general relativity in details."}
+          ]
+
 prompt = seallm_chat_convo_format(message, True)
 gen = llm.generate(prompt, sampling_params)