update checkpoint and remove trust_remote_code

README.md

@@ -51,15 +51,15 @@ pipeline_tag: text-generation
   <a href="https://github.com/MiniMax-AI/MiniMax-01" target="_blank" style="margin: 2px;">
     <img alt="GitHub" src="https://img.shields.io/badge/_GitHub-MinMax-FF4040?style=flat-square&labelColor=2C3E50" style="display: inline-block; vertical-align: middle;"/>
   </a>
-  <a href="https://huggingface.co/MiniMaxAI/MiniMax-Text-01/blob/main/LICENSE-MODEL" style="margin: 2px;">
+  <a href="https://huggingface.co/MiniMaxAI/MiniMax-Text-01-hf/blob/main/LICENSE-MODEL" style="margin: 2px;">
     <img alt="Model License" src="https://img.shields.io/badge/_Model_License-Model_Agreement-FF4040?style=flat-square&labelColor=2C3E50" style="display: inline-block; vertical-align: middle;"/>
   </a>
-   <a href="https://huggingface.co/MiniMaxAI/MiniMax-Text-01/blob/main/LICENSE-CODE" style="margin: 2px;">
+   <a href="https://huggingface.co/MiniMaxAI/MiniMax-Text-01-hf/blob/main/LICENSE-CODE" style="margin: 2px;">
     <img alt="Code License" src="https://img.shields.io/badge/_Code_License-MIT-FF4040?style=flat-square&labelColor=2C3E50" style="display: inline-block; vertical-align: middle;"/>
   </a>
 </div>
 <div align="center" style="line-height: 1;">
-  <a href="https://huggingface.co/MiniMaxAI/MiniMax-Text-01/blob/main/figures/wechat-qrcode.jpeg" target="_blank" style="margin: 2px;">
+  <a href="https://huggingface.co/MiniMaxAI/MiniMax-Text-01-hf/blob/main/figures/wechat-qrcode.jpeg" target="_blank" style="margin: 2px;">
     WeChat
   </a>
 </div>
@@ -174,7 +174,7 @@ Here we provide a simple example of loading the tokenizer and model to generate
 from transformers import AutoModelForCausalLM, AutoTokenizer, AutoConfig, QuantoConfig, GenerationConfig
 
 # load hf config
-hf_config = AutoConfig.from_pretrained("MiniMaxAI/MiniMax-Text-01", trust_remote_code=True)
+hf_config = AutoConfig.from_pretrained("MiniMaxAI/MiniMax-Text-01-hf")
 
 # quantization config, int8 is recommended
 quantization_config =  QuantoConfig(
@@ -200,7 +200,7 @@ for i in range(world_size):
         device_map[f'model.layers.{i * layers_per_device + j}'] = f'cuda:{i}'
 
 # load tokenizer
-tokenizer = AutoTokenizer.from_pretrained("MiniMaxAI/MiniMax-Text-01")
+tokenizer = AutoTokenizer.from_pretrained("MiniMaxAI/MiniMax-Text-01-hf")
 prompt = "Hello!"
 messages = [
     {"role": "system", "content": [{"type": "text", "text": "You are a helpful assistant created by MiniMax based on MiniMax-Text-01 model."}]},
@@ -216,11 +216,10 @@ model_inputs = tokenizer(text, return_tensors="pt").to("cuda")
 
 # load bfloat16 model, move to device, and apply quantization
 quantized_model = AutoModelForCausalLM.from_pretrained(
-    "MiniMaxAI/MiniMax-Text-01",
+    "MiniMaxAI/MiniMax-Text-01-hf",
     torch_dtype="bfloat16",
     device_map=device_map,
     quantization_config=quantization_config,
-    trust_remote_code=True,
     offload_buffers=True,
 )