update

README.md

@@ -40,11 +40,11 @@ pip install transformers torch torchvision einops timm peft sentencepiece flash_
 
 ```python
 import torch
-from transformers import AutoModel, AutoTokenizer
+from transformers import AutoConfig, AutoModel, AutoTokenizer
 
 
 # Set up the model and tokenizer
-model_path = 'h2oai/h2o-mississippi-800m'
+model_path = 'h2oai/h2ovl-mississippi-800m'
 config = AutoConfig.from_pretrained(model_path, trust_remote_code=True)
 config.llm_config._attn_implementation = 'flash_attention_2'
 model = AutoModel.from_pretrained(
@@ -54,7 +54,7 @@ model = AutoModel.from_pretrained(
     low_cpu_mem_usage=True,
     trust_remote_code=True).eval().cuda()
 tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True, use_fast=False)
-generation_config = dict(max_new_tokens=1024, do_sample=True)
+generation_config = dict(max_new_tokens=2048, do_sample=True)
 
 # pure-text conversation
 question = 'Hello, how are you?'