Merge branch 'main' of https://huggingface.co/nicholascao/chatbloom-1b7-sft into main

README.md

@@ -35,16 +35,17 @@ See [Github](https://github.com/NicholasCao/ChatBloom) for details.
 ## Usage
 ```python
 import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
 tokenizer = AutoTokenizer.from_pretrained('nicholascao/chatbloom-1b7-sft')
+tokenizer.pad_token_id = tokenizer.eos_token_id
+
 model = AutoModelForCausalLM.from_pretrained('nicholascao/chatbloom-1b7-sft').half()
-generation_config = GenerationConfig.from_pretrained('nicholascao/chatbloom-1b7-sft')
 
 inputs = tokenizer('<Human>: Hello <eoh> <Assistant>:', return_tensors='pt').to(torch.cuda.current_device())
 model.to(torch.cuda.current_device())
 
-output = model.generate(**inputs, generation_config=generation_config)
+output = model.generate(**inputs, max_length=768, do_sample=True, temperature=0.8, top_k=50, early_stopping=True, repetition_penalty=1.05)
 output = tokenizer.decode(output[0], skip_special_tokens=True)
 print(output)
 ```