license: apache-2.0
note : use original open llama tokenizer
#model_path = 'openlm-research/open_llama_3b' model_path = 'ruwan/open-llama-sharded-1GB-7B-alpaca-vmware'
model_path = 'openlm-research/open_llama_13b_600bt'
tokenizer = LlamaTokenizer.from_pretrained("openlm-research/open_llama_7b") model = LlamaForCausalLM.from_pretrained( model_path, torch_dtype=torch.float16, device_map='auto',load_in_8bit=True )
prompt_template = "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response:"
prompt= 'Explain in simple terms how the attention mechanism of a transformer model works'
inputt = prompt_template.format(instruction= prompt) input_ids = tokenizer(inputt, return_tensors="pt").input_ids.to("cuda")
output1 = model.generate(input_ids, max_length=512) input_length = input_ids.shape[1] output1 = output1[:, input_length:] output= tokenizer.decode(output1[0])