File size: 1,196 Bytes
44ee478 98735f0 44ee478 98735f0 44ee478 98735f0 44ee478 98735f0 44ee478 98735f0 44ee478 98735f0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 |
from transformers import AutoModelForCausalLM, AutoTokenizer, AutoConfig, QuantoConfig, GenerationConfig
model = "/Users/Goekdeniz.Guelmez@computacenter.com/Library/CloudStorage/OneDrive-COMPUTACENTER/Desktop/MiniMax01Text-Dev"
hf_config = AutoConfig.from_pretrained(model, trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = "Hello!"
messages = [
{"role": "system", "content": "You are a helpful assistant created by MiniMax based on MiniMax-Text-01 model."},
{"role": "user", "content": prompt},
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer(text, return_tensors="pt")
model = AutoModelForCausalLM.from_pretrained(
model,
trust_remote_code=True
)
generation_config = GenerationConfig(
max_new_tokens=20,
eos_token_id=200020,
use_cache=True,
)
generated_ids = model.generate(**model_inputs, generation_config=generation_config)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response) |