vitekkor/T-pro-it-1.0-bnb-8bit
This model is an 8-bit quantization of model t-tech/T-pro-it-1.0
using bitsandbytes.
Refer to the original model card for more details on the model.
Use with transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
MODEL_NAME = "vitekkor/T-pro-it-1.0-bnb-8bit"
model = AutoModelForCausalLM.from_pretrained(
MODEL_NAME,
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
prompt = "Напиши стих про машинное обучение"
messages = [
{"role": "system", "content": "Ты T-pro, виртуальный ассистент в Т-Технологии. Твоя задача - быть полезным диалоговым ассистентом."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
generated_ids = model.generate(
**model_inputs,
max_new_tokens=256
)
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)
Use with vllm
Python
pip install vllm
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
MODEL_NAME = "vitekkor/T-pro-it-1.0-bnb-8bit"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
llm = LLM(model=MODEL_NAME, max_model_len=8192)
prompt = "Напиши стих про машинное обучение"
messages = [
{"role": "system", "content": "Ты T-pro, виртуальный ассистент в Т-Технологии. Твоя задача - быть полезным диалоговым ассистентом."},
{"role": "user", "content": prompt}
]
prompt_token_ids = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)
Server:
vllm serve vitekkor/T-pro-it-1.0-bnb-8bit
- Downloads last month
- 572
Model tree for vitekkor/T-pro-it-1.0-bnb-8bit
Base model
t-tech/T-pro-it-1.0