В семействе 2 модели:
🟢Zamba2-1.2B-instruct;
🟠Zamba2-2.7B-instruct.
# Clone repo
git clone https://github.com/Zyphra/transformers_zamba2.git
cd transformers_zamba2
# Install the repository & accelerate:
pip install -e .
pip install accelerate
# Inference:
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)
user_turn_1 = "user_prompt1."
assistant_turn_1 = "assistant_prompt."
user_turn_2 = "user_prompt2."
sample = [{'role': 'user', 'content': user_turn_1}, {'role': 'assistant', 'content': assistant_turn_1}, {'role': 'user', 'content': user_turn_2}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))🖥GitHub
https://t.me/deep_learning_proj