inkoziev/

charllama-35M

import charactertokenizer

...
tokenizer = charactertokenizer.CharacterTokenizer.from_pretrained('inkoziev/charllama-35M')

prompt = '<s>У Лукоморья дуб зеленый\n'
encoded_prompt = tokenizer.encode(prompt, return_tensors='pt')
print('Tokenized prompt:', ' | '.join(tokenizer.decode([t]) for t in encoded_prompt[0]))

import os
import torch
import transformers
import charactertokenizer

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

model_name_or_path = 'inkoziev/charllama-35M'
model = transformers.AutoModelForCausalLM.from_pretrained(model_name_or_path)
model.to(device)
model.eval()

tokenizer = charactertokenizer.CharacterTokenizer.from_pretrained(model_path)

prompt = 'Меня зовут Ар'
encoded_prompt = tokenizer.encode(prompt, return_tensors='pt')

output_sequences = model.generate(
    input_ids=encoded_prompt.to(device),
    max_length=500,
    temperature=1.0,
    top_k=0,
    top_p=0.8,
    repetition_penalty=1.0,
    do_sample=True,
    num_return_sequences=5,
    pad_token_id=0,
)

for o in output_sequences:
    text = tokenizer.decode(o)
    if text.startswith('<s>'):
        text = text.replace('<s>', '')
    text = text[:text.index('</s>')].strip()
    print(text)
    print('-'*80)