Versions
v1: SFT -- 7658aab7702e56d9f5fa3b33bf7adcdae92f536b
Example
from transformers import AutoModelForCausalLM, AutoTokenizer
checkpoint = "belyakoff/SmolLM2-360M-Instruct-FT"
device = "cuda" # for GPU usage or "cpu" for CPU usage
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
# for multiple GPUs install accelerate and do `model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map="auto")`
model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
messages = [{"role": "user", "content": "Столица России?"}]
input_text=tokenizer.apply_chat_template(messages, tokenize=False)
print(input_text)
inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
outputs = model.generate(inputs, max_new_tokens=50, temperature=0.2, top_p=0.9, do_sample=True)
print(tokenizer.decode(outputs[0]))
# Столица России — Москва. Это один из самых известных и культурно значимых городов в мире.
Limitations
Don't change system prompt. Changing system prompt will make the model go crazy.