from transformers import AutoConfig, AutoModel, AutoTokenizer

undefined

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "meta-llama/Llama-3.2-1B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto",  # Automatic device placement
)

from transformers import (
    AutoModelForCausalLM,          # Text generation (GPT, Llama)
    AutoModelForSeq2SeqLM,         # Encoder-decoder (T5, BART)
    AutoModelForSequenceClassification,  # Classification
    AutoModelForTokenClassification,     # NER, POS tagging
    AutoModelForQuestionAnswering,       # Extractive QA
    AutoModelForMaskedLM,                # BERT-style masked LM
    AutoModelForImageClassification,     # Vision models
    AutoModelForSpeechSeq2Seq,           # Speech recognition
)

from transformers import pipeline

undefined

from transformers import pipeline
import torch

pipe = pipeline(
    "text-generation",
    model="meta-llama/Meta-Llama-3-8B-Instruct",
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Explain quantum computing in simple terms."},
]

response = pipe(messages, max_new_tokens=256)
print(response[0]["generated_text"][-1]["content"])

undefined

undefined

undefined

undefined

undefined

undefined

from transformers import AutoModelForCausalLM
import torch

undefined

undefined

undefined

model = AutoModelForCausalLM.from_pretrained(
    "microsoft/phi-2",
    trust_remote_code=True,  # Required for custom architectures
)

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_name = "Qwen/Qwen2.5-3B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

undefined

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What is the capital of France?"},
]

undefined

from transformers import AutoModel, AutoTokenizer
import torch

model = AutoModel.from_pretrained("sentence-transformers/all-MiniLM-L6-v2")
tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/all-MiniLM-L6-v2")

def get_embeddings(texts: list[str]) -> torch.Tensor:
    inputs = tokenizer(texts, padding=True, truncation=True, return_tensors="pt")

    with torch.no_grad():
        outputs = model(**inputs)

    # Mean pooling
    attention_mask = inputs["attention_mask"]
    embeddings = outputs.last_hidden_state
    mask_expanded = attention_mask.unsqueeze(-1).expand(embeddings.size()).float()
    sum_embeddings = (embeddings * mask_expanded).sum(1)
    sum_mask = mask_expanded.sum(1).clamp(min=1e-9)
    return sum_embeddings / sum_mask

embeddings = get_embeddings(["Hello world", "How are you?"])

from transformers import AutoModelForSequenceClassification, AutoTokenizer
import torch

model = AutoModelForSequenceClassification.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english")
tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english")

inputs = tokenizer("I love this movie!", return_tensors="pt")

with torch.no_grad():
    outputs = model(**inputs)
    predictions = torch.softmax(outputs.logits, dim=-1)

labels = model.config.id2label
for idx, prob in enumerate(predictions[0]):
    print(f"{labels[idx]}: {prob:.4f}")

from transformers import (
    AutoModelForSequenceClassification,
    AutoTokenizer,
    Trainer,
    TrainingArguments,
)
from datasets import load_dataset

undefined

undefined

See `reference/fine-tuning.md` for advanced patterns including LoRA, custom data collators, and evaluation metrics.

from transformers import AutoImageProcessor, AutoModelForImageClassification
from PIL import Image

processor = AutoImageProcessor.from_pretrained("google/vit-base-patch16-224")
model = AutoModelForImageClassification.from_pretrained("google/vit-base-patch16-224")

image = Image.open("image.jpg")
inputs = processor(images=image, return_tensors="pt")

with torch.no_grad():
    outputs = model(**inputs)
    predicted_class = outputs.logits.argmax(-1).item()
    print(model.config.id2label[predicted_class])

from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
import torch

processor = AutoProcessor.from_pretrained("openai/whisper-large-v3")
model = AutoModelForSpeechSeq2Seq.from_pretrained(
    "openai/whisper-large-v3",
    torch_dtype=torch.float16,
    device_map="auto",
)

undefined

from transformers import AutoProcessor, AutoModelForVision2Seq
from PIL import Image
import torch

model_name = "llava-hf/llava-1.5-7b-hf"
processor = AutoProcessor.from_pretrained(model_name)
model = AutoModelForVision2Seq.from_pretrained(
    model_name,
    torch_dtype=torch.float16,
    device_map="auto",
)

image = Image.open("image.jpg")
prompt = "USER: <image>\nDescribe this image in detail.\nASSISTANT:"

inputs = processor(text=prompt, images=image, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=200)
response = processor.decode(outputs[0], skip_special_tokens=True)

from transformers import AutoModelForCausalLM, BitsAndBytesConfig
import torch

undefined

model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-3.2-3B",
    torch_dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",  # Requires flash-attn package
    device_map="auto",
)

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16)
model = torch.compile(model, mode="reduce-overhead")

texts = ["First prompt", "Second prompt", "Third prompt"]
inputs = tokenizer(texts, return_tensors="pt", padding=True).to(model.device)

with torch.no_grad():
    outputs = model.generate(**inputs, max_new_tokens=50)

decoded = tokenizer.batch_decode(outputs, skip_special_tokens=True)