HuggingFace Transformers

Use the Transformers library for NLP, vision, and audio on GPU.

All examples can be run on GPU servers rented through CLORE.AI Marketplace.

Renting on CLORE.AI

1. Visit CLORE.AI Marketplace

2. Filter by GPU type, VRAM, and price

3. Choose On-Demand (fixed rate) or Spot (bid price)

4. Configure your order:

   • Select Docker image

   • Set ports (TCP for SSH, HTTP for web UIs)

   • Add environment variables if needed

   • Enter startup command

5. Select payment: CLORE, BTC, or USDT/USDC

6. Create order and wait for deployment

Access Your Server

• Find connection details in My Orders

• Web interfaces: Use the HTTP port URL

• SSH: ssh -p <port> root@<proxy-address>

What is Transformers?

Hugging Face Transformers provides:

• 100,000+ pretrained models

• Easy model loading and inference

• Fine-tuning support

• Multi-modal capabilities

Quick Deploy

Docker Image:

pytorch/pytorch:2.5.1-cuda12.4-cudnn9-devel

Ports:

22/tcp

Command:

pip install transformers accelerate datasets huggingface_hub

Installation

pip install transformers[torch]
pip install accelerate  # For large models
pip install datasets    # For training data

Text Generation

Basic Generation

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_name = "mistralai/Mistral-7B-Instruct-v0.2"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float16,
    device_map="auto"
)

prompt = "Explain quantum computing in simple terms:"
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

outputs = model.generate(
    **inputs,
    max_new_tokens=200,
    temperature=0.7,
    do_sample=True
)

response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Chat Models

from transformers import pipeline

pipe = pipeline(
    "text-generation",
    model="meta-llama/Llama-2-7b-chat-hf",
    torch_dtype=torch.float16,
    device_map="auto"
)

messages = [
    {"role": "user", "content": "What is machine learning?"}
]

outputs = pipe(
    messages,
    max_new_tokens=256,
    do_sample=True,
    temperature=0.7
)

print(outputs[0]["generated_text"][-1]["content"])

Streaming

from transformers import TextStreamer

streamer = TextStreamer(tokenizer)

model.generate(
    **inputs,
    max_new_tokens=200,
    streamer=streamer
)

Quantization

4-bit Quantization

from transformers import AutoModelForCausalLM, BitsAndBytesConfig
import torch

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.float16,
    bnb_4bit_use_double_quant=True
)

model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-2-13b-hf",
    quantization_config=bnb_config,
    device_map="auto"
)

8-bit Quantization

model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-2-7b-hf",
    load_in_8bit=True,
    device_map="auto"
)

Embeddings

from transformers import AutoModel, AutoTokenizer
import torch

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

def get_embedding(text):
    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True).to("cuda")
    with torch.no_grad():
        outputs = model(**inputs)
    # Mean pooling
    embedding = outputs.last_hidden_state.mean(dim=1)
    return embedding

emb = get_embedding("Hello, world!")
print(f"Embedding shape: {emb.shape}")

Image Classification

from transformers import pipeline
from PIL import Image

classifier = pipeline("image-classification", model="google/vit-base-patch16-224", device=0)

image = Image.open("cat.jpg")
results = classifier(image)

for result in results:
    print(f"{result['label']}: {result['score']:.4f}")

Object Detection

from transformers import pipeline
from PIL import Image

detector = pipeline("object-detection", model="facebook/detr-resnet-50", device=0)

image = Image.open("street.jpg")
results = detector(image)

for result in results:
    print(f"{result['label']}: {result['score']:.4f} at {result['box']}")

Image Segmentation

from transformers import pipeline
from PIL import Image

segmenter = pipeline("image-segmentation", model="facebook/maskformer-swin-base-ade", device=0)

image = Image.open("scene.jpg")
results = segmenter(image)

for segment in results:
    print(f"{segment['label']}: score {segment['score']:.4f}")

Speech Recognition

from transformers import pipeline

transcriber = pipeline(
    "automatic-speech-recognition",
    model="openai/whisper-large-v3",
    device=0
)

result = transcriber("audio.mp3")
print(result["text"])

Text-to-Speech

from transformers import pipeline
import scipy

synthesizer = pipeline("text-to-speech", model="microsoft/speecht5_tts", device=0)

speech = synthesizer("Hello, this is a test of text to speech.")

scipy.io.wavfile.write("output.wav", rate=speech["sampling_rate"], data=speech["audio"])

Fine-Tuning

Prepare Dataset

from datasets import load_dataset

dataset = load_dataset("imdb")
train_dataset = dataset["train"].select(range(1000))
eval_dataset = dataset["test"].select(range(200))

Training

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

model_name = "bert-base-uncased"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=2)

def tokenize_function(examples):
    return tokenizer(examples["text"], padding="max_length", truncation=True)

tokenized_train = train_dataset.map(tokenize_function, batched=True)
tokenized_eval = eval_dataset.map(tokenize_function, batched=True)

training_args = TrainingArguments(
    output_dir="./results",
    evaluation_strategy="epoch",
    learning_rate=2e-5,
    per_device_train_batch_size=16,
    per_device_eval_batch_size=16,
    num_train_epochs=3,
    weight_decay=0.01,
    fp16=True,
)

trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=tokenized_train,
    eval_dataset=tokenized_eval,
)

trainer.train()

Pipeline Tasks

Task	Pipeline Name
Text Generation	text-generation
Fill Mask	fill-mask
Summarization	summarization
Translation	translation
Question Answering	question-answering
Sentiment Analysis	sentiment-analysis
Image Classification	image-classification
Object Detection	object-detection
Speech Recognition	automatic-speech-recognition
Text-to-Speech	text-to-speech

Multi-GPU

from transformers import AutoModelForCausalLM

# Automatic device placement
model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-2-70b-hf",
    device_map="auto",
    torch_dtype=torch.float16
)

# Manual device map
device_map = {
    "model.embed_tokens": 0,
    "model.layers.0": 0,
    "model.layers.1": 0,
    # ...
    "model.layers.39": 1,
    "model.norm": 1,
    "lm_head": 1
}

model = AutoModelForCausalLM.from_pretrained(
    "model_name",
    device_map=device_map
)

Memory Optimization

# Flash Attention 2
model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-2-7b-hf",
    torch_dtype=torch.float16,
    attn_implementation="flash_attention_2",
    device_map="auto"
)

# Gradient checkpointing
model.gradient_checkpointing_enable()

Model Hub

Download Models

from huggingface_hub import snapshot_download

snapshot_download(
    repo_id="meta-llama/Llama-2-7b-hf",
    local_dir="./llama-2-7b"
)

Upload Models

from huggingface_hub import HfApi

api = HfApi()
api.upload_folder(
    folder_path="./my_model",
    repo_id="username/my-model",
    repo_type="model"
)

Performance Tips

Tip	Effect
Use torch_dtype=torch.float16	50% less memory
Enable Flash Attention 2	2x faster attention
Use quantization	75% less memory
Batch inference	Higher throughput

Troubleshooting

Cost Estimate

Typical CLORE.AI marketplace rates (as of 2024):

GPU	Hourly Rate	Daily Rate	4-Hour Session
RTX 3060	~$0.03	~$0.70	~$0.12
RTX 3090	~$0.06	~$1.50	~$0.25
RTX 4090	~$0.10	~$2.30	~$0.40
A100 40GB	~$0.17	~$4.00	~$0.70
A100 80GB	~$0.25	~$6.00	~$1.00

Prices vary by provider and demand. Check CLORE.AI Marketplace for current rates.

Save money:

• Use Spot market for flexible workloads (often 30-50% cheaper)

• Pay with CLORE tokens

• Compare prices across different providers

Next Steps

• vLLM Inference - Production serving

• Fine-tune LLMs - LoRA training

• DeepSpeed Training - Distributed training