implementing-llms-litgpt

litgpt download list

Fine-Tuning Setup:
- [ ] Step 1: Download pretrained model
- [ ] Step 2: Prepare dataset
- [ ] Step 3: Configure training
- [ ] Step 4: Run fine-tuning

# Download Llama 3 8B
litgpt download meta-llama/Meta-Llama-3-8B
 
# Download Phi-2 (smaller, faster)
litgpt download microsoft/phi-2
 
# Download Gemma 2B
litgpt download google/gemma-2b

[
  {
    "instruction": "What is the capital of France?",
    "input": "",
    "output": "The capital of France is Paris."
  },
  {
    "instruction": "Translate to Spanish: Hello, how are you?",
    "input": "",
    "output": "Hola, ¿cómo estás?"
  }
]

# Full fine-tuning (requires 40GB+ GPU for 7B models)
litgpt finetune \
  meta-llama/Meta-Llama-3-8B \
  --data JSON \
  --data.json_path data/my_dataset.json \
  --train.max_steps 1000 \
  --train.learning_rate 2e-5 \
  --train.micro_batch_size 1 \
  --train.global_batch_size 16
 
# LoRA fine-tuning (efficient, 16GB GPU)
litgpt finetune_lora \
  microsoft/phi-2 \
  --data JSON \
  --data.json_path data/my_dataset.json \
  --lora_r 16 \
  --lora_alpha 32 \
  --lora_dropout 0.05 \
  --train.max_steps 1000 \
  --train.learning_rate 1e-4

# View logs
tail -f out/finetune/logs.txt
 
# TensorBoard (if using --train.logger_name tensorboard)
tensorboard --logdir out/finetune/lightning_logs

LoRA Training:
- [ ] Step 1: Choose base model
- [ ] Step 2: Configure LoRA parameters
- [ ] Step 3: Train with LoRA
- [ ] Step 4: Merge LoRA weights (optional)

litgpt finetune_lora \
  microsoft/phi-2 \
  --data JSON \
  --data.json_path data/my_dataset.json \
  --lora_r 16 \          # LoRA rank (8-64, higher=more capacity)
  --lora_alpha 32 \      # LoRA scaling (typically 2×r)
  --lora_dropout 0.05 \  # Prevent overfitting
  --lora_query true \    # Apply LoRA to query projection
  --lora_key false \     # Usually not needed
  --lora_value true \    # Apply LoRA to value projection
  --lora_projection true \  # Apply LoRA to output projection
  --lora_mlp false \     # Usually not needed
  --lora_head false      # Usually not needed

litgpt finetune_lora \
  microsoft/phi-2 \
  --data JSON \
  --data.json_path data/my_dataset.json \
  --lora_r 16 \
  --train.epochs 3 \
  --train.learning_rate 1e-4 \
  --train.micro_batch_size 4 \
  --train.global_batch_size 32 \
  --out_dir out/phi2-lora
 
# Memory usage: ~8-12GB for Phi-2 with LoRA

litgpt merge_lora \
  out/phi2-lora/final \
  --out_dir out/phi2-merged

from litgpt import LLM
llm = LLM.load("out/phi2-merged")

Pretraining:
- [ ] Step 1: Prepare pretraining dataset
- [ ] Step 2: Configure model architecture
- [ ] Step 3: Set up multi-GPU training
- [ ] Step 4: Launch pretraining

python scripts/prepare_dataset.py \
  --source_path data/my_corpus.txt \
  --checkpoint_dir checkpoints/tokenizer \
  --destination_path data/pretrain \
  --split train,val

# config/pythia-160m.yaml
model_name: pythia-160m
block_size: 2048
vocab_size: 50304
n_layer: 12
n_head: 12
n_embd: 768
rotary_percentage: 0.25
parallel_residual: true
bias: true

# Single GPU
litgpt pretrain \
  --config config/pythia-160m.yaml \
  --data.data_dir data/pretrain \
  --train.max_tokens 10_000_000_000
 
# Multi-GPU with FSDP
litgpt pretrain \
  --config config/pythia-1b.yaml \
  --data.data_dir data/pretrain \
  --devices 8 \
  --train.max_tokens 100_000_000_000

# Using SLURM
sbatch --nodes=8 --gpus-per-node=8 \
  pretrain_script.sh
 
# pretrain_script.sh content:
litgpt pretrain \
  --config config/pythia-1b.yaml \
  --data.data_dir /shared/data/pretrain \
  --devices 8 \
  --num_nodes 8 \
  --train.global_batch_size 512 \
  --train.max_tokens 300_000_000_000

Model Deployment:
- [ ] Step 1: Test inference locally
- [ ] Step 2: Quantize model (optional)
- [ ] Step 3: Convert to GGUF (for llama.cpp)
- [ ] Step 4: Deploy with API

from litgpt import LLM
 
llm = LLM.load("out/phi2-lora/final")
 
# Single generation
print(llm.generate("What is machine learning?"))
 
# Streaming
for token in llm.generate("Explain quantum computing", stream=True):
    print(token, end="", flush=True)
 
# Batch inference
prompts = ["Hello", "Goodbye", "Thank you"]
results = [llm.generate(p) for p in prompts]

# 8-bit quantization (50% size reduction)
litgpt convert_lit_checkpoint \
  out/phi2-lora/final \
  --dtype bfloat16 \
  --quantize bnb.nf4
 
# 4-bit quantization (75% size reduction)
litgpt convert_lit_checkpoint \
  out/phi2-lora/final \
  --quantize bnb.nf4-dq  # Double quantization

python scripts/convert_lit_checkpoint.py \
  --checkpoint_path out/phi2-lora/final \
  --output_path models/phi2.gguf \
  --model_name microsoft/phi-2

from fastapi import FastAPI
from litgpt import LLM
 
app = FastAPI()
llm = LLM.load("out/phi2-lora/final")
 
@app.post("/generate")
def generate(prompt: str, max_tokens: int = 100):
    result = llm.generate(
        prompt,
        max_new_tokens=max_tokens,
        temperature=0.7
    )
    return {"response": result}
 
# Run: uvicorn api:app --host 0.0.0.0 --port 8000

# Instead of litgpt finetune (requires 40GB+)
litgpt finetune_lora  # Only needs 12-16GB

litgpt finetune_lora \
  ... \
  --train.gradient_accumulation_iters 4  # Accumulate gradients

# Already enabled by default on Ampere+ GPUs (A100, RTX 30/40 series)
# No configuration needed

--train.micro_batch_size 1 \
--train.global_batch_size 32 \
--train.gradient_accumulation_iters 32  # Effective batch=32

# List all available models
litgpt download list
 
# Download if not exists
litgpt download meta-llama/Meta-Llama-3-8B

ls checkpoints/
# Should see: meta-llama/Meta-Llama-3-8B/

--lora_r 8  # Instead of 16 or 32

--lora_query true \
--lora_value true \
--lora_projection false \  # Disable this
--lora_mlp false  # And this