Instructions to use RGarrido03/GPT2-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RGarrido03/GPT2-LoRA with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("openai-community/gpt2")
model = PeftModel.from_pretrained(base_model, "RGarrido03/GPT2-LoRA")

Transformers

How to use RGarrido03/GPT2-LoRA with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="RGarrido03/GPT2-LoRA")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("RGarrido03/GPT2-LoRA", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RGarrido03/GPT2-LoRA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RGarrido03/GPT2-LoRA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RGarrido03/GPT2-LoRA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RGarrido03/GPT2-LoRA

SGLang

How to use RGarrido03/GPT2-LoRA with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "RGarrido03/GPT2-LoRA" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RGarrido03/GPT2-LoRA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "RGarrido03/GPT2-LoRA" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RGarrido03/GPT2-LoRA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use RGarrido03/GPT2-LoRA with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for RGarrido03/GPT2-LoRA to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for RGarrido03/GPT2-LoRA to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RGarrido03/GPT2-LoRA to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="RGarrido03/GPT2-LoRA",
    max_seq_length=2048,
)

Docker Model Runner
How to use RGarrido03/GPT2-LoRA with Docker Model Runner:
```
docker model run hf.co/RGarrido03/GPT2-LoRA
```

Model Card for unsloth

This model is a fine-tuned version of openai-community/gpt2 on the knkarthick/samsum dataset. It has been trained using TRL.

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="None", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with SFT.

Training Hyperparameters

The following hyperparameters were used during training:

Parameter	Value
LoRA Rank ($r$)	32
LoRA Alpha (Scale)	16.0
LoRA Dropout	0.0
Learning Rate	2e-4
Optimizer	AdamW
Batch Size	4
Epochs	3
Seed	3407

Training Metrics

Training was monitored via Weights & Biases (W&B).

Final Training Loss: 2.5596
Final Validation Loss: 2.4426

{
  "_runtime": 1828,
  "_step": 303,
  "_timestamp": 1776940747.4150884,
  "_wandb.runtime": 1828,
  "eval/loss": 2.442631959915161,
  "eval/runtime": 8.4963,
  "eval/samples_per_second": 96.277,
  "eval/steps_per_second": 24.128,
  "total_flos": 4539887471702016,
  "train/epoch": 3,
  "train/global_step": 2763,
  "train/grad_norm": 0.24430057406425476,
  "train/learning_rate": 2.985074626865672e-7,
  "train/loss": 2.5596,
  "train_loss": 2.563603694569232,
  "train_runtime": 1834.6214,
  "train_samples_per_second": 24.088,
  "train_steps_per_second": 1.506
}

Framework versions

PEFT 0.19.1
TRL: 0.24.0
Transformers: 4.57.3
Pytorch: 2.10.0
Datasets: 4.3.0
Tokenizers: 0.22.2

Downloads last month: 83

Model tree for RGarrido03/GPT2-LoRA

Base model

openai-community/gpt2

Adapter

(1688)

this model

RGarrido03
/

GPT2-LoRA