Instructions to use Mikivis/gpt2-large-lora-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mikivis/gpt2-large-lora-sft with Transformers:

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

pipe = pipeline("text-generation", model="Mikivis/gpt2-large-lora-sft")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Mikivis/gpt2-large-lora-sft")
model = AutoModelForCausalLM.from_pretrained("Mikivis/gpt2-large-lora-sft")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Mikivis/gpt2-large-lora-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mikivis/gpt2-large-lora-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mikivis/gpt2-large-lora-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Mikivis/gpt2-large-lora-sft

SGLang

How to use Mikivis/gpt2-large-lora-sft 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 "Mikivis/gpt2-large-lora-sft" \
    --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": "Mikivis/gpt2-large-lora-sft",
		"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 "Mikivis/gpt2-large-lora-sft" \
        --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": "Mikivis/gpt2-large-lora-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Mikivis/gpt2-large-lora-sft with Docker Model Runner:
```
docker model run hf.co/Mikivis/gpt2-large-lora-sft
```

gpt2-large-lora-sft

This model is a fine-tuned version of gpt2-large on the customized dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.00013
train_batch_size: 1
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 6
total_train_batch_size: 6
total_eval_batch_size: 48
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 2.5

Training results

Framework versions

Transformers 4.32.1
Pytorch 2.0.1+cu117
Datasets 2.10.1
Tokenizers 0.13.3

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	28.05
ARC (25-shot)	26.79
HellaSwag (10-shot)	44.15
MMLU (5-shot)	25.82
TruthfulQA (0-shot)	39.06
Winogrande (5-shot)	55.09
GSM8K (5-shot)	0.0
DROP (3-shot)	5.46

Downloads last month: 12

Safetensors

Model size

0.8B params

Tensor type

F16

Model tree for Mikivis/gpt2-large-lora-sft

Base model

openai-community/gpt2-large

Finetuned

(129)

this model

Mikivis
/

gpt2-large-lora-sft