Instructions to use phinate/my_finetuned_GPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use phinate/my_finetuned_GPT with Transformers:

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

pipe = pipeline("text-generation", model="phinate/my_finetuned_GPT")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("phinate/my_finetuned_GPT")
model = AutoModelForMultimodalLM.from_pretrained("phinate/my_finetuned_GPT")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use phinate/my_finetuned_GPT with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/phinate/my_finetuned_GPT

SGLang

How to use phinate/my_finetuned_GPT 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 "phinate/my_finetuned_GPT" \
    --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": "phinate/my_finetuned_GPT",
		"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 "phinate/my_finetuned_GPT" \
        --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": "phinate/my_finetuned_GPT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use phinate/my_finetuned_GPT with Docker Model Runner:
```
docker model run hf.co/phinate/my_finetuned_GPT
```

my_finetuned_GPT

This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.4836

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	17	2.8296
No log	2.0	34	2.6582
No log	3.0	51	2.5844
No log	4.0	68	2.5321
No log	5.0	85	2.5066
No log	6.0	102	2.4886
No log	7.0	119	2.4846
No log	8.0	136	2.4754
No log	9.0	153	2.4724
No log	10.0	170	2.4703
No log	11.0	187	2.4751
No log	12.0	204	2.4703
No log	13.0	221	2.4746
No log	14.0	238	2.4774
No log	15.0	255	2.4779
No log	16.0	272	2.4810
No log	17.0	289	2.4828
No log	18.0	306	2.4833
No log	19.0	323	2.4835
No log	20.0	340	2.4836

Framework versions

Transformers 4.28.1
Pytorch 2.0.0+cu118
Datasets 2.12.0
Tokenizers 0.13.3

Downloads last month: 2