Instructions to use gjonesQ02/StatementOfWork_Generator_Omega2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gjonesQ02/StatementOfWork_Generator_Omega2 with Transformers:

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

pipe = pipeline("text-generation", model="gjonesQ02/StatementOfWork_Generator_Omega2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gjonesQ02/StatementOfWork_Generator_Omega2")
model = AutoModelForCausalLM.from_pretrained("gjonesQ02/StatementOfWork_Generator_Omega2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use gjonesQ02/StatementOfWork_Generator_Omega2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gjonesQ02/StatementOfWork_Generator_Omega2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gjonesQ02/StatementOfWork_Generator_Omega2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/gjonesQ02/StatementOfWork_Generator_Omega2

SGLang

How to use gjonesQ02/StatementOfWork_Generator_Omega2 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 "gjonesQ02/StatementOfWork_Generator_Omega2" \
    --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": "gjonesQ02/StatementOfWork_Generator_Omega2",
		"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 "gjonesQ02/StatementOfWork_Generator_Omega2" \
        --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": "gjonesQ02/StatementOfWork_Generator_Omega2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use gjonesQ02/StatementOfWork_Generator_Omega2 with Docker Model Runner:
```
docker model run hf.co/gjonesQ02/StatementOfWork_Generator_Omega2
```

StatementOfWork_Generator_Omega2

This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.9436

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: 50
eval_batch_size: 50
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	15	0.9674
No log	2.0	30	0.9673
No log	3.0	45	0.9633
No log	4.0	60	0.9629
No log	5.0	75	0.9633
No log	6.0	90	0.9634
No log	7.0	105	0.9635
No log	8.0	120	0.9603
No log	9.0	135	0.9550
No log	10.0	150	0.9583
No log	11.0	165	0.9574
No log	12.0	180	0.9544
No log	13.0	195	0.9540
No log	14.0	210	0.9575
No log	15.0	225	0.9530
No log	16.0	240	0.9519
No log	17.0	255	0.9514
No log	18.0	270	0.9534
No log	19.0	285	0.9498
No log	20.0	300	0.9554
No log	21.0	315	0.9474
No log	22.0	330	0.9539
No log	23.0	345	0.9470
No log	24.0	360	0.9491
No log	25.0	375	0.9478
No log	26.0	390	0.9454
No log	27.0	405	0.9472
No log	28.0	420	0.9481
No log	29.0	435	0.9467
No log	30.0	450	0.9473
No log	31.0	465	0.9478
No log	32.0	480	0.9439
No log	33.0	495	0.9453
0.2954	34.0	510	0.9446
0.2954	35.0	525	0.9453
0.2954	36.0	540	0.9452
0.2954	37.0	555	0.9442
0.2954	38.0	570	0.9459
0.2954	39.0	585	0.9442
0.2954	40.0	600	0.9443
0.2954	41.0	615	0.9445
0.2954	42.0	630	0.9442
0.2954	43.0	645	0.9441
0.2954	44.0	660	0.9453
0.2954	45.0	675	0.9447
0.2954	46.0	690	0.9441
0.2954	47.0	705	0.9438
0.2954	48.0	720	0.9438
0.2954	49.0	735	0.9437
0.2954	50.0	750	0.9436

Framework versions

Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2

Downloads last month: 2

Safetensors

Model size

81.9M params

Tensor type

F32

Model tree for gjonesQ02/StatementOfWork_Generator_Omega2

Base model

distilbert/distilgpt2

Finetuned

(1456)

this model