Instructions to use PatrickTyBrown/GPT-Neo_DnD_Control with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PatrickTyBrown/GPT-Neo_DnD_Control with Transformers:

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

pipe = pipeline("text-generation", model="PatrickTyBrown/GPT-Neo_DnD_Control")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PatrickTyBrown/GPT-Neo_DnD_Control")
model = AutoModelForCausalLM.from_pretrained("PatrickTyBrown/GPT-Neo_DnD_Control", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PatrickTyBrown/GPT-Neo_DnD_Control with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/PatrickTyBrown/GPT-Neo_DnD_Control

SGLang

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

Docker Model Runner
How to use PatrickTyBrown/GPT-Neo_DnD_Control with Docker Model Runner:
```
docker model run hf.co/PatrickTyBrown/GPT-Neo_DnD_Control
```

PatrickTyBrown commited on Sep 8, 2022

Commit

93953bf

1 Parent(s): a3f0fd7

update model card README.md

Browse files

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -13,12 +13,12 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [PatrickTyBrown/GPT-Neo_DnD](https://huggingface.co/PatrickTyBrown/GPT-Neo_DnD) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 2.6848
-- eval_runtime: 141.4633
-- eval_samples_per_second: 6.525
-- eval_steps_per_second: 3.266
-- epoch: 2.92
-- step: 27000
 ## Model description

 This model is a fine-tuned version of [PatrickTyBrown/GPT-Neo_DnD](https://huggingface.co/PatrickTyBrown/GPT-Neo_DnD) on the None dataset.
 It achieves the following results on the evaluation set:
+- eval_loss: 2.6518
+- eval_runtime: 141.422
+- eval_samples_per_second: 6.527
+- eval_steps_per_second: 3.267
+- epoch: 3.9
+- step: 36000
 ## Model description