Instructions to use KoboldAI/GPT-Neo-1.3B-Adventure with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KoboldAI/GPT-Neo-1.3B-Adventure with Transformers:

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

pipe = pipeline("text-generation", model="KoboldAI/GPT-Neo-1.3B-Adventure")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KoboldAI/GPT-Neo-1.3B-Adventure")
model = AutoModelForCausalLM.from_pretrained("KoboldAI/GPT-Neo-1.3B-Adventure")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use KoboldAI/GPT-Neo-1.3B-Adventure with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KoboldAI/GPT-Neo-1.3B-Adventure"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KoboldAI/GPT-Neo-1.3B-Adventure",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/KoboldAI/GPT-Neo-1.3B-Adventure

SGLang

How to use KoboldAI/GPT-Neo-1.3B-Adventure 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 "KoboldAI/GPT-Neo-1.3B-Adventure" \
    --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": "KoboldAI/GPT-Neo-1.3B-Adventure",
		"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 "KoboldAI/GPT-Neo-1.3B-Adventure" \
        --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": "KoboldAI/GPT-Neo-1.3B-Adventure",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use KoboldAI/GPT-Neo-1.3B-Adventure with Docker Model Runner:
```
docker model run hf.co/KoboldAI/GPT-Neo-1.3B-Adventure
```

GPT-Neo-1.3B-Adventure

Commit History

Adding `safetensors` variant of this model (#1)

93a083d

Henk717

SFconvertbot commited on Mar 20, 2023

Added welcome text

803261b

mrseeker87 commited on Mar 22, 2022

updated docker

60c62e3

Julius ter Pelkwijk commited on Mar 19, 2022

Editing again, hopefully with more effect

ba76d76

mrseeker87 commited on Mar 14, 2022

adding tag for huggingface

4f1be6a

mrseeker87 commited on Mar 14, 2022

Initial commit

37a0d2d

Julius ter Pelkwijk commited on Mar 14, 2022

Update README.md

dbb9291

mrseeker87 commited on Mar 14, 2022

initial commit

65897ff

mrseeker87 commited on Mar 14, 2022

Commit History

Adding `safetensors` variant of this model (#1) 93a083d

Added welcome text 803261b

updated docker 60c62e3

Editing again, hopefully with more effect ba76d76

adding tag for huggingface 4f1be6a

Initial commit 37a0d2d

Update README.md dbb9291

initial commit 65897ff

Adding `safetensors` variant of this model (#1)

93a083d

Added welcome text

803261b

updated docker

60c62e3

Editing again, hopefully with more effect

ba76d76

adding tag for huggingface

4f1be6a

Initial commit

37a0d2d

Update README.md

dbb9291

initial commit

65897ff