Instructions to use adamroberts/tinystories-5090 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adamroberts/tinystories-5090 with Transformers:

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

pipe = pipeline("text-generation", model="adamroberts/tinystories-5090")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("adamroberts/tinystories-5090")
model = AutoModelForCausalLM.from_pretrained("adamroberts/tinystories-5090", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use adamroberts/tinystories-5090 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "adamroberts/tinystories-5090"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adamroberts/tinystories-5090",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/adamroberts/tinystories-5090

SGLang

How to use adamroberts/tinystories-5090 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 "adamroberts/tinystories-5090" \
    --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": "adamroberts/tinystories-5090",
		"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 "adamroberts/tinystories-5090" \
        --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": "adamroberts/tinystories-5090",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use adamroberts/tinystories-5090 with Docker Model Runner:
```
docker model run hf.co/adamroberts/tinystories-5090
```

adamroberts commited on May 23

Commit

acb894c

verified ·

1 Parent(s): d2c028b

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -2

README.md CHANGED Viewed

@@ -9,7 +9,6 @@ tags:
 - gpt2
 - tinystories
 - llm-kittens
-- thunderkittens
 - bf16
 - cuda
 datasets:
@@ -123,4 +122,4 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 Source implementation: `https://github.com/adamdroberts/llm.kittens`
-TinyStories reference paper: `https://arxiv.org/abs/2305.07759`

 - gpt2
 - tinystories
 - llm-kittens
 - bf16
 - cuda
 datasets:
 Source implementation: `https://github.com/adamdroberts/llm.kittens`
+TinyStories reference paper: `https://arxiv.org/abs/2305.07759`