Instructions to use roneneldan/TinyStories-Instruct-1M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use roneneldan/TinyStories-Instruct-1M with Transformers:

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

pipe = pipeline("text-generation", model="roneneldan/TinyStories-Instruct-1M")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("roneneldan/TinyStories-Instruct-1M")
model = AutoModelForCausalLM.from_pretrained("roneneldan/TinyStories-Instruct-1M")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use roneneldan/TinyStories-Instruct-1M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "roneneldan/TinyStories-Instruct-1M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "roneneldan/TinyStories-Instruct-1M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/roneneldan/TinyStories-Instruct-1M

SGLang

How to use roneneldan/TinyStories-Instruct-1M 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 "roneneldan/TinyStories-Instruct-1M" \
    --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": "roneneldan/TinyStories-Instruct-1M",
		"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 "roneneldan/TinyStories-Instruct-1M" \
        --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": "roneneldan/TinyStories-Instruct-1M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use roneneldan/TinyStories-Instruct-1M with Docker Model Runner:
```
docker model run hf.co/roneneldan/TinyStories-Instruct-1M
```

roneneldan commited on May 16, 2023

Commit

8cd464c

1 Parent(s): 5f6b961

Update readme.md

Browse files

Files changed (1) hide show

readme.md +4 -4

readme.md CHANGED Viewed

@@ -1,10 +1,10 @@
-This model was trained on the TinyStories dataset - https://arxiv.org/abs/2305.07759
-In order to use the model, put the files config.json and pytorch_model.pt in any folder, and then run the following code:
 from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
-model = AutoModelForCausalLM.from_pretrained('path to folder here') # REPLACE BY PATH
 tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neo-125M")
@@ -13,7 +13,7 @@ prompt = "Once upon a time there was"
 input_ids = tokenizer.encode(prompt, return_tensors="pt")
 # Generate completion
-output = model.generate(input_ids, max_length = 1000, num_beams=1, generation_config = generation_config)
 # Decode the completion
 output_text = tokenizer.decode(output[0], skip_special_tokens=True)

+Model trained on the TinyStories-Instruct Dataset, see https://arxiv.org/abs/2305.07759
+------ EXAMPLE USAGE ---
 from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
+model = AutoModelForCausalLM.from_pretrained('roneneldan/TinyStories-Instruct-1M')
 tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neo-125M")
 input_ids = tokenizer.encode(prompt, return_tensors="pt")
 # Generate completion
+output = model.generate(input_ids, max_length = 1000, num_beams=1)
 # Decode the completion
 output_text = tokenizer.decode(output[0], skip_special_tokens=True)