Instructions to use TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T with Transformers:

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

pipe = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T")
model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T

SGLang

How to use TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T 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 "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T" \
    --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": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
		"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 "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T" \
        --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": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T with Docker Model Runner:
```
docker model run hf.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
```

Phenomenon of saturation not reached?

by DrNicefellow - opened Feb 7, 2024

Discussion

DrNicefellow

Feb 7, 2024

As studying the phenomenon of saturation is one purpose of training TinyLlama, and the saturation seems not reached with the 3T tokens. Do you think it's reasonable to give it further training until saturation? If doing so, careful choices on learning rate could be important.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment