Instructions to use jploski/falcon-mini-shakespeare with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jploski/falcon-mini-shakespeare with Transformers:

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

pipe = pipeline("text-generation", model="jploski/falcon-mini-shakespeare", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("jploski/falcon-mini-shakespeare", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jploski/falcon-mini-shakespeare with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/jploski/falcon-mini-shakespeare

SGLang

How to use jploski/falcon-mini-shakespeare 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 "jploski/falcon-mini-shakespeare" \
    --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": "jploski/falcon-mini-shakespeare",
		"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 "jploski/falcon-mini-shakespeare" \
        --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": "jploski/falcon-mini-shakespeare",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jploski/falcon-mini-shakespeare with Docker Model Runner:
```
docker model run hf.co/jploski/falcon-mini-shakespeare
```

falcon-mini-shakespeare

This model was trained from scratch on "tinyshakespeare" text file.

Model description

The configuration and code is adapted from tiiuae/falcon-7b, with configuration parameters changed to make it a very tiny model.

License: Apache 2.0.

Intended uses & limitations

Intended just to aid debugging efforts of a GGML port of Falcon.

Training and evaluation data

https://raw.githubusercontent.com/karpathy/char-rnn/master/data/tinyshakespeare/input.txt

Training procedure

Just used the single tinyshakespeare text file as both the training and validation set (split up into paragraphs). See:

https://colab.research.google.com/drive/1utyxwRbOHCxUCqkIeei2JDAlKvAleRaF?usp=sharing

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0005
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 256
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
num_epochs: 10

Framework versions

Transformers 4.28.0
Pytorch 2.0.1+cu118
Datasets 2.12.0
Tokenizers 0.13.3

Downloads last month: 14