Instructions to use tmickleydoyle/ghost-typer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tmickleydoyle/ghost-typer with Transformers:

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

pipe = pipeline("text-generation", model="tmickleydoyle/ghost-typer")

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

tokenizer = AutoTokenizer.from_pretrained("tmickleydoyle/ghost-typer")
model = AutoModelForCausalLM.from_pretrained("tmickleydoyle/ghost-typer", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tmickleydoyle/ghost-typer with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/tmickleydoyle/ghost-typer

SGLang

How to use tmickleydoyle/ghost-typer 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 "tmickleydoyle/ghost-typer" \
    --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": "tmickleydoyle/ghost-typer",
		"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 "tmickleydoyle/ghost-typer" \
        --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": "tmickleydoyle/ghost-typer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tmickleydoyle/ghost-typer with Docker Model Runner:
```
docker model run hf.co/tmickleydoyle/ghost-typer
```

ghost-typer

File size: 998 Bytes

c160abb
3c53a76
c160abb
 
3c53a76
c160abb
 
 
 
 
 
 
 
 
 
 
 
3c53a76
c160abb
 
 
 
 
 
 
 
 
3c53a76
c160abb
3c53a76
 
c160abb

{
  "_comment": "Chosen by scripts/sweep.py (docs/sweep.json): best keystrokes saved at >= 90% precision on held-out prompts (OASST/MBPP/CoNaLa + WildChat); smoothing and policy.ext from the lookback/look-ahead experiments (docs/experiments_lookback.json). hf = dense transformers model (vocab capped for width); web = sparse browser export.",
  "hf": {
    "n_prev": 3,
    "smoothing": "mkn",
    "phrase_weight": 1.0,
    "prompt_weight": 1.0,
    "reply_weight": 1.0,
    "wildchat_weight": 1.0,
    "max_vocab": 6000,
    "min_word_count": 2,
    "min_count": null,
    "force_phrases": false,
    "param_target": 400000000
  },
  "web": {
    "n_prev": 3,
    "smoothing": "mkn",
    "phrase_weight": 1.0,
    "prompt_weight": 1.0,
    "reply_weight": 1.0,
    "wildchat_weight": 1.0,
    "max_vocab": 1000000,
    "min_word_count": 2,
    "min_count": 2
  },
  "policy": {
    "tau": 0.62,
    "min_support": 0,
    "max_words": 8,
    "ext": 0.8
  },
  "export": {
    "deltas": "u8"
  }
}