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

Libraries

How to use tmickleydoyle/tiny-autocomplete with Transformers:

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

pipe = pipeline("text-generation", model="tmickleydoyle/tiny-autocomplete")

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tmickleydoyle/tiny-autocomplete with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/tmickleydoyle/tiny-autocomplete

SGLang

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

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

tiny-autocomplete / data /SOURCES.md

tmickleydoyle

Confidence-gated ghost text for coding prompts: Kneser-Ney compile, 4.5 MB browser export + zero-dep runtime, held-out precision/keystrokes-saved benchmarks

4113449 verified about 11 hours ago

preview code

Raw History Blame Contribute Delete

2.08 kB

# Data sources

`prompts.txt` and `replies.txt` are produced by `scripts/fetch_coding_prompts.py`. Every line is
human-written English prose taken from the datasets below. LLM-generated messages are excluded
(OASST `synthetic` flag). The script keeps only prose: it removes code blocks, code-looking
lines and markdown, keeps up to 2 sentences per prompt and 5 per reply, and keeps sentences
of 3–24 words.

| File | Dataset | What is used | License | Attribution |
|---|---|---|---|---|
| `prompts.txt` | [OpenAssistant/oasst2](https://huggingface.co/datasets/OpenAssistant/oasst2) | English **user** messages (all turns, reviewed, not deleted, not synthetic) from conversations whose opening prompt is about code | Apache-2.0 | Köpf et al., *OpenAssistant Conversations: Democratizing Large Language Model Alignment*, 2023 |
| `prompts.txt` | [google-research-datasets/mbpp](https://huggingface.co/datasets/google-research-datasets/mbpp) | task descriptions (`text`), all splits | CC-BY-4.0 | Austin et al., *Program Synthesis with Large Language Models*, 2021 |
| `prompts.txt` | [neulab/conala](https://huggingface.co/datasets/neulab/conala) | curated intents (`intent`), paired train + test | MIT | Yin et al., *Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow*, MSR 2018 |
| `replies.txt` | [OpenAssistant/oasst2](https://huggingface.co/datasets/OpenAssistant/oasst2) | English **assistant** messages, written by human volunteers, from the same conversations | Apache-2.0 | as above |

Counts from the last fetch:

| Source | Sentences |
|---|---|
| OASST user turns | 4,169 |
| MBPP | 938 |
| CoNaLa | 2,820 |
| OASST assistant turns | 13,183 |

After removing duplicates: **7,133** lines in `prompts.txt` and **12,841** in `replies.txt`.

The weights contain only n-gram statistics derived from these lines, plus the hand-written
phrases in `../phrases/`. No dataset was used to train anything. 10% of `prompts.txt` (chosen
by content hash) is held out when measuring precision and keystrokes saved
(`scripts/sweep.py`, `scripts/benchmark.py`).

	# Data sources

	`prompts.txt` and `replies.txt` are produced by `scripts/fetch_coding_prompts.py`. Every line is
	human-written English prose taken from the datasets below. LLM-generated messages are excluded
	(OASST `synthetic` flag). The script keeps only prose: it removes code blocks, code-looking
	lines and markdown, keeps up to 2 sentences per prompt and 5 per reply, and keeps sentences
	of 3–24 words.

	\| File \| Dataset \| What is used \| License \| Attribution \|
	\|---\|---\|---\|---\|---\|
	\| `prompts.txt` \| [OpenAssistant/oasst2](https://huggingface.co/datasets/OpenAssistant/oasst2) \| English user messages (all turns, reviewed, not deleted, not synthetic) from conversations whose opening prompt is about code \| Apache-2.0 \| Köpf et al., OpenAssistant Conversations: Democratizing Large Language Model Alignment, 2023 \|
	\| `prompts.txt` \| [google-research-datasets/mbpp](https://huggingface.co/datasets/google-research-datasets/mbpp) \| task descriptions (`text`), all splits \| CC-BY-4.0 \| Austin et al., Program Synthesis with Large Language Models, 2021 \|
	\| `prompts.txt` \| [neulab/conala](https://huggingface.co/datasets/neulab/conala) \| curated intents (`intent`), paired train + test \| MIT \| Yin et al., Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow, MSR 2018 \|
	\| `replies.txt` \| [OpenAssistant/oasst2](https://huggingface.co/datasets/OpenAssistant/oasst2) \| English assistant messages, written by human volunteers, from the same conversations \| Apache-2.0 \| as above \|

	Counts from the last fetch:

	\| Source \| Sentences \|
	\|---\|---\|
	\| OASST user turns \| 4,169 \|
	\| MBPP \| 938 \|
	\| CoNaLa \| 2,820 \|
	\| OASST assistant turns \| 13,183 \|

	After removing duplicates: 7,133 lines in `prompts.txt` and 12,841 in `replies.txt`.

	The weights contain only n-gram statistics derived from these lines, plus the hand-written
	phrases in `../phrases/`. No dataset was used to train anything. 10% of `prompts.txt` (chosen
	by content hash) is held out when measuring precision and keystrokes saved
	(`scripts/sweep.py`, `scripts/benchmark.py`).