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 / web /cli.ts

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

Raw History Blame Contribute Delete

1.92 kB

// Run the browser runtime from the command line (Bun or Node >= 23.6):
//   bun web/cli.ts "write a python fun" "how do i "
//   bun web/cli.ts --json ...                 full suggestion chains (used by test_model.py)
//   bun web/cli.ts --dist ...                 top-5 next-token log-probs after each text
//   bun web/cli.ts --model path/to/model.bin  use another export (default web/model.bin)

import { readFileSync } from "node:fs";
import { join } from "node:path";
import { preTokenize } from "../tokenizer.ts";
import { CompiledAutocomplete } from "./autocomplete.ts";

const dir = import.meta.dirname ?? new URL(".", import.meta.url).pathname;
let args = process.argv.slice(2);
let modelPath = join(dir, "model.bin");
const mi = args.indexOf("--model");
if (mi >= 0) {
  modelPath = args[mi + 1];
  args = [...args.slice(0, mi), ...args.slice(mi + 2)];
}
const mode = args[0] === "--json" || args[0] === "--dist" ? args.shift() : "";

const buf = readFileSync(modelPath);
const ac = new CompiledAutocomplete(buf.buffer.slice(buf.byteOffset, buf.byteOffset + buf.byteLength));

if (mode === "--dist") {
  const out = args.map((t) => {
    const ids = [ac.eosId, ...preTokenize(t).map((p) => ac.vocab.indexOf(p)).map((i) => (i < 0 ? ac.unkId : i))];
    const { probs } = ac.dist(ids);
    const top = [...probs.keys()].sort((a, b) => probs[b] - probs[a]).slice(0, 5);
    return { text: t, top: top.map((i) => [i, Math.log(probs[i])]) };
  });
  console.log(JSON.stringify(out));
} else {
  const results = args.map((t) => {
    const start = performance.now();
    const s = ac.suggest(t);
    return { text: t, ...s, ms: performance.now() - start };
  });
  if (mode === "--json") console.log(JSON.stringify(results));
  else for (const r of results) console.log(`${r.text}\x1b[90m${r.ghost}\x1b[0m   ${r.ghost ? Math.round(r.prob * 100) + "%" : "(no confident suggestion)"}  ${r.ms.toFixed(2)} ms`);
}

	// Run the browser runtime from the command line (Bun or Node >= 23.6):
	// bun web/cli.ts "write a python fun" "how do i "
	// bun web/cli.ts --json ... full suggestion chains (used by test_model.py)
	// bun web/cli.ts --dist ... top-5 next-token log-probs after each text
	// bun web/cli.ts --model path/to/model.bin use another export (default web/model.bin)

	import { readFileSync } from "node:fs";
	import { join } from "node:path";
	import { preTokenize } from "../tokenizer.ts";
	import { CompiledAutocomplete } from "./autocomplete.ts";

	const dir = import.meta.dirname ?? new URL(".", import.meta.url).pathname;
	let args = process.argv.slice(2);
	let modelPath = join(dir, "model.bin");
	const mi = args.indexOf("--model");
	if (mi >= 0) {
	modelPath = args[mi + 1];
	args = [...args.slice(0, mi), ...args.slice(mi + 2)];
	}
	const mode = args[0] === "--json" \|\| args[0] === "--dist" ? args.shift() : "";

	const buf = readFileSync(modelPath);
	const ac = new CompiledAutocomplete(buf.buffer.slice(buf.byteOffset, buf.byteOffset + buf.byteLength));

	if (mode === "--dist") {
	const out = args.map((t) => {
	const ids = [ac.eosId, ...preTokenize(t).map((p) => ac.vocab.indexOf(p)).map((i) => (i < 0 ? ac.unkId : i))];
	const { probs } = ac.dist(ids);
	const top = [...probs.keys()].sort((a, b) => probs[b] - probs[a]).slice(0, 5);
	return { text: t, top: top.map((i) => [i, Math.log(probs[i])]) };
	});
	console.log(JSON.stringify(out));
	} else {
	const results = args.map((t) => {
	const start = performance.now();
	const s = ac.suggest(t);
	return { text: t, ...s, ms: performance.now() - start };
	});
	if (mode === "--json") console.log(JSON.stringify(results));
	else for (const r of results) console.log(`${r.text}\x1b[90m${r.ghost}\x1b[0m ${r.ghost ? Math.round(r.prob * 100) + "%" : "(no confident suggestion)"} ${r.ms.toFixed(2)} ms`);
	}