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 / autocomplete.ts

tmickleydoyle

Compiled (not trained) 91M-param Llama autocomplete model, TypeScript runtime and UI, docs

ab4f92b verified 1 day ago

Raw History Blame Contribute Delete

1.47 kB

// Command-line autocomplete tester (zero dependencies).
//
//   bun autocomplete.ts                     interactive prompt
//   bun autocomplete.ts "once upon a"       complete one or more prompts
//   bun autocomplete.ts --json "how are"    machine-readable output (used by tests)
//
// Also runs on Node >= 23.6 (`node autocomplete.ts`). For a browser UI see ui.ts.

import { createInterface } from "node:readline";
import { Autocompleter } from "./model.ts";

const DIR = import.meta.dirname ?? new URL(".", import.meta.url).pathname;
const ac = new Autocompleter(DIR);

function show(prompt: string): void {
  const t0 = performance.now();
  const r = ac.complete(prompt);
  const ms = Math.round(performance.now() - t0);
  console.log(`${prompt}\x1b[36m${r.completion}\x1b[0m   (${ms} ms)`);
  console.log("  next: " + r.top.map((t) => `${JSON.stringify(t.token)} ${(Math.exp(t.logprob) * 100).toFixed(1)}%`).join("  "));
}

const args = process.argv.slice(2);
if (args[0] === "--json") {
  console.log(JSON.stringify(args.slice(1).map((p) => ac.complete(p))));
} else if (args.length) {
  args.forEach(show);
} else {
  const cfg = ac.model.cfg;
  console.log(`Loaded ${cfg.num_hidden_layers}-layer model, vocab ${cfg.vocab_size}. Type a prefix (Ctrl+D to quit).`);
  const rl = createInterface({ input: process.stdin, output: process.stdout, prompt: "> " });
  rl.prompt();
  rl.on("line", (line) => {
    if (line.trim()) show(line);
    rl.prompt();
  });
}

	// Command-line autocomplete tester (zero dependencies).
	//
	// bun autocomplete.ts interactive prompt
	// bun autocomplete.ts "once upon a" complete one or more prompts
	// bun autocomplete.ts --json "how are" machine-readable output (used by tests)
	//
	// Also runs on Node >= 23.6 (`node autocomplete.ts`). For a browser UI see ui.ts.

	import { createInterface } from "node:readline";
	import { Autocompleter } from "./model.ts";

	const DIR = import.meta.dirname ?? new URL(".", import.meta.url).pathname;
	const ac = new Autocompleter(DIR);

	function show(prompt: string): void {
	const t0 = performance.now();
	const r = ac.complete(prompt);
	const ms = Math.round(performance.now() - t0);
	console.log(`${prompt}\x1b[36m${r.completion}\x1b[0m (${ms} ms)`);
	console.log(" next: " + r.top.map((t) => `${JSON.stringify(t.token)} ${(Math.exp(t.logprob) * 100).toFixed(1)}%`).join(" "));
	}

	const args = process.argv.slice(2);
	if (args[0] === "--json") {
	console.log(JSON.stringify(args.slice(1).map((p) => ac.complete(p))));
	} else if (args.length) {
	args.forEach(show);
	} else {
	const cfg = ac.model.cfg;
	console.log(`Loaded ${cfg.num_hidden_layers}-layer model, vocab ${cfg.vocab_size}. Type a prefix (Ctrl+D to quit).`);
	const rl = createInterface({ input: process.stdin, output: process.stdout, prompt: "> " });
	rl.prompt();
	rl.on("line", (line) => {
	if (line.trim()) show(line);
	rl.prompt();
	});
	}