Instructions to use DedeProGames/GPT-U-20M-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DedeProGames/GPT-U-20M-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="DedeProGames/GPT-U-20M-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

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

tokenizer = AutoTokenizer.from_pretrained("DedeProGames/GPT-U-20M-Instruct")
model = AutoModelForCausalLM.from_pretrained("DedeProGames/GPT-U-20M-Instruct", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DedeProGames/GPT-U-20M-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DedeProGames/GPT-U-20M-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DedeProGames/GPT-U-20M-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DedeProGames/GPT-U-20M-Instruct

SGLang

How to use DedeProGames/GPT-U-20M-Instruct 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 "DedeProGames/GPT-U-20M-Instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DedeProGames/GPT-U-20M-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "DedeProGames/GPT-U-20M-Instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DedeProGames/GPT-U-20M-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DedeProGames/GPT-U-20M-Instruct with Docker Model Runner:
```
docker model run hf.co/DedeProGames/GPT-U-20M-Instruct
```

GPT-U-20M-Instruct / tokenizer_config.json

DedeProGames

Add GPT-U-20M-Instruct: SFT on smol-smoltalk, Kiyo-protocol evals

a4b0e23 verified 8 days ago

Raw History Blame Contribute Delete

708 Bytes

{
  "backend": "tokenizers",
  "bos_token": "<|endoftext|>",
  "eos_token": "<|endoftext|>",
  "pad_token": "<|endoftext|>",
  "unk_token": null,
  "model_max_length": 1024,
  "tokenizer_class": "PreTrainedTokenizerFast",
  "chat_template": "{{- '<|endoftext|>' -}}{%- for message in messages -%}{%- if message['role'] == 'system' -%}{{ '### System:\n' + message['content'].strip() + '\n' }}{%- elif message['role'] == 'user' -%}{{ '### User:\n' + message['content'].strip() + '\n' }}{%- elif message['role'] == 'assistant' -%}{{ '### Assistant:\n' + message['content'].strip() + '\n<|endoftext|>' }}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{ '### Assistant:\n' }}{%- endif -%}"
}

	{
	"backend": "tokenizers",
	"bos_token": "<\|endoftext\|>",
	"eos_token": "<\|endoftext\|>",
	"pad_token": "<\|endoftext\|>",
	"unk_token": null,
	"model_max_length": 1024,
	"tokenizer_class": "PreTrainedTokenizerFast",
	"chat_template": "{{- '<\|endoftext\|>' -}}{%- for message in messages -%}{%- if message['role'] == 'system' -%}{{ '### System:\n' + message['content'].strip() + '\n' }}{%- elif message['role'] == 'user' -%}{{ '### User:\n' + message['content'].strip() + '\n' }}{%- elif message['role'] == 'assistant' -%}{{ '### Assistant:\n' + message['content'].strip() + '\n<\|endoftext\|>' }}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{ '### Assistant:\n' }}{%- endif -%}"
	}