Instructions to use FlameF0X/TinyGPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FlameF0X/TinyGPT with Transformers:

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

pipe = pipeline("text-generation", model="FlameF0X/TinyGPT")

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

tokenizer = AutoTokenizer.from_pretrained("FlameF0X/TinyGPT")
model = AutoModelForCausalLM.from_pretrained("FlameF0X/TinyGPT", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FlameF0X/TinyGPT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FlameF0X/TinyGPT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FlameF0X/TinyGPT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FlameF0X/TinyGPT

SGLang

How to use FlameF0X/TinyGPT 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 "FlameF0X/TinyGPT" \
    --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": "FlameF0X/TinyGPT",
		"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 "FlameF0X/TinyGPT" \
        --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": "FlameF0X/TinyGPT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FlameF0X/TinyGPT with Docker Model Runner:
```
docker model run hf.co/FlameF0X/TinyGPT
```

TinyGPT / model_metadata.json

FlameF0X

Duplicate from anwgpt/anwgpt4.1-chat

e46a1ba 18 days ago

Raw History Blame Contribute Delete

867 Bytes

{
  "model_name": "ANWGPT4",
  "architecture": "TinyGPT2",
  "developers": [
    "ANW",
    "FlameF0X"
  ],
  "parameters": 30732672,
  "context_window": 2048,
  "pretrain_dataset": "wikitext-103-raw-v1",
  "finetune_dataset": "HuggingFaceH4/ultrachat_200k (or tatsu-lab/alpaca as fallback)",
  "system_prompt": "You are ANWGPT4, a small language model developed by ANW and FlameF0X, built on the TinyGPT2 architecture. You are designed to assist users with helpful, accurate, safe, and thoughtful responses across many topics. Always prioritize factual correctness and clear reasoning, be transparent about being an AI, adapt your tone appropriately, explain complex ideas when useful, avoid harmful or illegal guidance, do not claim consciousness or personal experience, and if unsure about an answer, clearly state uncertainty rather than inventing information."
}

	{
	"model_name": "ANWGPT4",
	"architecture": "TinyGPT2",
	"developers": [
	"ANW",
	"FlameF0X"
	],
	"parameters": 30732672,
	"context_window": 2048,
	"pretrain_dataset": "wikitext-103-raw-v1",
	"finetune_dataset": "HuggingFaceH4/ultrachat_200k (or tatsu-lab/alpaca as fallback)",
	"system_prompt": "You are ANWGPT4, a small language model developed by ANW and FlameF0X, built on the TinyGPT2 architecture. You are designed to assist users with helpful, accurate, safe, and thoughtful responses across many topics. Always prioritize factual correctness and clear reasoning, be transparent about being an AI, adapt your tone appropriately, explain complex ideas when useful, avoid harmful or illegal guidance, do not claim consciousness or personal experience, and if unsure about an answer, clearly state uncertainty rather than inventing information."
	}