Instructions to use teapotai/teapot1alpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use teapotai/teapot1alpha with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="teapotai/teapot1alpha") 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("teapotai/teapot1alpha") model = AutoModelForCausalLM.from_pretrained("teapotai/teapot1alpha", 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 teapotai/teapot1alpha with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "teapotai/teapot1alpha" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "teapotai/teapot1alpha", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/teapotai/teapot1alpha
- SGLang
How to use teapotai/teapot1alpha 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 "teapotai/teapot1alpha" \ --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": "teapotai/teapot1alpha", "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 "teapotai/teapot1alpha" \ --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": "teapotai/teapot1alpha", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use teapotai/teapot1alpha with Docker Model Runner:
docker model run hf.co/teapotai/teapot1alpha
Download phase_stats.json from teapotai/teapot1alpha: direct link, hf CLI and curl.
- Browser
- Download file 1.21 kB
-
https://huggingface.co/teapotai/teapot1alpha/resolve/main/phase_stats.json
- Command line
-
hf download hf://teapotai/teapot1alpha/phase_stats.json
-
curl -L -o phase_stats.json https://huggingface.co/teapotai/teapot1alpha/resolve/main/phase_stats.json
1.21 kB
| { | |
| "pretrain": { | |
| "first_loss": 10.997010231018066, | |
| "last_loss": 2.365316390991211, | |
| "tokens": 40000004096, | |
| "tokens_per_source": { | |
| "dclm-edu/train": 21200001024, | |
| "fineweb-edu/train": 14000001024, | |
| "stack-edu-HF/train": 2400000000, | |
| "finemath/infiwebmath-4plus/train": 800000000, | |
| "finemath/finemath-4plus/train": 700000256, | |
| "smollm-corpus/cosmopedia-v2/train": 900001792 | |
| }, | |
| "tok_per_sec": 70463.29019271227 | |
| }, | |
| "sft": { | |
| "first_loss": 3.732140064239502, | |
| "last_loss": 0.010234128683805466, | |
| "tokens": 147299012, | |
| "tokens_per_source": { | |
| "fineweb-edu/train": 12001280, | |
| "squad_v2/train": 4000097, | |
| "synthqa/train": 3292997, | |
| "hotpot_qa/distractor/train": 6001037, | |
| "smoltalk/apigen-80k/train": 6000009, | |
| "When2Call/train_sft/train": 6000033, | |
| "teapot-chat/train": 8000135, | |
| "smoltalk/everyday-conversations/train": 8000033, | |
| "smoltalk/smol-constraints/train": 6000177, | |
| "smoltalk/smol-rewrite/train": 4000072, | |
| "smoltalk/smol-summarize/train": 4000330, | |
| "smoltalk/smol-magpie-ultra/train": 2000695, | |
| "gsm8k/main/train": 4000302 | |
| }, | |
| "tok_per_sec": 23070.48189301041 | |
| } | |
| } |