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

Libraries

How to use teapotai/teapotllm with Transformers:

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

pipe = pipeline("text-generation", model="teapotai/teapotllm")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("teapotai/teapotllm")
model = AutoModelForSeq2SeqLM.from_pretrained("teapotai/teapotllm")

Transformers.js

How to use teapotai/teapotllm with Transformers.js:

// npm i @huggingface/transformers
import { pipeline } from '@huggingface/transformers';

// Allocate pipeline
const pipe = await pipeline('text-generation', 'teapotai/teapotllm');

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use teapotai/teapotllm with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "teapotai/teapotllm"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "teapotai/teapotllm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/teapotai/teapotllm

SGLang

How to use teapotai/teapotllm 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/teapotllm" \
    --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": "teapotai/teapotllm",
		"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 "teapotai/teapotllm" \
        --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": "teapotai/teapotllm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

it run but

by rakmik - opened Mar 31, 2025

Discussion

rakmik

Mar 31, 2025

Imports

import fitz # PyMuPDF
from teapotai import TeapotAI

Load and extract text from PDF

pdf_path = '/content/Understanding_Climate_Change.pdf'
doc = fitz.open(pdf_path)
pdf_text = ""

Extract text from all pages

for page in doc:
pdf_text += page.get_text()

doc.close()

Initialize TeapotAI with PDF content as document

teapot_ai = TeapotAI(documents=[pdf_text])

Ask question about Fahd Mirza

query = "What is the topic of the book?"
answer = teapot_ai.query(query=query, context=pdf_text)

_____ _ _ ___ o ;;
| |_ __ _ _ __ ___ | |_ / \ |_ | __ /--_/ /
| |/ _ / ` | ' \ / _ | | / _ \ | | ( | |/
| | _/ (| | |) | () | |_ / ___ \ | | _|~~~~~~~|
||__|_,_| ./ _/ _/ // __| ____/
||
Loading Model: teapotai/teapotllm Revision: 699ab39cbf586674806354e92fbd6179f9a95f4a
Device set to use cpu
Device set to use cpu
Generating embeddings for documents...
Document Embedding: 100%|██████████| 1/1 [00:04<00:00, 4.37s/doc]
Token indices sequence length is longer than the specified maximum sequence length for this model (12644 > 512). Running this sequence through the model will result in indexing errors

rakmik

Apr 1, 2025

https://github.com/kim90000/teapotllm/blob/main/Xteapotllm.ipynb

zakerytclarke

Teapot AI org Apr 3, 2025

You need to use proper document chunking and rag settings to ensure you don't overfill context.

zakerytclarke changed discussion status to closed Apr 3, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment