Instructions to use davidx08/atithi-ai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use davidx08/atithi-ai with Transformers:

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

pipe = pipeline("text-generation", model="davidx08/atithi-ai")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("davidx08/atithi-ai")
model = AutoModelForCausalLM.from_pretrained("davidx08/atithi-ai", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use davidx08/atithi-ai with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf davidx08/atithi-ai
# Run inference directly in the terminal:
llama cli -hf davidx08/atithi-ai

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf davidx08/atithi-ai
# Run inference directly in the terminal:
llama cli -hf davidx08/atithi-ai

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf davidx08/atithi-ai
# Run inference directly in the terminal:
./llama-cli -hf davidx08/atithi-ai

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf davidx08/atithi-ai
# Run inference directly in the terminal:
./build/bin/llama-cli -hf davidx08/atithi-ai

Use Docker

docker model run hf.co/davidx08/atithi-ai

LM Studio
Jan

vLLM

How to use davidx08/atithi-ai with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "davidx08/atithi-ai"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "davidx08/atithi-ai",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/davidx08/atithi-ai

SGLang

How to use davidx08/atithi-ai 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 "davidx08/atithi-ai" \
    --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": "davidx08/atithi-ai",
		"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 "davidx08/atithi-ai" \
        --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": "davidx08/atithi-ai",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use davidx08/atithi-ai with Ollama:
```
ollama run hf.co/davidx08/atithi-ai
```

Unsloth Studio

How to use davidx08/atithi-ai with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for davidx08/atithi-ai to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for davidx08/atithi-ai to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for davidx08/atithi-ai to start chatting

Docker Model Runner
How to use davidx08/atithi-ai with Docker Model Runner:
```
docker model run hf.co/davidx08/atithi-ai
```

Lemonade

How to use davidx08/atithi-ai with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull davidx08/atithi-ai

Run and chat with the model

lemonade run user.atithi-ai-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

davidx08 commited on 23 days ago

Commit

2c351eb

verified ·

1 Parent(s): 9091d3b

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +46 -33

README.md CHANGED Viewed

@@ -2,49 +2,62 @@
 license: apache-2.0
 base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 tags:
-- travel
-- tourism
-- india
-- hotels
-- restaurants
-- weather
-- railways
-- flights
-- nexuzy-lab
-- gguf
-- lora
-- nexuzy
-- devil-one
 language:
-- en
 pipeline_tag: text-generation
 library_name: transformers
 ---
-# 🇮🇳 Atithi AI - India's Digital Travel Companion
 <p align="center">
   <img src="atitihi_logo.png" width="300" alt="Atithi AI Logo">
 </p>
-Atithi AI is an India-focused travel, hotel, restaurant, and local discovery assistant developed by **David** at **Nexuzy Lab** (Research division of **DEVIL ONE PVT LTD**).
-## 🚀 Project Overview
-Fine-tuned on 173,000+ records covering Indian tourism, 27,000+ restaurants, railways, flights, and bus routes. Designed for local planning and localized information.
-## 👤 Developer & Company Information
-- **Lead Developer:** David ([david@nexuzy.in](mailto:david@nexuzy.in))
-- **Organization:** Nexuzy Lab ([nexuzylab@gmail.com](mailto:nexuzylab@gmail.com))
-- **Parent Company:** DEVIL ONE PVT LTD ([https://devilone.in](https://devilone.in))
-- **Official Website:** [https://nexuzy.in/index.php](https://nexuzy.in/index.php)
-- **GitHub:** [https://github.com/david0154](https://github.com/david0154)
-## 📂 Model Variants
-- **Full Model:** Merged standalone weights for use with `transformers`.
-- **GGUF Version:** 8-bit quantized file (`atithi-ai-v1.gguf`) for mobile/edge/local deployment via llama.cpp.
-## 💡 Features
 - Knowledge of 27,000+ Indian restaurants.
-- Indian Railways, Flight schedules, and Bus route context.
-- Tourism destination discovery and budget hotel assistance.
-- Optimized for compact, fast inference.

 license: apache-2.0
 base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 tags:
+  - travel
+  - tourism
+  - india
+  - hotels
+  - restaurants
+  - weather
+  - maps
+  - geolocation
+  - railways
+  - flights
+  - bus-routes
+  - nexuzy-lab
+  - gguf
+  - lora
 language:
+  - en
+new_version: davidx08/atithi-ai
 pipeline_tag: text-generation
 library_name: transformers
 ---
+# Atithi AI
+Atithi AI is an India-focused travel, hotel, restaurant, and local discovery assistant built on `TinyLlama/TinyLlama-1.1B-Chat-v1.0` and developed by **David** at **Nexuzy Lab**, which is presented as a research and innovation division under **DEVIL ONE PVT LTD**.
 <p align="center">
   <img src="atitihi_logo.png" width="300" alt="Atithi AI Logo">
 </p>
+## Model scope
+Atithi AI is intended as a compact domain-tuned assistant for the Indian ecosystem, supporting:
+- Tourist destination discovery
+- Hotel and stay assistance
+- Restaurant and food place information
+- Railway, flight, and bus travel context
+- Weather-aware planning prompts
+- Maps, routes, and location-driven assistance
+- City-level and region-level travel recommendations
+- Edge and local deployment workflows through GGUF compatibility
+## Developer information
+- **Developer:** David
+- **Developer Email:** david@nexuzy.in
+- **Organization:** Nexuzy Lab
+- **Parent Company:** DEVIL ONE PVT LTD
+- **Website:** https://nexuzy.in/index.php
+## Features
+- Fine-tuned from a small, efficient base model for lightweight deployment.
 - Knowledge of 27,000+ Indian restaurants.
+- India-specific travel and hospitality orientation.
+- GGUF compatible for edge deployment.
+## Usage with Transformers
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+model = AutoModelForCausalLM.from_pretrained("davidx08/atithi-ai")
+tokenizer = AutoTokenizer.from_pretrained("davidx08/atithi-ai")
+```