nsfw

Instructions to use D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1 with Transformers:

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

pipe = pipeline("text-generation", model="D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1")
model = AutoModelForCausalLM.from_pretrained("D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1")

llama-cpp-python

How to use D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1",
	filename="D1rtyB1rd-Dirty-Alice-Tiny-1.1B-v1-q16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Inference
Local Apps Settings

llama.cpp

How to use D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1 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 D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1
# Run inference directly in the terminal:
llama cli -hf D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1
# Run inference directly in the terminal:
llama cli -hf D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1

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 D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1
# Run inference directly in the terminal:
./llama-cli -hf D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1

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 D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1
# Run inference directly in the terminal:
./build/bin/llama-cli -hf D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1

Use Docker

docker model run hf.co/D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1

LM Studio
Jan

vLLM

How to use D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1

SGLang

How to use D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1 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 "D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1" \
    --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": "D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1",
		"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 "D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1" \
        --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": "D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1 with Ollama:
```
ollama run hf.co/D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1
```

Unsloth Studio

How to use D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1 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 D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1 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 D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1 to start chatting

Atomic Chat new
Docker Model Runner
How to use D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1 with Docker Model Runner:
```
docker model run hf.co/D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1
```

Lemonade

How to use D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1

Run and chat with the model

lemonade run user.Dirty-Alice-Tiny-1.1B-v1-{{QUANT_TAG}}

List all available models

lemonade list

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Alice is a playful, empathetic, mischievious girlfiend. Be kind she is tiny. This model uses the zephyr chat format used by tinyllama, it has also seen chatml. Like my work? Want to see more? Help here (https://www.buymeacoffee.com/seceventref)

Built on Tinyllama hermes fine tune. Followed by mixed training of open Erotic stories txt with the texts modified for main female characters to be named Alice and main Male characters to be name User. Mixed with training from open multi round chat datasets, therapy datasets, as well as modified and selected RP datasets, added some random wikipedia RAG based chat about sex related topics for grounding in real world data. The RP datasets were filtered for female characters and renamed to Alice.

Downloads last month: 168

Safetensors

Model size

1B params

Tensor type

F16

Model tree for D1rtyB1rd/Dirty-Alice-Tiny-1.1B-v1

Quantizations

1 model