Instructions to use theyur/dhamma-parrot-v01 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use theyur/dhamma-parrot-v01 with Transformers:

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

pipe = pipeline("text-generation", model="theyur/dhamma-parrot-v01")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("theyur/dhamma-parrot-v01")
model = AutoModelForCausalLM.from_pretrained("theyur/dhamma-parrot-v01", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use theyur/dhamma-parrot-v01 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 theyur/dhamma-parrot-v01
# Run inference directly in the terminal:
llama cli -hf theyur/dhamma-parrot-v01

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf theyur/dhamma-parrot-v01
# Run inference directly in the terminal:
llama cli -hf theyur/dhamma-parrot-v01

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 theyur/dhamma-parrot-v01
# Run inference directly in the terminal:
./llama-cli -hf theyur/dhamma-parrot-v01

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 theyur/dhamma-parrot-v01
# Run inference directly in the terminal:
./build/bin/llama-cli -hf theyur/dhamma-parrot-v01

Use Docker

docker model run hf.co/theyur/dhamma-parrot-v01

LM Studio
Jan

vLLM

How to use theyur/dhamma-parrot-v01 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "theyur/dhamma-parrot-v01"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "theyur/dhamma-parrot-v01",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/theyur/dhamma-parrot-v01

SGLang

How to use theyur/dhamma-parrot-v01 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 "theyur/dhamma-parrot-v01" \
    --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": "theyur/dhamma-parrot-v01",
		"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 "theyur/dhamma-parrot-v01" \
        --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": "theyur/dhamma-parrot-v01",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use theyur/dhamma-parrot-v01 with Ollama:
```
ollama run hf.co/theyur/dhamma-parrot-v01
```

Unsloth Studio

How to use theyur/dhamma-parrot-v01 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 theyur/dhamma-parrot-v01 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 theyur/dhamma-parrot-v01 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for theyur/dhamma-parrot-v01 to start chatting

Docker Model Runner
How to use theyur/dhamma-parrot-v01 with Docker Model Runner:
```
docker model run hf.co/theyur/dhamma-parrot-v01
```

Lemonade

How to use theyur/dhamma-parrot-v01 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull theyur/dhamma-parrot-v01

Run and chat with the model

lemonade run user.dhamma-parrot-v01-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

dhamma-parrot-v01 / Modelfile

theyur

Upload folder using huggingface_hub

0108adc verified 16 days ago

Raw

History Blame Contribute Delete

671 Bytes

	FROM ./dhamma-parrot-v01.gguf

	# dhamma-parrot-v01 -- run 20260706_134154_rope_bare_diac_fix_check_14000
	# Base completion model on a narrow Pali/meditation corpus. NOT a chat model:
	# use raw completion, a chat template injects tokens it has never seen.
	# Trained context is 360 tokens.
	PARAMETER num_ctx 360
	PARAMETER num_predict 200
	PARAMETER temperature 0.8

	# This tokenizer has no EOS token. No EOS was set, so generation runs until num_predict.
	# The tags are USER_DEFINED, so they render as text and these stop strings fire.
	PARAMETER stop "</topic:essay>"
	PARAMETER stop "</topic:recollection>"
	PARAMETER stop "</topic:qa>"
	PARAMETER stop "</a>"