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

Libraries

How to use ntkuhn/lean-parrot with Transformers:

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

pipe = pipeline("text-generation", model="ntkuhn/lean-parrot")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ntkuhn/lean-parrot")
model = AutoModelForCausalLM.from_pretrained("ntkuhn/lean-parrot")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ntkuhn/lean-parrot with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ntkuhn/lean-parrot

SGLang

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

Docker Model Runner
How to use ntkuhn/lean-parrot with Docker Model Runner:
```
docker model run hf.co/ntkuhn/lean-parrot
```

ntkuhn
/

lean-parrot

step 15000

+version https://git-lfs.github.com/spec/v1
+oid sha256:2ef8f77ced2ee993ab02d4f1d786a5856568a502cb394d6727686058bea72bc8
+size 1805

+version https://git-lfs.github.com/spec/v1
+oid sha256:20e0bdde07135d0276a2903b45808a2ad490d3ff918b8c1da0a35254262d8ebb
+size 1743

+version https://git-lfs.github.com/spec/v1
+oid sha256:04dd2067b884975da76e4c35443ccecbed22505f5652218c8353f6964e6f8906
+size 5099248

+version https://git-lfs.github.com/spec/v1
+oid sha256:2835ec0ea615d69cab2bc28d51b7bd470df4a04ac8b72e6324f4337c8ca40a7d
+size 623

+version https://git-lfs.github.com/spec/v1
+oid sha256:c84ed97ab943a46458137fe5c5bcf3d40590506d5c50e19f60c9047a19205f53
+size 939723977

+version https://git-lfs.github.com/spec/v1
+oid sha256:7bfa906866d71d88282974c3c53c91e5a1826b36cdf18c28f24d95cde552036e
+size 482446121

+version https://git-lfs.github.com/spec/v1
+oid sha256:abd87fe21071ae647be72194824880bb5a83db539e851c4a98529b1e4d57b293
+size 14567

+version https://git-lfs.github.com/spec/v1
+oid sha256:c4eb937eb503db8066497a7b27f6861444b66030da67b644a38525d9811fe6a5
+size 559

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@