Instructions to use MarsupialAI/SkunkApe-16b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MarsupialAI/SkunkApe-16b with Transformers:

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

pipe = pipeline("text-generation", model="MarsupialAI/SkunkApe-16b")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MarsupialAI/SkunkApe-16b")
model = AutoModelForCausalLM.from_pretrained("MarsupialAI/SkunkApe-16b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MarsupialAI/SkunkApe-16b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MarsupialAI/SkunkApe-16b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MarsupialAI/SkunkApe-16b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MarsupialAI/SkunkApe-16b

SGLang

How to use MarsupialAI/SkunkApe-16b 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 "MarsupialAI/SkunkApe-16b" \
    --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": "MarsupialAI/SkunkApe-16b",
		"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 "MarsupialAI/SkunkApe-16b" \
        --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": "MarsupialAI/SkunkApe-16b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MarsupialAI/SkunkApe-16b with Docker Model Runner:
```
docker model run hf.co/MarsupialAI/SkunkApe-16b
```

MarsupialAI commited on Mar 23, 2024

Commit

bddfbbe

verified ·

1 Parent(s): 415b5dd

Create README.md

Browse files

Files changed (1) hide show

README.md +35 -0

README.md ADDED Viewed

	@@ -0,0 +1,35 @@

+---
+license: other
+license_name: yi-other
+---
+# Skunk Ape 34b 200k
+This model is a dare-ties merge of three Yi 34b 200k finetunes with the latest updated (v20240321) version of Yi 34b 200k as the base model.
+The exact merge recipe is included in the dareties.yml file.
+Mergefuel:
+  - adamo1139/Yi-34b-200K-AEZAKMI-RAW-TOXIC-2702
+  - jondurbin/airoboros-34b-3.2
+  - abacusai/Smaug-34B-v0.1
+This model is uncensored and capable of generating objectionable material. However, it is not an explicitely-NSFW model,
+and it has never "gone rogue" and tried to insert NSFW content into SFW prompts in my experience. As with any LLM, no
+factual claims made by the model should be taken at face value. You know that boilerplate safety disclaimer that most
+professional models have?  Assume this has it too. This model is for entertainment purposes only.
+iMatrix GGUFs:
+# Sample output
+```
+{{[INPUT]}}
+Write a detailed and humorous story about a cute and fluffy bunny that goes to a Gwar concert.
+{{[OUTPUT]}}
+```
+# Prompt format
+Seems to work with both Alpaca and chatml prompts.