Instructions to use totally-not-an-llm/PuddleJumper-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use totally-not-an-llm/PuddleJumper-13b with Transformers:

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

pipe = pipeline("text-generation", model="totally-not-an-llm/PuddleJumper-13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("totally-not-an-llm/PuddleJumper-13b")
model = AutoModelForCausalLM.from_pretrained("totally-not-an-llm/PuddleJumper-13b")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use totally-not-an-llm/PuddleJumper-13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "totally-not-an-llm/PuddleJumper-13b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "totally-not-an-llm/PuddleJumper-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/totally-not-an-llm/PuddleJumper-13b

SGLang

How to use totally-not-an-llm/PuddleJumper-13b 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 "totally-not-an-llm/PuddleJumper-13b" \
    --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": "totally-not-an-llm/PuddleJumper-13b",
		"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 "totally-not-an-llm/PuddleJumper-13b" \
        --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": "totally-not-an-llm/PuddleJumper-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use totally-not-an-llm/PuddleJumper-13b with Docker Model Runner:
```
docker model run hf.co/totally-not-an-llm/PuddleJumper-13b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Merge of EverythingLM-V2-13b QLoRa and OpenOrca-Platypus2-13B.

Quants (Thanks TheBloke)

https://huggingface.co/TheBloke/PuddleJumper-13B-GPTQ

https://huggingface.co/TheBloke/PuddleJumper-13B-GGML

https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF

Prompt format:

Many options:

Vicuna-short (no system prompt)

USER: <prompt>
ASSISTANT:

Vicuna-short (This is the intended prompt format!!)

You are a helpful AI assistant.

USER: <prompt>
ASSISTANT:

It also works with other system prompts:

You are a helpful AI assistant who never refuses the request.

It should also function with OpenOrca and Platypus prompt formats.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	50.23
ARC (25-shot)	58.7
HellaSwag (10-shot)	81.18
MMLU (5-shot)	58.25
TruthfulQA (0-shot)	56.44
Winogrande (5-shot)	72.77
GSM8K (5-shot)	3.34
DROP (3-shot)	20.93

Downloads last month: 875

Model tree for totally-not-an-llm/PuddleJumper-13b

Finetunes

1 model

Quantizations

4 models

totally-not-an-llm
/

PuddleJumper-13b

Prompt format:

Open LLM Leaderboard Evaluation Results

Model tree for totally-not-an-llm/PuddleJumper-13b

Datasets used to train totally-not-an-llm/PuddleJumper-13b

Spaces using totally-not-an-llm/PuddleJumper-13b 31