Instructions to use Trappu/Nemo-Picaro-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Trappu/Nemo-Picaro-12B with Transformers:

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

pipe = pipeline("text-generation", model="Trappu/Nemo-Picaro-12B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Trappu/Nemo-Picaro-12B")
model = AutoModelForCausalLM.from_pretrained("Trappu/Nemo-Picaro-12B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Trappu/Nemo-Picaro-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Trappu/Nemo-Picaro-12B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Trappu/Nemo-Picaro-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Trappu/Nemo-Picaro-12B

SGLang

How to use Trappu/Nemo-Picaro-12B 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 "Trappu/Nemo-Picaro-12B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Trappu/Nemo-Picaro-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Trappu/Nemo-Picaro-12B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Trappu/Nemo-Picaro-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use Trappu/Nemo-Picaro-12B 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 Trappu/Nemo-Picaro-12B 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 Trappu/Nemo-Picaro-12B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Trappu/Nemo-Picaro-12B to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Trappu/Nemo-Picaro-12B",
    max_seq_length=2048,
)

Docker Model Runner
How to use Trappu/Nemo-Picaro-12B with Docker Model Runner:
```
docker model run hf.co/Trappu/Nemo-Picaro-12B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Uploaded model

Developed by: Trappu
License: apache-2.0
Finetuned from model : royallab/MN-LooseCannon-12B-v2

Details

This model was trained on my own little dataset free of synthetic data, which focuses solely on storywriting and scenrio prompting (Example: [ Scenario: bla bla bla; Tags: bla bla bla ]),

I don't really recommend this model due to its nature and obvious flaws (rampant impersonation, stupid, etc...). It's a a one-trick pony and will be really rough for the average LLM user to handle.

Instead, I recommend you guys use Magnum-Picaro-0.7-v2-12b. The idea was to have Magnum work as some sort of stabilizer to fix the issues that emerge from the lack of multiturn/smart data in Picaro's dataset. It worked, I think. I enjoy the outputs and it's smart enough to work with.

Prompting

If for some reason, you still want to try this model over Magnum-Picaro, it was trained on chatml with no system prompts, so below is the recommended prompt formatting.

<|im_start|>user
bla bla bla<|im_end|>
<|im_start|>assistant
bla bla bla you!<|im_end|>

For SillyTavern users:

Instruct template

Context template

Settings preset

The above settings are the ones I recommend.

Temp = 1.2

Min P = 0.1

DRY Rep Pen: Multiplier = 0.8, Base = 1.75, Allowed Length = 2, Penalty Range = 1024

Little guide on useful samplers and how to import settings presets and instruct/context templates and other stuff people might find useful here

Every other sampler neutralized.

Downloads last month: 4

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for Trappu/Nemo-Picaro-12B

Base model

royallab/MN-LooseCannon-12B-v2

Finetuned

(4)

this model

Merges

23 models

Quantizations

2 models

Collection including Trappu/Nemo-Picaro-12B

Picaro fixed for real

Collection

4 items • Updated Sep 10, 2024 • 1