Instructions to use royallab/L3-Picaro-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use royallab/L3-Picaro-8B with Transformers:

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

pipe = pipeline("text-generation", model="royallab/L3-Picaro-8B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("royallab/L3-Picaro-8B")
model = AutoModelForMultimodalLM.from_pretrained("royallab/L3-Picaro-8B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use royallab/L3-Picaro-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "royallab/L3-Picaro-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "royallab/L3-Picaro-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/royallab/L3-Picaro-8B

SGLang

How to use royallab/L3-Picaro-8B 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 "royallab/L3-Picaro-8B" \
    --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": "royallab/L3-Picaro-8B",
		"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 "royallab/L3-Picaro-8B" \
        --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": "royallab/L3-Picaro-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use royallab/L3-Picaro-8B with Docker Model Runner:
```
docker model run hf.co/royallab/L3-Picaro-8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

L3-Picaro-8B

This is a Llama 3-based model consisting of a merge between:

meta-llama/Meta-Llama-3-8B (FP16 not available to the public yet. However, the merge config is.)
Trappu/Picaro-lora-l3 (with a fixed vocab size by merging on llama-2-13b)

This merge was performed with permission from the Lora creator (Trappu)

Mergekit config (Inspired from Charles Goddard):

merge_method: passthrough
models:
  - model: F:\AI\models\Meta-Llama-3-8B+F:\AI\loras\Picaro-lora-l3
dtype: float16

Usage

This model will follow the ChatML instruct format without the system prompt:

<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Bias, Risks, and Limitations

The model will show biases similar to those observed in niche roleplaying forums on the Internet, besides those exhibited by the base model. It is not intended for supplying factual information or advice in any form.

Training Details

This model is a merge. Please refer to the linked repositories of the merged models for details.

Donate?

All my infrastructure and cloud expenses are paid out of pocket. If you'd like to donate, you can do so here: https://ko-fi.com/kingbri

You should not feel obligated to donate, but if you do, I'd appreciate it.

Downloads last month: 3

Safetensors

Model size

8B params

Tensor type

F16

Model tree for royallab/L3-Picaro-8B

Quantizations

1 model