Instructions to use reeducator/bluemoonrp-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use reeducator/bluemoonrp-13b with Transformers:

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

pipe = pipeline("text-generation", model="reeducator/bluemoonrp-13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("reeducator/bluemoonrp-13b")
model = AutoModelForCausalLM.from_pretrained("reeducator/bluemoonrp-13b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use reeducator/bluemoonrp-13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "reeducator/bluemoonrp-13b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "reeducator/bluemoonrp-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/reeducator/bluemoonrp-13b

SGLang

How to use reeducator/bluemoonrp-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 "reeducator/bluemoonrp-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": "reeducator/bluemoonrp-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 "reeducator/bluemoonrp-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": "reeducator/bluemoonrp-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use reeducator/bluemoonrp-13b with Docker Model Runner:
```
docker model run hf.co/reeducator/bluemoonrp-13b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

General

Bluemoon roleplay finetune of LLaMA 13B (2 roleplayers only).

Models

Two models are provided, labeled (1) 4k-epoch6 and (2) epoch3 (other branch). In case of the (1), the training is extended over more epochs to reduce the high training loss observed in (2). This release also tests a longer 4k context token size achieved with AliBi.

GGML 4-bit for llama.cpp

ggml-bluemoonrp-13b-4k-epoch6-q5_0.bin
ggml-bluemoonrp-13b-epoch3-q5_0.bin

GPTQ 4-bit CUDA:

bluemoonrp-13b-4k-epoch6-4bit-128g.safetensors
bluemoonrp-13b-epoch3-4bit-128g.safetensors

Remarks

This model has been trained using the following prompt (Vicuna 1.1 format):

A transcript of a roleplay between two players, LEAD and ASSOCIATE. LEAD sets up a scenario and the characters, from which ASSOCIATE then assumes a character role and continues the story for that role in response to description given by LEAD. The story and characters are developed by exchange of detailed event descriptions and character dialogs, successively given by both LEAD and ASSOCIATE.
LEAD: [role1 message]
ASSOCIATE: [role2 message]</s>

Downloads last month: 210

Model tree for reeducator/bluemoonrp-13b

Quantizations

3 models