Instructions to use Undi95/ReMM-v1-LRPSGPT-2Char-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Undi95/ReMM-v1-LRPSGPT-2Char-13B with Transformers:

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

pipe = pipeline("text-generation", model="Undi95/ReMM-v1-LRPSGPT-2Char-13B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Undi95/ReMM-v1-LRPSGPT-2Char-13B")
model = AutoModelForCausalLM.from_pretrained("Undi95/ReMM-v1-LRPSGPT-2Char-13B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Undi95/ReMM-v1-LRPSGPT-2Char-13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Undi95/ReMM-v1-LRPSGPT-2Char-13B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Undi95/ReMM-v1-LRPSGPT-2Char-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Undi95/ReMM-v1-LRPSGPT-2Char-13B

SGLang

How to use Undi95/ReMM-v1-LRPSGPT-2Char-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 "Undi95/ReMM-v1-LRPSGPT-2Char-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": "Undi95/ReMM-v1-LRPSGPT-2Char-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 "Undi95/ReMM-v1-LRPSGPT-2Char-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": "Undi95/ReMM-v1-LRPSGPT-2Char-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Undi95/ReMM-v1-LRPSGPT-2Char-13B with Docker Model Runner:
```
docker model run hf.co/Undi95/ReMM-v1-LRPSGPT-2Char-13B
```

This model is based on ReMM v1 merged with the ShareGPT-13b-qloras for "2 characters".

Description

This repo contains fp16 files of ReMM-v1-LRPSGPT-2Char-13B, and is made to be used with character card containing "TWO PERSONAS".

LoRA used

https://huggingface.co/royallab/LimaRP-ShareGPT-13b-qloras/tree/main/prompt-a/twochar

Prompt template: Custom

Enter roleplay mode. You are currently %{having a conversation|in conversation|in a roleplay chat} with <SECOND>, whose %{traits are|persona is|characteristics are}:
<SECOND PERSONA>
%{You are|Play the role of|Take the role of} <FIRST> with the following %{persona|definitions|character sheet|traits}:
<FIRST PERSONA>
%{In addition|Additionally|Also}, %{keep the following scenario in mind|remember this scenario|pay attention to this scenario}:
<SCENARIO>

Or try to use Chat without instruction.

More info: https://huggingface.co/royallab/LimaRP-ShareGPT-13b-qloras/blob/main/prompt-a/README.md

Special thanks to Sushi ♥

Downloads last month: 7

Collection including Undi95/ReMM-v1-LRPSGPT-2Char-13B

Honorable mentions

Collection

Some models I've made and I liked but isn't part of a serie. • 10 items • Updated Feb 4, 2024 • 6