Instructions to use teknium/Base-GPT4-x-Alpaca-Roleplay-Lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use teknium/Base-GPT4-x-Alpaca-Roleplay-Lora with Transformers:

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

pipe = pipeline("text-generation", model="teknium/Base-GPT4-x-Alpaca-Roleplay-Lora")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("teknium/Base-GPT4-x-Alpaca-Roleplay-Lora")
model = AutoModelForCausalLM.from_pretrained("teknium/Base-GPT4-x-Alpaca-Roleplay-Lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use teknium/Base-GPT4-x-Alpaca-Roleplay-Lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "teknium/Base-GPT4-x-Alpaca-Roleplay-Lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "teknium/Base-GPT4-x-Alpaca-Roleplay-Lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/teknium/Base-GPT4-x-Alpaca-Roleplay-Lora

SGLang

How to use teknium/Base-GPT4-x-Alpaca-Roleplay-Lora 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 "teknium/Base-GPT4-x-Alpaca-Roleplay-Lora" \
    --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": "teknium/Base-GPT4-x-Alpaca-Roleplay-Lora",
		"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 "teknium/Base-GPT4-x-Alpaca-Roleplay-Lora" \
        --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": "teknium/Base-GPT4-x-Alpaca-Roleplay-Lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use teknium/Base-GPT4-x-Alpaca-Roleplay-Lora with Docker Model Runner:
```
docker model run hf.co/teknium/Base-GPT4-x-Alpaca-Roleplay-Lora
```

4bit GPTQ version?

by nacs - opened Apr 17, 2023

Discussion

nacs

Apr 17, 2023

Thanks for training this dataset. I'd love to try it but was curious if you could upload a 4-bit quantized version of this model?

(It would take a lot less space and VRAM). Thanks!

teknium

Owner Apr 18, 2023

Thanks for training this dataset. I'd love to try it but was curious if you could upload a 4-bit quantized version of this model?

(It would take a lot less space and VRAM). Thanks!

Yes I'll do so right now

gkp255

Apr 19, 2023

Would it be possible to also get a version that works with llama.cpp (https://github.com/ggerganov/llama.cpp)?

teknium

Owner Apr 22, 2023

Would it be possible to also get a version that works with llama.cpp (https://github.com/ggerganov/llama.cpp)?

I'm sorry I've never worked with it, so I'm not quite sure how to

teknium

Owner Apr 22, 2023

Thanks for training this dataset. I'd love to try it but was curious if you could upload a 4-bit quantized version of this model?

(It would take a lot less space and VRAM). Thanks!

I'm uploading a version 2 of the RP Lora merged with GPT4-x-Alpaca model in 4bit quantization right now, you can get it here:
https://huggingface.co/teknium/GPT4-x-Alpaca13b-RolePlayLora-4bit-v2

gkp255

Apr 27, 2023

Would it be possible to also get a version that works with llama.cpp (https://github.com/ggerganov/llama.cpp)?

I'm sorry I've never worked with it, so I'm not quite sure how to

I can take a crack at it. It's for compatibility with Llama.cpp

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment