Instructions to use FPHam/Plot_BOT_V3_13b_GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FPHam/Plot_BOT_V3_13b_GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="FPHam/Plot_BOT_V3_13b_GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FPHam/Plot_BOT_V3_13b_GPTQ")
model = AutoModelForCausalLM.from_pretrained("FPHam/Plot_BOT_V3_13b_GPTQ")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FPHam/Plot_BOT_V3_13b_GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FPHam/Plot_BOT_V3_13b_GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FPHam/Plot_BOT_V3_13b_GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FPHam/Plot_BOT_V3_13b_GPTQ

SGLang

How to use FPHam/Plot_BOT_V3_13b_GPTQ 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 "FPHam/Plot_BOT_V3_13b_GPTQ" \
    --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": "FPHam/Plot_BOT_V3_13b_GPTQ",
		"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 "FPHam/Plot_BOT_V3_13b_GPTQ" \
        --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": "FPHam/Plot_BOT_V3_13b_GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FPHam/Plot_BOT_V3_13b_GPTQ with Docker Model Runner:
```
docker model run hf.co/FPHam/Plot_BOT_V3_13b_GPTQ
```

Wishing for a GGUF

by tofufishes - opened Oct 19, 2023

Discussion

tofufishes

Oct 19, 2023

Any chance you could release a GGUF of this?

I'd love to try it, but I'm on a M1 Mac... so a little bit of nvidia-envy going on here. On the other hand, at q5 or q8 quant would be great since my system ram is shared with the gpu.

And please don't bother if this is too much trouble. I'm new, so I don't really know if I'm asking for something easy or hard.

Either way, thanks in advance!

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