Instructions to use TheBloke/Vicuna-13B-1-3-SuperHOT-8K-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/Vicuna-13B-1-3-SuperHOT-8K-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/Vicuna-13B-1-3-SuperHOT-8K-GPTQ", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/Vicuna-13B-1-3-SuperHOT-8K-GPTQ", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("TheBloke/Vicuna-13B-1-3-SuperHOT-8K-GPTQ", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/Vicuna-13B-1-3-SuperHOT-8K-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/Vicuna-13B-1-3-SuperHOT-8K-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/Vicuna-13B-1-3-SuperHOT-8K-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/Vicuna-13B-1-3-SuperHOT-8K-GPTQ

SGLang

How to use TheBloke/Vicuna-13B-1-3-SuperHOT-8K-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 "TheBloke/Vicuna-13B-1-3-SuperHOT-8K-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": "TheBloke/Vicuna-13B-1-3-SuperHOT-8K-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 "TheBloke/Vicuna-13B-1-3-SuperHOT-8K-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": "TheBloke/Vicuna-13B-1-3-SuperHOT-8K-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/Vicuna-13B-1-3-SuperHOT-8K-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/Vicuna-13B-1-3-SuperHOT-8K-GPTQ
```

3000+ context, no output

by underlines - opened Jun 26, 2023

Discussion

underlines

Jun 26, 2023

I set everything exactly as mentioned, ExLlama, max_seq_len 8192, compress_pos_emb 4, short contexts work, but when I paste a 3000 token context for summarization, the generated tokens are simply 0.
Tried all Vicuna Prompt Templates, instruct, chat-instruct and chat etc.

underlines

Jun 28, 2023

https://huggingface.co/TheBloke/Vicuna-33B-1-1-preview-SuperHOT-8K-GPTQ/discussions/1#649c0950272ee9fd6b635ea3

For people using TheBloke's Runpod Template: It didn't update ExLlama, but it's now fixed. Restart your pods or update ExLlama.

underlines changed discussion status to closed Jun 28, 2023

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