Instructions to use timdettmers/guanaco-33b-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use timdettmers/guanaco-33b-merged with Transformers:

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

pipe = pipeline("text-generation", model="timdettmers/guanaco-33b-merged")

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

tokenizer = AutoTokenizer.from_pretrained("timdettmers/guanaco-33b-merged")
model = AutoModelForCausalLM.from_pretrained("timdettmers/guanaco-33b-merged", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use timdettmers/guanaco-33b-merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "timdettmers/guanaco-33b-merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "timdettmers/guanaco-33b-merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/timdettmers/guanaco-33b-merged

SGLang

How to use timdettmers/guanaco-33b-merged 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 "timdettmers/guanaco-33b-merged" \
    --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": "timdettmers/guanaco-33b-merged",
		"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 "timdettmers/guanaco-33b-merged" \
        --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": "timdettmers/guanaco-33b-merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use timdettmers/guanaco-33b-merged with Docker Model Runner:
```
docker model run hf.co/timdettmers/guanaco-33b-merged
```

Prompt Format?

by xzuyn - opened May 25, 2023

Discussion

xzuyn

May 25, 2023

Is this using the same format as the LoRA versions? https://huggingface.co/JosephusCheung/Guanaco & https://huggingface.co/KBlueLeaf/guanaco-7B-leh

LoRA Version's Format

### Instruction:
User: History User Input
Assistant: History Assistant Answer
### Input:
System: Knowledge
User: New User Input
### Response:
New Assistant Answer

Based on what @mljxy says on this discussion its not the same as your QLoRA? https://huggingface.co/TheBloke/guanaco-13B-GGML/discussions/1#646f9d3b6098ee820fbd4dba

header = "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions."
prompt_template = "### Human: {query}\n### Assistant:{response}"

Could you add a readme to these QLoRA models so that it's better understood how to properly use them?

YeungNLP

May 26, 2023

I have read the source code, the prompt should be:

A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
### Human: {input}
### Assistant: {output}

cooki3monster

Jun 19, 2023

I have read the source code, the prompt should be:

A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
### Human: {input}
### Assistant: {output}

I'm interested in how I can read the source code to a llm.

Thanks

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