Instructions to use grimulkan/aurelian-alpha0.1-70b-rope8-32K-6bpw_h8_exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grimulkan/aurelian-alpha0.1-70b-rope8-32K-6bpw_h8_exl2 with Transformers:

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

pipe = pipeline("text-generation", model="grimulkan/aurelian-alpha0.1-70b-rope8-32K-6bpw_h8_exl2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("grimulkan/aurelian-alpha0.1-70b-rope8-32K-6bpw_h8_exl2")
model = AutoModelForCausalLM.from_pretrained("grimulkan/aurelian-alpha0.1-70b-rope8-32K-6bpw_h8_exl2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use grimulkan/aurelian-alpha0.1-70b-rope8-32K-6bpw_h8_exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "grimulkan/aurelian-alpha0.1-70b-rope8-32K-6bpw_h8_exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "grimulkan/aurelian-alpha0.1-70b-rope8-32K-6bpw_h8_exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/grimulkan/aurelian-alpha0.1-70b-rope8-32K-6bpw_h8_exl2

SGLang

How to use grimulkan/aurelian-alpha0.1-70b-rope8-32K-6bpw_h8_exl2 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 "grimulkan/aurelian-alpha0.1-70b-rope8-32K-6bpw_h8_exl2" \
    --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": "grimulkan/aurelian-alpha0.1-70b-rope8-32K-6bpw_h8_exl2",
		"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 "grimulkan/aurelian-alpha0.1-70b-rope8-32K-6bpw_h8_exl2" \
        --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": "grimulkan/aurelian-alpha0.1-70b-rope8-32K-6bpw_h8_exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use grimulkan/aurelian-alpha0.1-70b-rope8-32K-6bpw_h8_exl2 with Docker Model Runner:
```
docker model run hf.co/grimulkan/aurelian-alpha0.1-70b-rope8-32K-6bpw_h8_exl2
```

Repetition issue

by lazyDataScientist - opened Dec 11, 2023

Discussion

lazyDataScientist

Dec 11, 2023

Could you share the exact parameters that you use which the model returns good output. I have tried the recommended repetition_penalty setting and I get !?!?!?!?!?!?!?!?!?!... for every prompt that that I gave the model.

grimulkan

Owner Jan 10, 2024

•

edited Jan 11, 2024

Sorry, never got a notification for this comment for some reason.

That type of repetition looks like a different problem. Could be prompt format (llama-chat) or rope scaling (which has to be 8)?

Here are 2 sets that work well for me in Oobabooga:

Standard sampling:

'temperature': 0.8
'top_p': 0.6
'min_p': 0
'top_k': 40
'repetition_penalty': 1.12
'presence_penalty': 0
'frequency_penalty': 0
'repetition_penalty_range': 1024
'typical_p': 1
'tfs': 1
'top_a': 0

Mirostat:

'mirostat_mode': 2
'mirostat_tau': 2
'mirostat_eta': 0.1

with the other settings set to defaults:

'temperature': 1
'top_p': 1
'min_p': 0
'top_k': 0
'repetition_penalty': 1
'presence_penalty': 0
'frequency_penalty': 0
'repetition_penalty_range': 1024
'typical_p': 1
'tfs': 1
'top_a': 0

edit: I see we actually sorted this out in a different thread, didn’t connect the names… Well these settings can be here for others.

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