Instructions to use alpindale/goliath-120b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alpindale/goliath-120b with Transformers:

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

pipe = pipeline("text-generation", model="alpindale/goliath-120b")

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

tokenizer = AutoTokenizer.from_pretrained("alpindale/goliath-120b")
model = AutoModelForCausalLM.from_pretrained("alpindale/goliath-120b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use alpindale/goliath-120b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alpindale/goliath-120b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alpindale/goliath-120b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/alpindale/goliath-120b

SGLang

How to use alpindale/goliath-120b 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 "alpindale/goliath-120b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alpindale/goliath-120b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "alpindale/goliath-120b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alpindale/goliath-120b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use alpindale/goliath-120b with Docker Model Runner:
```
docker model run hf.co/alpindale/goliath-120b
```

How much CPU ram will it take to load and for inference?

by aslawliet - opened Nov 14, 2023

Discussion

aslawliet

Nov 14, 2023

What is amount of CPU ram will I require to run this model on ubuntu with ram 8gb and swap 150gb?

adamo1139

Nov 14, 2023

Depends on the quantization you use. With 16-bit precision, which is the model in this repository, you would need about 240-260GB. Some people have good results with q2_k quantization that is about 50GB in size, about 55GB RAM use. Still, if you plan to use swap as your primary place for storing the weights during inference, you will have a really bad time running it. Basically, all of the weights need to be read once to generate one token. If you plan to use a SATA 6Gb/s SSD, which is likely given that you have 8GB of RAM, you are looking at read speed of about 500MB/s. Meaning that it would take you 100 seconds to read the weights once, so generating a sentence would take you about 1800 seconds - half an hour.

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