Instructions to use OEvortex/HelpingAI-180B-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OEvortex/HelpingAI-180B-base with Transformers:

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

pipe = pipeline("text-generation", model="OEvortex/HelpingAI-180B-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OEvortex/HelpingAI-180B-base")
model = AutoModelForCausalLM.from_pretrained("OEvortex/HelpingAI-180B-base")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OEvortex/HelpingAI-180B-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OEvortex/HelpingAI-180B-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OEvortex/HelpingAI-180B-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OEvortex/HelpingAI-180B-base

SGLang

How to use OEvortex/HelpingAI-180B-base 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 "OEvortex/HelpingAI-180B-base" \
    --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": "OEvortex/HelpingAI-180B-base",
		"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 "OEvortex/HelpingAI-180B-base" \
        --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": "OEvortex/HelpingAI-180B-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OEvortex/HelpingAI-180B-base with Docker Model Runner:
```
docker model run hf.co/OEvortex/HelpingAI-180B-base
```

Abhaykoul commited on Apr 5, 2024

Commit

49b8306

verified ·

1 Parent(s): 3dda717

Create README.md

Browse files

Files changed (1) hide show

README.md +25 -0

README.md ADDED Viewed

	@@ -0,0 +1,25 @@

+---
+license: mit
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- gemma
+---
+# HelpingAI-180B-base
+## Description
+The HelpingAI-180B-base model is a large-scale artificial intelligence model developed to assist in various natural language processing tasks. Trained on a diverse range of data sources, this model is designed to generate text, facilitate language understanding, and support various downstream tasks.
+## Model Information
+- **Model size**: 180 billion parameters
+- **Training data**: Diverse datasets covering a wide range of topics and domains.
+- **Training objective**: Language modeling with an emphasis on understanding and generating human-like text.
+- **Tokenizer**: Gemma tokenizer
+## Intended Use
+The HelpingAI-180B-base model is intended for researchers, developers, and practitioners in the field of natural language processing (NLP). It can be used for a variety of tasks, including but not limited to:
+- Text generation
+- Language understanding
+- Text summarization
+- Dialogue generation