Instructions to use LoneStriker/LWM-Text-Chat-1M-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LoneStriker/LWM-Text-Chat-1M-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="LoneStriker/LWM-Text-Chat-1M-AWQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LoneStriker/LWM-Text-Chat-1M-AWQ")
model = AutoModelForCausalLM.from_pretrained("LoneStriker/LWM-Text-Chat-1M-AWQ")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LoneStriker/LWM-Text-Chat-1M-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LoneStriker/LWM-Text-Chat-1M-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LoneStriker/LWM-Text-Chat-1M-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/LoneStriker/LWM-Text-Chat-1M-AWQ

SGLang

How to use LoneStriker/LWM-Text-Chat-1M-AWQ 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 "LoneStriker/LWM-Text-Chat-1M-AWQ" \
    --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": "LoneStriker/LWM-Text-Chat-1M-AWQ",
		"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 "LoneStriker/LWM-Text-Chat-1M-AWQ" \
        --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": "LoneStriker/LWM-Text-Chat-1M-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LoneStriker/LWM-Text-Chat-1M-AWQ with Docker Model Runner:
```
docker model run hf.co/LoneStriker/LWM-Text-Chat-1M-AWQ
```

VRAM require

by paperplanedeemo - opened Feb 19, 2024

Discussion

paperplanedeemo

Feb 19, 2024

exm. Could you please tell me how much VRAM does this model require?I haven't tested it yet, so I want to choose a configuration that meets the requirements for deployment. Thank you!

LoneStriker

Owner Feb 19, 2024

Not sure, but I was able to get to around 190K context with about 110 GB VRAM across my 5x 3090s using the exl2 quant. 1M is going to be some ungodly number.

paperplanedeemo

Feb 20, 2024

Not sure, but I was able to get to around 190K context with about 110 GB VRAM across my 5x 3090s using the exl2 quant. 1M is going to be some ungodly number.

thank you so much

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