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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

Adding prompt template

by mandeepbagga - opened Feb 17, 2024

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

+12

-0

Files changed (1) hide show

README.md +12 -0

README.md CHANGED Viewed

@@ -18,6 +18,18 @@ LWM-Text-1M-Chat was trained in December 2023.
 **Paper or resources for more information:**
 https://largeworldmodel.github.io/
 ## License
 Llama 2 is licensed under the LLAMA 2 Community License,
 Copyright (c) Meta Platforms, Inc. All Rights Reserved.

 **Paper or resources for more information:**
 https://largeworldmodel.github.io/
+## Prompt Template
+**For replicating middle in haystack:**
+```
+You are a helpful assistant. USER: {context} {question} Don't give information outside the document or repeat your findings. Keep your response short and direct. ASSISTANT:
+```
+**For general use:**
+```
+You are a helpful assistant. USER: {context} {question}. ASSISTANT:
+```
 ## License
 Llama 2 is licensed under the LLAMA 2 Community License,
 Copyright (c) Meta Platforms, Inc. All Rights Reserved.