Instructions to use zai-org/LongAlign-7B-64k-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/LongAlign-7B-64k-base with Transformers:

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

pipe = pipeline("text-generation", model="zai-org/LongAlign-7B-64k-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zai-org/LongAlign-7B-64k-base")
model = AutoModelForCausalLM.from_pretrained("zai-org/LongAlign-7B-64k-base")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zai-org/LongAlign-7B-64k-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zai-org/LongAlign-7B-64k-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zai-org/LongAlign-7B-64k-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/zai-org/LongAlign-7B-64k-base

SGLang

How to use zai-org/LongAlign-7B-64k-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 "zai-org/LongAlign-7B-64k-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": "zai-org/LongAlign-7B-64k-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 "zai-org/LongAlign-7B-64k-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": "zai-org/LongAlign-7B-64k-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use zai-org/LongAlign-7B-64k-base with Docker Model Runner:
```
docker model run hf.co/zai-org/LongAlign-7B-64k-base
```

bys0318 commited on Feb 1, 2024

Commit

fa28d01

verified ·

1 Parent(s): 2295749

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -11,7 +11,7 @@ license: apache-2.0
 # LongAlign-7B-64k-base
 <p align="center">
-  🤗 <a href="https://huggingface.co/datasets/THUDM/LongAlign-10k" target="_blank">[LongAlign Dataset] </a> • 💻 <a href="https://github.com/THUDM/LongAlign" target="_blank">[Github Repo]</a> • 📃 <a href="https://arxiv.org/" target="_blank">[LongAlign Paper]</a>
 </p>
 **LongAlign** is the first full recipe for LLM alignment on long context. We propose the **LongAlign-10k** dataset, containing 10,000 long instruction data of 8k-64k in length. We investigate on trianing strategies, namely **packing (with loss weighting) and sorted batching**, which are all implemented in our code. For real-world long context evaluation, we introduce **LongBench-Chat** that evaluate the instruction-following capability on queries of 10k-100k length.

 # LongAlign-7B-64k-base
 <p align="center">
+  🤗 <a href="https://huggingface.co/datasets/THUDM/LongAlign-10k" target="_blank">[LongAlign Dataset] </a> • 💻 <a href="https://github.com/THUDM/LongAlign" target="_blank">[Github Repo]</a> • 📃 <a href="https://arxiv.org/abs/2401.18058" target="_blank">[LongAlign Paper]</a>
 </p>
 **LongAlign** is the first full recipe for LLM alignment on long context. We propose the **LongAlign-10k** dataset, containing 10,000 long instruction data of 8k-64k in length. We investigate on trianing strategies, namely **packing (with loss weighting) and sorted batching**, which are all implemented in our code. For real-world long context evaluation, we introduce **LongBench-Chat** that evaluate the instruction-following capability on queries of 10k-100k length.