Instructions to use Yukang/Llama-2-7b-longlora-16k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Yukang/Llama-2-7b-longlora-16k with Transformers:

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

pipe = pipeline("text-generation", model="Yukang/Llama-2-7b-longlora-16k")

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

tokenizer = AutoTokenizer.from_pretrained("Yukang/Llama-2-7b-longlora-16k")
model = AutoModelForCausalLM.from_pretrained("Yukang/Llama-2-7b-longlora-16k", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Yukang/Llama-2-7b-longlora-16k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Yukang/Llama-2-7b-longlora-16k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yukang/Llama-2-7b-longlora-16k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Yukang/Llama-2-7b-longlora-16k

SGLang

How to use Yukang/Llama-2-7b-longlora-16k 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 "Yukang/Llama-2-7b-longlora-16k" \
    --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": "Yukang/Llama-2-7b-longlora-16k",
		"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 "Yukang/Llama-2-7b-longlora-16k" \
        --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": "Yukang/Llama-2-7b-longlora-16k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Yukang/Llama-2-7b-longlora-16k with Docker Model Runner:
```
docker model run hf.co/Yukang/Llama-2-7b-longlora-16k
```

Yukang commited on Sep 24, 2023

Commit

4cf8eeb

1 Parent(s): 9efd1b3

Upload README.md

Browse files

Files changed (1) hide show

README.md +1 -3

README.md CHANGED Viewed

@@ -1,8 +1,6 @@
-[![Gradio](https://img.shields.io/badge/Gradio-Online%20Demo-blue)](https://b3cfcf9e79ff42df5f.gradio.live)
 # LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
-<font size=6><div align='center' > <a href=http://arxiv.org/abs/2309.12307>**Paper**</a> | <a href="https://huggingface.co/Yukang">**Models**</a> | <a href="https://github.com/dvlab-research/LongLoRA">**Code**</a> | <a href="https://b3cfcf9e79ff42df5f.gradio.live">**Demo**</a></div></font>
 **LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models [[Paper](http://arxiv.org/abs/2309.12307)]** <br />
 [Yukang Chen](https://scholar.google.com/citations?user=6p0ygKUAAAAJ&hl=en),

 # LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
+<font size=6><div align='center' > <a href=http://arxiv.org/abs/2309.12307>**Paper**</a> | <a href="https://huggingface.co/Yukang">**Models**</a> | <a href="https://github.com/dvlab-research/LongLoRA">**Code**</a> </div></font>
 **LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models [[Paper](http://arxiv.org/abs/2309.12307)]** <br />
 [Yukang Chen](https://scholar.google.com/citations?user=6p0ygKUAAAAJ&hl=en),