Instructions to use ICTNLP/bayling-7b-diff with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ICTNLP/bayling-7b-diff with Transformers:

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

pipe = pipeline("text-generation", model="ICTNLP/bayling-7b-diff")

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

tokenizer = AutoTokenizer.from_pretrained("ICTNLP/bayling-7b-diff")
model = AutoModelForCausalLM.from_pretrained("ICTNLP/bayling-7b-diff", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ICTNLP/bayling-7b-diff with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ICTNLP/bayling-7b-diff

SGLang

How to use ICTNLP/bayling-7b-diff 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 "ICTNLP/bayling-7b-diff" \
    --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": "ICTNLP/bayling-7b-diff",
		"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 "ICTNLP/bayling-7b-diff" \
        --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": "ICTNLP/bayling-7b-diff",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ICTNLP/bayling-7b-diff with Docker Model Runner:
```
docker model run hf.co/ICTNLP/bayling-7b-diff
```

Vily1998 commited on Jun 19, 2023

Commit

2f63dc5

1 Parent(s): bfff42d

update

Browse files

Files changed (1) hide show

README.md +25 -0

README.md CHANGED Viewed

@@ -1,3 +1,28 @@
 ---
 license: gpl-3.0
 ---

 ---
 license: gpl-3.0
 ---
+# BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models
+**BayLing** (**百聆**, **bǎi líng**) is an instruction-following LLM equipped with advanced language alignment, showing superior capability in English/Chinese generation, instruction following and multi-turn interaction. BayLing can be  effortlessly deployed on a consumer-grade GPU with 16GB of memory, and assists users with tasks such as translation, writing, creation, suggestion...
+**This model is the *weight-diff* version of BayLing-7B.**
+👇 Learn more about BayLing:
+💬 [**Demo**](http://nlp.ict.ac.cn/bayling/demo): Welcome to apply for a trial of BayLing's online demo (beta version).
+📄 **Paper**: BayLing's technical report.
+🏠 [**Blog**](http://nlp.ict.ac.cn/bayling): BayLing's homepage. You can discover some case of BayLing here.
+✍️ [**BayLing-80 Test Set**](./data/BayLing-80): A human-annotated evaluation set comprising multi-turn instructions in both English and Chinese, can be used to evaluate the multilingual and multi-turn interaction capabilities of LLMs.
+🤗 **Model**: The *weight-diff* version of [BayLing-7B](https://huggingface.co/ICTNLP/bayling-7b-diff) and [BayLing-13B](https://huggingface.co/ICTNLP/bayling-13b-diff), you can quickly get the parameters of BayLing through [apply_delta.py](./apply_delta.py). The HF models of BayLing are anonymized version (exclude BayLing's name in its knowledge), in order to facilitate future LLMs to build upon BayLing.
+> BayLing is developed by [NLP Group](http://nlp.ict.ac.cn/) of [Institute of Computing Technology](https://www.cas.cn/), [Chinese Academy of Sciences](https://www.cas.cn/) (ICT/CAS)
+>
+> Any question or suggestion, please contact with `bayling@ict.ac.cn`
+Refer to our [Github Repo](https://github.com/ictnlp/BayLing) for the detailed introduction to BayLing, including deploying BayLing, interacting with BayLing and BayLing's performance.