Instructions to use Xwin-LM/Xwin-LM-70B-V0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Xwin-LM/Xwin-LM-70B-V0.1 with Transformers:

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

pipe = pipeline("text-generation", model="Xwin-LM/Xwin-LM-70B-V0.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Xwin-LM/Xwin-LM-70B-V0.1")
model = AutoModelForCausalLM.from_pretrained("Xwin-LM/Xwin-LM-70B-V0.1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Xwin-LM/Xwin-LM-70B-V0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Xwin-LM/Xwin-LM-70B-V0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Xwin-LM/Xwin-LM-70B-V0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Xwin-LM/Xwin-LM-70B-V0.1

SGLang

How to use Xwin-LM/Xwin-LM-70B-V0.1 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 "Xwin-LM/Xwin-LM-70B-V0.1" \
    --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": "Xwin-LM/Xwin-LM-70B-V0.1",
		"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 "Xwin-LM/Xwin-LM-70B-V0.1" \
        --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": "Xwin-LM/Xwin-LM-70B-V0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Xwin-LM/Xwin-LM-70B-V0.1 with Docker Model Runner:
```
docker model run hf.co/Xwin-LM/Xwin-LM-70B-V0.1
```

Adding Evaluation Results

by leaderboard-pr-bot - opened Nov 17, 2023

base: refs/heads/main

←

from: refs/pr/9

Discussion Files changed

+14

-0

Files changed (1) hide show

README.md +14 -0

README.md CHANGED Viewed

@@ -152,3 +152,17 @@ Please consider citing our work if you use the data or code in this repo.
 ## Acknowledgements
 Thanks to [Llama 2](https://ai.meta.com/llama/), [FastChat](https://github.com/lm-sys/FastChat), [AlpacaFarm](https://github.com/tatsu-lab/alpaca_farm), and [vllm](https://github.com/vllm-project/vllm).

 ## Acknowledgements
 Thanks to [Llama 2](https://ai.meta.com/llama/), [FastChat](https://github.com/lm-sys/FastChat), [AlpacaFarm](https://github.com/tatsu-lab/alpaca_farm), and [vllm](https://github.com/vllm-project/vllm).
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Xwin-LM__Xwin-LM-70B-V0.1)
+| Metric                | Value                     |
+|-----------------------|---------------------------|
+| Avg.                  | 58.87   |
+| ARC (25-shot)         | 70.22          |
+| HellaSwag (10-shot)   | 87.25    |
+| MMLU (5-shot)         | 69.77         |
+| TruthfulQA (0-shot)   | 59.86   |
+| Winogrande (5-shot)   | 82.87   |
+| GSM8K (5-shot)        | 27.22        |
+| DROP (3-shot)         | 14.91         |