Instructions to use xDAN-AI/xDAN-L2-Chat-Performance-e2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xDAN-AI/xDAN-L2-Chat-Performance-e2 with Transformers:

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

pipe = pipeline("text-generation", model="xDAN-AI/xDAN-L2-Chat-Performance-e2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("xDAN-AI/xDAN-L2-Chat-Performance-e2")
model = AutoModelForCausalLM.from_pretrained("xDAN-AI/xDAN-L2-Chat-Performance-e2")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use xDAN-AI/xDAN-L2-Chat-Performance-e2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xDAN-AI/xDAN-L2-Chat-Performance-e2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xDAN-AI/xDAN-L2-Chat-Performance-e2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/xDAN-AI/xDAN-L2-Chat-Performance-e2

SGLang

How to use xDAN-AI/xDAN-L2-Chat-Performance-e2 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 "xDAN-AI/xDAN-L2-Chat-Performance-e2" \
    --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": "xDAN-AI/xDAN-L2-Chat-Performance-e2",
		"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 "xDAN-AI/xDAN-L2-Chat-Performance-e2" \
        --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": "xDAN-AI/xDAN-L2-Chat-Performance-e2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use xDAN-AI/xDAN-L2-Chat-Performance-e2 with Docker Model Runner:
```
docker model run hf.co/xDAN-AI/xDAN-L2-Chat-Performance-e2
```

Passthrough?

by Kquant03 - opened Jan 30, 2024

Discussion

Kquant03

Jan 30, 2024

Passthrough of one of the xDan models to increase it up to 13B

Perhaps DARE ties or a SLERP of the resulting merge with Cat 13B

Then, perhaps attempting to passthrough this up to 20B so I can merge it with Psyfighter 20B.

Going to have to be careful and test each merge after they finish to make sure it isn't broken before continuing down those steps.

Would I be able to try this if you gave me access to your repo?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment