Instructions to use KnutJaegersberg/Deacon-34B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KnutJaegersberg/Deacon-34B with Transformers:

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

pipe = pipeline("text-generation", model="KnutJaegersberg/Deacon-34B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KnutJaegersberg/Deacon-34B")
model = AutoModelForCausalLM.from_pretrained("KnutJaegersberg/Deacon-34B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use KnutJaegersberg/Deacon-34B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KnutJaegersberg/Deacon-34B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KnutJaegersberg/Deacon-34B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/KnutJaegersberg/Deacon-34B

SGLang

How to use KnutJaegersberg/Deacon-34B 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 "KnutJaegersberg/Deacon-34B" \
    --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": "KnutJaegersberg/Deacon-34B",
		"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 "KnutJaegersberg/Deacon-34B" \
        --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": "KnutJaegersberg/Deacon-34B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use KnutJaegersberg/Deacon-34B with Docker Model Runner:
```
docker model run hf.co/KnutJaegersberg/Deacon-34B
```

Update README.md with license information

by Chen-01AI - opened Jun 25, 2024

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-3

Chen-01AI

Jun 25, 2024

•

edited Jun 27, 2024

Today I'm sending you the PR to help you update the model license, and give a recommendation according to apache-2.0.

License Update:
Since license of all Yi Series models has been updated from yi-license to apache-2.0, this PR is to help you update it.
License under apache-2.0 enables more free and flexible use and distribution, promoting open collaboration and innovation. It can be a good choice to make your models widely available and provide access which is reliable and high-quality. (https://www.apache.org/licenses/LICENSE-2.0)
If it looks good to you, you can choose to update other yi derivatives (if you have) license to apache-2.0 on your own if I miss out.
Recommendation for Yi Derivatives:
All Yi Series models are now licensed under apache-2.0. It is recomended that Yi derivatives mention the specific Yi models they're based on in any place (e.g., in the Model Card) to align with the requirement of apache-2.0.
Ways of changing other derivatives:
I've noticed that you have created many inspiring Yi derivatives.
Since each pull request (PR) sends you a notification, I'm concerned that sending PRs for all your derivatives might overwhelm you with emails.
To avoid this, I’m wondering which approach you’d prefer: should I send PRs for each derivative, or would it be better for you to update them on your own? Please let me know your decision, thanks!
Thanks for your continued support and contributions to Yi models.

Update README.md with license information48b85910

Chen-01AI

Jul 5, 2024

Hi, have you reviewd this PR? If it looks good to you, you can merge it! 😀 And tell me the way that you would like to use to update other derivatives now licensed under yi-license.

KnutJaegersberg changed pull request status to merged Jul 12, 2024

KnutJaegersberg

Owner Jul 12, 2024

Sure, thanks for the initiative!

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