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, AutoModelForMultimodalLM

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

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
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This model has been llamafied and uses a llama tokenizer. I took it from https://huggingface.co/chargoddard/Yi-34B-Llama It's fine tuned on EverythingLM dataset for 5 epochs with NEFTune. If you want to understand the pun of the model name, you gotta look at the 3b version of it.

License The Yi series models are fully open for academic research and free commercial usage with permission via applications. All usage must adhere to the Model License Agreement 2.0. To apply for the official commercial license, please contact us (yi@01.ai).

Prompt Example:

### System:

You are an AI assistant. User will give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps.

### Instruction: 

How do you fine tune a large language model? 

### Response:

Downloads last month: 110

Safetensors

Model size

34B params

Tensor type

F16

Model tree for KnutJaegersberg/Deacon-34B

Quantizations

6 models

KnutJaegersberg
/

Deacon-34B

Model tree for KnutJaegersberg/Deacon-34B

Dataset used to train KnutJaegersberg/Deacon-34B