Instructions to use KnutJaegersberg/Deacon-34b-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KnutJaegersberg/Deacon-34b-4bit with Transformers:

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

pipe = pipeline("text-generation", model="KnutJaegersberg/Deacon-34b-4bit")

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("KnutJaegersberg/Deacon-34b-4bit")
model = AutoModel.from_pretrained("KnutJaegersberg/Deacon-34b-4bit")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use KnutJaegersberg/Deacon-34b-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KnutJaegersberg/Deacon-34b-4bit"
# 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-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/KnutJaegersberg/Deacon-34b-4bit

SGLang

How to use KnutJaegersberg/Deacon-34b-4bit 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-4bit" \
    --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-4bit",
		"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-4bit" \
        --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-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use KnutJaegersberg/Deacon-34b-4bit with Docker Model Runner:
```
docker model run hf.co/KnutJaegersberg/Deacon-34b-4bit
```

The perfect organism.

An adapter for KnutJaegersberg/Yi-34B-Llamafied. 5 epochs with NEFTune. The brand new bitsandbytes 4-bit file format.

Run pip install -U bitsandbytes and install this pull requested transformer version: https://github.com/poedator/transformers/tree/save4

Might still be buggy. It was a bit too early. I'll wait until the functionality is officially supported, due to some cuda issues. I don't want to resolve those, I'll just wait a couple of days.

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: 21

KnutJaegersberg
/

Deacon-34b-4bit

Dataset used to train KnutJaegersberg/Deacon-34b-4bit