Instructions to use Kooten/DaringLotus-4bpw-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kooten/DaringLotus-4bpw-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="Kooten/DaringLotus-4bpw-exl2")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Kooten/DaringLotus-4bpw-exl2")
model = AutoModelForCausalLM.from_pretrained("Kooten/DaringLotus-4bpw-exl2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Kooten/DaringLotus-4bpw-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kooten/DaringLotus-4bpw-exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kooten/DaringLotus-4bpw-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Kooten/DaringLotus-4bpw-exl2

SGLang

How to use Kooten/DaringLotus-4bpw-exl2 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 "Kooten/DaringLotus-4bpw-exl2" \
    --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": "Kooten/DaringLotus-4bpw-exl2",
		"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 "Kooten/DaringLotus-4bpw-exl2" \
        --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": "Kooten/DaringLotus-4bpw-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Kooten/DaringLotus-4bpw-exl2 with Docker Model Runner:
```
docker model run hf.co/Kooten/DaringLotus-4bpw-exl2
```

DaringLotus-10.7B 4bpw EXL2

Description

EXL2 quant of BlueNipples/DaringLotus-10.7B

6bpw should be comfortable on 12 gb with 8k context
4bpw might just fit on 8gb of vram at 4k context
if you have more ram get the 8bpw

Other quants:

EXL2: 8bpw, 6bpw, 5bpw, 4bpw

Prompt Format

Alpaca:

I am not entirely certain of this but i think alpaca is correct for this model

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Input:
{input}

### Response:

Contact

Kooten on discord

Downloads last month: 16