Instructions to use Natkituwu/Kunokukulemonchini-7b-5.0bpw-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Natkituwu/Kunokukulemonchini-7b-5.0bpw-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="Natkituwu/Kunokukulemonchini-7b-5.0bpw-exl2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Natkituwu/Kunokukulemonchini-7b-5.0bpw-exl2")
model = AutoModelForCausalLM.from_pretrained("Natkituwu/Kunokukulemonchini-7b-5.0bpw-exl2", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Natkituwu/Kunokukulemonchini-7b-5.0bpw-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Natkituwu/Kunokukulemonchini-7b-5.0bpw-exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Natkituwu/Kunokukulemonchini-7b-5.0bpw-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Natkituwu/Kunokukulemonchini-7b-5.0bpw-exl2

SGLang

How to use Natkituwu/Kunokukulemonchini-7b-5.0bpw-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 "Natkituwu/Kunokukulemonchini-7b-5.0bpw-exl2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Natkituwu/Kunokukulemonchini-7b-5.0bpw-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Natkituwu/Kunokukulemonchini-7b-5.0bpw-exl2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Natkituwu/Kunokukulemonchini-7b-5.0bpw-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Natkituwu/Kunokukulemonchini-7b-5.0bpw-exl2 with Docker Model Runner:
```
docker model run hf.co/Natkituwu/Kunokukulemonchini-7b-5.0bpw-exl2
```

Kunokukulemonchini-7b-5.0bpw-exl2

This is an 5.0 bpw exl2 quant of a merger icefog72/Kunokukulemonchini-7b.

Good balance between 4.1bpw and 6.5bpw, should give more context than 6.5bpw.

Merge Details

Slightly edited kukulemon-7B config.json before merge to get at least ~32k context window.

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:


slices:
  - sources:
      - model: grimjim/kukulemon-7B
        layer_range: [0, 32]
      - model: Nitral-AI/Kunocchini-7b-128k-test
        layer_range: [0, 32]
merge_method: slerp
base_model: Nitral-AI/Kunocchini-7b-128k-test
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: float16

Downloads last month: 11

Model tree for Natkituwu/Kunokukulemonchini-7b-5.0bpw-exl2

ChaoticNeutrals/Kunocchini-7b-128k-test

grimjim/kukulemon-7B

Merge model

this model