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
```

Natkituwu commited on Mar 19, 2024

Commit

50d1148

verified ·

1 Parent(s): d7258bb

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -4

README.md CHANGED Viewed

@@ -1,16 +1,22 @@
 ---
-base_model: []
 library_name: transformers
 tags:
 - mergekit
 - merge
 license: cc-by-nc-4.0
 ---
-# Kunokukulemonchini-7b
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
-Here is an 4.1bpw exl2 quant [Kunokukulemonchini-7b-4.1bpw-exl2](https://huggingface.co/icefog72/Kunokukulemonchini-7b-4.1bpw-exl2) for people like me with 6gb vram.
 ## Merge Details
 Slightly edited kukulemon-7B config.json before merge to get at least ~32k context window.

 ---
+base_model:
+- grimjim/kukulemon-7B
+- Nitral-AI/Kunocchini-7b-128k-test
 library_name: transformers
 tags:
 - mergekit
 - merge
+- mistral
+- alpaca
 license: cc-by-nc-4.0
 ---
+# Kunokukulemonchini-7b-5.0bpw-exl2
+This is an 5.0 bpw exl2 quant of a merger [icefog72/Kunokukulemonchini-7b](https://huggingface.co/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.