Instructions to use ChaoticNeutrals/Kunocchini-7b-128k-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ChaoticNeutrals/Kunocchini-7b-128k-test with Transformers:

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

pipe = pipeline("text-generation", model="ChaoticNeutrals/Kunocchini-7b-128k-test", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ChaoticNeutrals/Kunocchini-7b-128k-test", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("ChaoticNeutrals/Kunocchini-7b-128k-test", trust_remote_code=True)
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 ChaoticNeutrals/Kunocchini-7b-128k-test with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ChaoticNeutrals/Kunocchini-7b-128k-test"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ChaoticNeutrals/Kunocchini-7b-128k-test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ChaoticNeutrals/Kunocchini-7b-128k-test

SGLang

How to use ChaoticNeutrals/Kunocchini-7b-128k-test 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 "ChaoticNeutrals/Kunocchini-7b-128k-test" \
    --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": "ChaoticNeutrals/Kunocchini-7b-128k-test",
		"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 "ChaoticNeutrals/Kunocchini-7b-128k-test" \
        --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": "ChaoticNeutrals/Kunocchini-7b-128k-test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ChaoticNeutrals/Kunocchini-7b-128k-test with Docker Model Runner:
```
docker model run hf.co/ChaoticNeutrals/Kunocchini-7b-128k-test
```

Possible to make a request?

by Lewdiculous - opened Mar 12, 2024

Discussion

Lewdiculous

Mar 12, 2024

•

edited Mar 12, 2024

Not sure if you take requests like this, if you do and have the spare time and hardware availability, could we see a Slerp similar to this but with these?

Endevor/InfinityRP-v1-7B
Epiculous/Fett-uccine-Long-Noodle-7B-120k-Context

If it is viable of course, I'm not sure about specifics.

🤗

Nitral-AI

The Chaotic Neutrals org Mar 12, 2024

•

edited Mar 12, 2024

Very feasible - its in the oven now, should automatically upload when done. @Lewdiculous

Lewdiculous

Mar 12, 2024

•

edited Mar 12, 2024

Thanks for the quick action.

Mostly want to see if cohesion at slightly higher context can be improved without losing the original quality, but well... Fingers crossed mostly for a miracle.