Instructions to use Keynote-Technology/KAI-7B-Instruct-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Keynote-Technology/KAI-7B-Instruct-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="Keynote-Technology/KAI-7B-Instruct-v0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Keynote-Technology/KAI-7B-Instruct-v0.1")
model = AutoModelForCausalLM.from_pretrained("Keynote-Technology/KAI-7B-Instruct-v0.1")
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

vLLM

How to use Keynote-Technology/KAI-7B-Instruct-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Keynote-Technology/KAI-7B-Instruct-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Keynote-Technology/KAI-7B-Instruct-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Keynote-Technology/KAI-7B-Instruct-v0.1

SGLang

How to use Keynote-Technology/KAI-7B-Instruct-v0.1 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 "Keynote-Technology/KAI-7B-Instruct-v0.1" \
    --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": "Keynote-Technology/KAI-7B-Instruct-v0.1",
		"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 "Keynote-Technology/KAI-7B-Instruct-v0.1" \
        --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": "Keynote-Technology/KAI-7B-Instruct-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Keynote-Technology/KAI-7B-Instruct-v0.1 with Docker Model Runner:
```
docker model run hf.co/Keynote-Technology/KAI-7B-Instruct-v0.1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

KAI-7B Instruct

KAI-7B-Instruct is a 7 Billion parameter causal model based on KAI-7B and Mistral-7B. KAI-7B has been finetuned on a mixture of chat/instruct datasets.

Why use KAI-7B Instruct?

KAI-7B is a strong base model, outperforming comparable open-source models (e.g., LLaMA 2 7b, Mistral 7B, e.t.c.).
KAI-7B Instruct is trained on a framework for improving the instruction-following capabilities of pretrained language models.
KAI-7B Instruct is a ready-to-use model based off KAI-7B, meaning it is easier to deploy.

Banned Use

KAI-7B Instruct is governed by the apache 2.0 liscense, and therefore means that whatever the license deems unacceptable shall not be allowed. We specificaly ban the use of ANY AND ALL KAI MODELS for hate speech towards a paricular thing, person, our particular group due to legal and ethical issues.

Downloads last month: 32

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for Keynote-Technology/KAI-7B-Instruct-v0.1

Quantizations

7 models

Datasets used to train Keynote-Technology/KAI-7B-Instruct-v0.1

Collection including Keynote-Technology/KAI-7B-Instruct-v0.1

KAI Large Language Models

Collection

All of the KAI LLMs in one collection. The KAI models are a series of lightweight LLMs ranging from 1 Billion parameters to 7 Billion parameters • 5 items • Updated Nov 14, 2023 • 2