Instructions to use kalo-team/llama3-4x8b-pythonT2_step_final with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kalo-team/llama3-4x8b-pythonT2_step_final with Transformers:

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

pipe = pipeline("text-generation", model="kalo-team/llama3-4x8b-pythonT2_step_final")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kalo-team/llama3-4x8b-pythonT2_step_final")
model = AutoModelForCausalLM.from_pretrained("kalo-team/llama3-4x8b-pythonT2_step_final")
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 kalo-team/llama3-4x8b-pythonT2_step_final with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kalo-team/llama3-4x8b-pythonT2_step_final"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kalo-team/llama3-4x8b-pythonT2_step_final",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kalo-team/llama3-4x8b-pythonT2_step_final

SGLang

How to use kalo-team/llama3-4x8b-pythonT2_step_final 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 "kalo-team/llama3-4x8b-pythonT2_step_final" \
    --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": "kalo-team/llama3-4x8b-pythonT2_step_final",
		"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 "kalo-team/llama3-4x8b-pythonT2_step_final" \
        --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": "kalo-team/llama3-4x8b-pythonT2_step_final",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kalo-team/llama3-4x8b-pythonT2_step_final with Docker Model Runner:
```
docker model run hf.co/kalo-team/llama3-4x8b-pythonT2_step_final
```

Training Code

by ahandleman - opened Jun 4, 2024

Discussion

ahandleman

Jun 4, 2024

Any chance your team would be willing to release your training code? I'm interested in your approach to knowledge distillation and afaik right now there aren't any open source knowledge distillation projects.

IkariDev

kalo-team org Jun 5, 2024

Training code will be open source at some point, idk when tho, would have to ask @kalomaze .

WhoTookMyAmogusNickname

kalo-team org Jun 18, 2024

•

edited Jun 18, 2024

@ahandleman Heya, I'm the dev behind the pipeline, opensourcing it is in my plans, no promises on when exactly as this has been one hell of a project for me, for which it earned its loving nickname of "purgatory", but it'll get released. Currently aiming to opensource at the same time as we release a nice distilled model.

WhoTookMyAmogusNickname

kalo-team org Jul 23, 2024

Hey @ahandleman , the training code had been released!
https://github.com/golololologol/LLM-Distillery

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment