Instructions to use LLaMAX/LLaMAX3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LLaMAX/LLaMAX3-8B with Transformers:

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

pipe = pipeline("text-generation", model="LLaMAX/LLaMAX3-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LLaMAX/LLaMAX3-8B")
model = AutoModelForCausalLM.from_pretrained("LLaMAX/LLaMAX3-8B")
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]:]))

Inference
Local Apps Settings

vLLM

How to use LLaMAX/LLaMAX3-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LLaMAX/LLaMAX3-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLaMAX/LLaMAX3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LLaMAX/LLaMAX3-8B

SGLang

How to use LLaMAX/LLaMAX3-8B 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 "LLaMAX/LLaMAX3-8B" \
    --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": "LLaMAX/LLaMAX3-8B",
		"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 "LLaMAX/LLaMAX3-8B" \
        --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": "LLaMAX/LLaMAX3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LLaMAX/LLaMAX3-8B with Docker Model Runner:
```
docker model run hf.co/LLaMAX/LLaMAX3-8B
```

Please explain.

by ZeroWw - opened Jul 9, 2024

Discussion

ZeroWw

Jul 9, 2024

Is this a finetune or the model was trained from scratch/merged?

ZeroWw

Jul 9, 2024

Hmm it seems it was trained from scratch..
Who did this?

llama-anon

Jul 10, 2024

This comment has been hidden

LLaMAX

Owner Jul 12, 2024

Is this a finetune or the model was trained from scratch/merged?

Thank you for your interest in our work. Our model is based on the LLaMA series models and has been further trained on over 100 languages. For detailed training information, please refer to our paper: https://arxiv.org/pdf/2407.05975

ZeroWw

Jul 12, 2024

further? meaning "finetuned"?

LLaMAX

Owner Jul 21, 2024

further? meaning "finetuned"?

Yes, we used LLaMA3 as the starting point and trained it on data from more languages.

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