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
Notebooks
Google Colab
Kaggle
Local Apps

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
```

LLaMAX commited on Dec 6, 2024

Commit

1c357ba

verified ·

1 Parent(s): 406d97d

Update README.md

Browse files

Files changed (1) hide show

README.md +19 -5

README.md CHANGED Viewed

@@ -133,10 +133,24 @@ Akrikaans (af), Amharic (am), Arabic (ar), Armenian (hy), Assamese (as), Asturia
 If our model helps your work, please cite this paper:
 ```
-@article{lu2024llamax,
-  title={LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages},
-  author={Lu, Yinquan and Zhu, Wenhao and Li, Lei and Qiao, Yu and Yuan, Fei},
-  journal={arXiv preprint arXiv:2407.05975},
-  year={2024}
 }
 ```

 If our model helps your work, please cite this paper:
 ```
+@inproceedings{lu-etal-2024-llamax,
+    title = "{LL}a{MAX}: Scaling Linguistic Horizons of {LLM} by Enhancing Translation Capabilities Beyond 100 Languages",
+    author = "Lu, Yinquan  and
+      Zhu, Wenhao  and
+      Li, Lei  and
+      Qiao, Yu  and
+      Yuan, Fei",
+    editor = "Al-Onaizan, Yaser  and
+      Bansal, Mohit  and
+      Chen, Yun-Nung",
+    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
+    month = nov,
+    year = "2024",
+    address = "Miami, Florida, USA",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2024.findings-emnlp.631",
+    doi = "10.18653/v1/2024.findings-emnlp.631",
+    pages = "10748--10772",
+    abstract = "Large Language Models (LLMs) demonstrate remarkable translation capabilities in high-resource language tasks, yet their performance in low-resource languages is hindered by insufficient multilingual data during pre-training. To address this, we conduct extensive multilingual continual pre-training on the LLaMA series models, enabling translation support across more than 100 languages. Through a comprehensive analysis of training strategies, such as vocabulary expansion and data augmentation, we develop LLaMAX. Remarkably, without sacrificing its generalization ability, LLaMAX achieves significantly higher translation performance compared to existing open-source LLMs (by more than 10 spBLEU points) and performs on-par with specialized translation model (M2M-100-12B) on the Flores-101 benchmark. Extensive experiments indicate that LLaMAX can serve as a robust multilingual foundation model. The code and the models are publicly available.",
 }
 ```