Instructions to use LLaMAX/LLaMAX2-7B-MetaMath with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LLaMAX/LLaMAX2-7B-MetaMath with Transformers:

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

pipe = pipeline("text-generation", model="LLaMAX/LLaMAX2-7B-MetaMath")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LLaMAX/LLaMAX2-7B-MetaMath")
model = AutoModelForCausalLM.from_pretrained("LLaMAX/LLaMAX2-7B-MetaMath")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use LLaMAX/LLaMAX2-7B-MetaMath with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LLaMAX/LLaMAX2-7B-MetaMath"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLaMAX/LLaMAX2-7B-MetaMath",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/LLaMAX/LLaMAX2-7B-MetaMath

SGLang

How to use LLaMAX/LLaMAX2-7B-MetaMath 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/LLaMAX2-7B-MetaMath" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLaMAX/LLaMAX2-7B-MetaMath",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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/LLaMAX2-7B-MetaMath" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLaMAX/LLaMAX2-7B-MetaMath",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LLaMAX/LLaMAX2-7B-MetaMath with Docker Model Runner:
```
docker model run hf.co/LLaMAX/LLaMAX2-7B-MetaMath
```

huangtao6 commited on Jul 9, 2024

Commit

2039528

1 Parent(s): 29d7d78

update readme

Browse files

Files changed (1) hide show

README.md +10 -2

README.md CHANGED Viewed

@@ -1,7 +1,7 @@
 ### Model Sources
 - **Paper**: LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages
-- **Link**:
 - **Repository**: https://github.com/CONE-MT/LLaMAX/
 ### Model Description
@@ -58,5 +58,13 @@ We evaluated LLaMAX2-7B-MetaMath on the MGSM dataset. Compared with MetaMath-7B,
 if our model helps your work, please cite this paper:
 ```
 ```

 ### Model Sources
 - **Paper**: LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages
+- **Link**: https://arxiv.org/pdf/2407.05975
 - **Repository**: https://github.com/CONE-MT/LLaMAX/
 ### Model Description
 if our model helps your work, please cite this paper:
 ```
+@misc{lu2024llamaxscalinglinguistichorizons,
+      title={LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages},
+      author={Yinquan Lu and Wenhao Zhu and Lei Li and Yu Qiao and Fei Yuan},
+      year={2024},
+      eprint={2407.05975},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2407.05975},
+}
 ```