Instructions to use sail/data-mixture-human-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sail/data-mixture-human-1b with Transformers:

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

pipe = pipeline("text-generation", model="sail/data-mixture-human-1b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sail/data-mixture-human-1b")
model = AutoModelForCausalLM.from_pretrained("sail/data-mixture-human-1b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use sail/data-mixture-human-1b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sail/data-mixture-human-1b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sail/data-mixture-human-1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sail/data-mixture-human-1b

SGLang

How to use sail/data-mixture-human-1b 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 "sail/data-mixture-human-1b" \
    --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": "sail/data-mixture-human-1b",
		"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 "sail/data-mixture-human-1b" \
        --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": "sail/data-mixture-human-1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sail/data-mixture-human-1b with Docker Model Runner:
```
docker model run hf.co/sail/data-mixture-human-1b
```

SivilTaram commited on Jul 11, 2024

Commit

fcb60ec

verified ·

1 Parent(s): 777b5b9

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -8

README.md CHANGED Viewed

@@ -71,6 +71,7 @@ valid:
   valid_the_pile_pile_cc: 1.0
 model_name: tinyllama_1_1b
 ```
 ## Model Variants
@@ -98,14 +99,11 @@ We evaluated each model using [lm-evaluation-harness](https://github.com/Eleuthe
 If you use these models in your research, please cite the RegMix paper:
 ```
-@misc{liu2024regmix,
-      title={RegMix: Data Mixture as Regression for Language Model Pre-training},
-      author={Qian Liu and Xiaosen Zheng and Niklas Muennighoff and Guangtao Zeng and Longxu Dou and Tianyu Pang and Jing Jiang and Min Lin},
-      year={2024},
-      eprint={2407.01492},
-      archivePrefix={arXiv},
-      primaryClass={cs.CL},
-      url={https://arxiv.org/abs/2407.01492},
 }
 ```

   valid_the_pile_pile_cc: 1.0
 model_name: tinyllama_1_1b
 ```
+> Domain weights will be normalized to make sure their sum is 1.0 for train sets in our code.
 ## Model Variants
 If you use these models in your research, please cite the RegMix paper:
 ```
+@article{liu2024regmix,
+  title={RegMix: Data Mixture as Regression for Language Model Pre-training},
+  author={Liu, Qian and Zheng, Xiaosen and Muennighoff, Niklas and Zeng, Guangtao and Dou, Longxu and Pang, Tianyu and Jiang, Jing and Lin, Min},
+  journal={arXiv preprint arXiv:2407.01492},
+  year={2024}
 }
 ```