Instructions to use goldfish-models/zho_hant_10mb with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use goldfish-models/zho_hant_10mb with Transformers:

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

pipe = pipeline("text-generation", model="goldfish-models/zho_hant_10mb")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("goldfish-models/zho_hant_10mb")
model = AutoModelForCausalLM.from_pretrained("goldfish-models/zho_hant_10mb")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use goldfish-models/zho_hant_10mb with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "goldfish-models/zho_hant_10mb"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "goldfish-models/zho_hant_10mb",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/goldfish-models/zho_hant_10mb

SGLang

How to use goldfish-models/zho_hant_10mb 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 "goldfish-models/zho_hant_10mb" \
    --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": "goldfish-models/zho_hant_10mb",
		"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 "goldfish-models/zho_hant_10mb" \
        --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": "goldfish-models/zho_hant_10mb",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use goldfish-models/zho_hant_10mb with Docker Model Runner:
```
docker model run hf.co/goldfish-models/zho_hant_10mb
```

zho_hant_10mb / README.md

goldfish-models

Upload README.md with huggingface_hub

6ae7c26 verified over 1 year ago

preview code

raw

history blame contribute delete

3.07 kB


	---
	license: apache-2.0
	language:
	- zho
	- chi
	datasets:
	- allenai/nllb
	- cis-lmu/Glot500
	- legacy-datasets/wikipedia
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- goldfish
	- arxiv:2408.10441
	---

	# zho_hant_10mb

	Goldfish is a suite of monolingual language models trained for 350 languages.
	This model is the <b>Chinese</b> (Han Traditional script) model trained on 10MB of data, after accounting for an estimated byte premium of 0.99; content-matched text in Chinese takes on average 0.99x as many UTF-8 bytes to encode as English.
	The Goldfish models are trained primarily for comparability across languages and for low-resource languages; Goldfish performance for high-resource languages is not designed to be comparable with modern large language models (LLMs).

	Note: This language is available in Goldfish with other scripts (writing systems). See: zho_hans.

	Note: zho_hant is a [macrolanguage](https://iso639-3.sil.org/code_tables/639/data) code. Individual language codes yue_hant (Yue Chinese) and lzh_hant (Literary Chinese) are included in Goldfish, although with less data.

	All training and hyperparameter details are in our paper, [Goldfish: Monolingual Language Models for 350 Languages (Chang et al., 2024)](https://www.arxiv.org/abs/2408.10441).

	Training code and sample usage: https://github.com/tylerachang/goldfish

	Sample usage also in this Google Colab: [link](https://colab.research.google.com/drive/1rHFpnQsyXJ32ONwCosWZ7frjOYjbGCXG?usp=sharing)

	## Model details:

	To access all Goldfish model details programmatically, see https://github.com/tylerachang/goldfish/blob/main/model_details.json.
	All models are trained with a [CLS] (same as [BOS]) token prepended, and a [SEP] (same as [EOS]) token separating sequences.
	For best results, make sure that [CLS] is prepended to your input sequence (see sample usage linked above)!
	Details for this model specifically:

	* Architecture: gpt2
	* Parameters: 39087104
	* Maximum sequence length: 512 tokens
	* Training text data (raw): 9.89MB
	* Training text data (byte premium scaled): 10.005MB
	* Training tokens: 2445824 (x10 epochs)
	* Vocabulary size: 50000
	* Compute cost: 1848074541465600.0 FLOPs or ~0.2 NVIDIA A6000 GPU hours

	Training datasets (percentages prior to deduplication):
	* 36.42318%: [NLLB (CommonCrawl and ParaCrawl)](https://huggingface.co/datasets/allenai/nllb)
	* 33.54996%: [Wikipedia 2023/08](https://dumps.wikimedia.org/)
	* 29.93702%: [Glot500](https://huggingface.co/datasets/cis-lmu/Glot500), including [CCNet](https://github.com/facebookresearch/cc_net), [Tatoeba](https://tatoeba.org/en/), [Wikipedia Hugging Face](https://huggingface.co/datasets/legacy-datasets/wikipedia)
	* 0.08984%: [Tatoeba](https://tatoeba.org/en/)


	## Citation

	If you use this model, please cite:

	```
	@article{chang-etal-2024-goldfish,
	title={Goldfish: Monolingual Language Models for 350 Languages},
	author={Chang, Tyler A. and Arnett, Catherine and Tu, Zhuowen and Bergen, Benjamin K.},
	journal={Preprint},
	year={2024},
	url={https://www.arxiv.org/abs/2408.10441},
	}
	```