Instructions to use goldfish-models/hin_deva_100mb with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use goldfish-models/hin_deva_100mb with Transformers:

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

pipe = pipeline("text-generation", model="goldfish-models/hin_deva_100mb")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("goldfish-models/hin_deva_100mb")
model = AutoModelForCausalLM.from_pretrained("goldfish-models/hin_deva_100mb")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use goldfish-models/hin_deva_100mb with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "goldfish-models/hin_deva_100mb"
# 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/hin_deva_100mb",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/goldfish-models/hin_deva_100mb

SGLang

How to use goldfish-models/hin_deva_100mb 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/hin_deva_100mb" \
    --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/hin_deva_100mb",
		"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/hin_deva_100mb" \
        --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/hin_deva_100mb",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use goldfish-models/hin_deva_100mb with Docker Model Runner:
```
docker model run hf.co/goldfish-models/hin_deva_100mb
```

goldfish-models commited on Aug 20, 2024

Commit

fd43aa2

verified ·

1 Parent(s): 1b95067

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -18,6 +18,8 @@ Goldfish is a suite of monolingual language models trained for 350 languages.
 This model is the <b>Hindi</b> (Devanagari script) model trained on 100MB of data, after accounting for an estimated byte premium of 2.37; content-matched text in Hindi takes on average 2.37x 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: hin_deva is an [individual language](https://iso639-3.sil.org/code_tables/639/data) code. It is not contained in any macrolanguage codes contained in Goldfish (for script deva).
 All training and hyperparameter details are in our paper, [Goldfish: Monolingual Language Models for 350 Languages (Chang et al., 2024)](https://github.com/tylerachang/goldfish/blob/main/goldfish_paper_20240815.pdf).

 This model is the <b>Hindi</b> (Devanagari script) model trained on 100MB of data, after accounting for an estimated byte premium of 2.37; content-matched text in Hindi takes on average 2.37x 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: hin_latn.
 Note: hin_deva is an [individual language](https://iso639-3.sil.org/code_tables/639/data) code. It is not contained in any macrolanguage codes contained in Goldfish (for script deva).
 All training and hyperparameter details are in our paper, [Goldfish: Monolingual Language Models for 350 Languages (Chang et al., 2024)](https://github.com/tylerachang/goldfish/blob/main/goldfish_paper_20240815.pdf).