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

Libraries

How to use goldfish-models/kon_latn_full with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use goldfish-models/kon_latn_full with vLLM:

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

goldfish-models commited on Aug 25, 2024

Commit

a8a8b54

verified ·

1 Parent(s): fadf806

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -12,7 +12,7 @@ library_name: transformers
 pipeline_tag: text-generation
 tags:
 - goldfish
 ---
 # kon_latn_full
@@ -23,7 +23,7 @@ The Goldfish models are trained primarily for comparability across languages and
 Note: kon_latn is a [macrolanguage](https://iso639-3.sil.org/code_tables/639/data) code. None of its contained individual languages are included in Goldfish (for script latn).
-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).
 Training code and sample usage: https://github.com/tylerachang/goldfish
@@ -33,6 +33,7 @@ Sample usage also in this Google Colab: [link](https://colab.research.google.com
 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.
 Details for this model specifically:
 * Architecture: gpt2
@@ -61,5 +62,6 @@ If you use this model, please cite:
   author={Chang, Tyler A. and Arnett, Catherine and Tu, Zhuowen and Bergen, Benjamin K.},
   journal={Preprint},
   year={2024},
 }
 ```

 pipeline_tag: text-generation
 tags:
 - goldfish
+- arxiv:2408.10441
 ---
 # kon_latn_full
 Note: kon_latn is a [macrolanguage](https://iso639-3.sil.org/code_tables/639/data) code. None of its contained individual languages are included in Goldfish (for script latn).
+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
 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
   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},
 }
 ```