Instructions to use barbaroo/gptsw3-6.7B-translation-en-fo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use barbaroo/gptsw3-6.7B-translation-en-fo with Transformers:

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

pipe = pipeline("text-generation", model="barbaroo/gptsw3-6.7B-translation-en-fo")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("barbaroo/gptsw3-6.7B-translation-en-fo")
model = AutoModelForCausalLM.from_pretrained("barbaroo/gptsw3-6.7B-translation-en-fo", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use barbaroo/gptsw3-6.7B-translation-en-fo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "barbaroo/gptsw3-6.7B-translation-en-fo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "barbaroo/gptsw3-6.7B-translation-en-fo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/barbaroo/gptsw3-6.7B-translation-en-fo

SGLang

How to use barbaroo/gptsw3-6.7B-translation-en-fo 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 "barbaroo/gptsw3-6.7B-translation-en-fo" \
    --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": "barbaroo/gptsw3-6.7B-translation-en-fo",
		"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 "barbaroo/gptsw3-6.7B-translation-en-fo" \
        --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": "barbaroo/gptsw3-6.7B-translation-en-fo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use barbaroo/gptsw3-6.7B-translation-en-fo with Docker Model Runner:
```
docker model run hf.co/barbaroo/gptsw3-6.7B-translation-en-fo
```

barbaroo commited on Sep 2, 2025

Commit

b0f57ff

verified ·

1 Parent(s): 200a18a

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -3

README.md CHANGED Viewed

@@ -13,9 +13,8 @@ tags: []
 ### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 - **Developed by:** [More Information Needed]
 - **Funded by [optional]:** [More Information Needed]
@@ -120,7 +119,9 @@ Use the code below to get started with the model.
 #### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
 [More Information Needed]

 ### Model Description
+This is the merged version of the adapter (barbaroo/gptsw3_translate_synth_6.7B) and the base model (AI-Sweden-Models/gpt-sw3-6.7b-v2)
 - **Developed by:** [More Information Needed]
 - **Funded by [optional]:** [More Information Needed]
 #### Metrics
+BLEU score: 19.8
+CHRF score: 52.4
 [More Information Needed]