Instructions to use merge-crew/da-sv-task-arithmetic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use merge-crew/da-sv-task-arithmetic with Transformers:

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

pipe = pipeline("text-generation", model="merge-crew/da-sv-task-arithmetic")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("merge-crew/da-sv-task-arithmetic")
model = AutoModelForCausalLM.from_pretrained("merge-crew/da-sv-task-arithmetic")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use merge-crew/da-sv-task-arithmetic with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/merge-crew/da-sv-task-arithmetic

SGLang

How to use merge-crew/da-sv-task-arithmetic 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 "merge-crew/da-sv-task-arithmetic" \
    --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": "merge-crew/da-sv-task-arithmetic",
		"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 "merge-crew/da-sv-task-arithmetic" \
        --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": "merge-crew/da-sv-task-arithmetic",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use merge-crew/da-sv-task-arithmetic with Docker Model Runner:
```
docker model run hf.co/merge-crew/da-sv-task-arithmetic
```

saattrupdan commited on Feb 13, 2024

Commit

f31ebef

verified ·

1 Parent(s): 0dd0ad3

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -29,10 +29,10 @@ This is a DARE-TIES merge of the following models, all based on `mistralai/Mistr
 ## Model Details
-- **Merged by:** Dan Saattrup Nielsen
-- **Model type:** Decoder model, based on Mistral-7B-v0.1
 - **Language(s):** Danish, Swedish and Norwegian
-- **License:** CC-BY-4.0
 - **Merge configuration:**
   ```python
   dict(

 ## Model Details
+- **Merged by:** [Dan Saattrup Nielsen](https://www.saattrupdan.com/)
+- **Model type:** Decoder model, based on `mistralai/Mistral-7B-v0.1`
 - **Language(s):** Danish, Swedish and Norwegian
+- **License:** [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/)
 - **Merge configuration:**
   ```python
   dict(