Instructions to use Joaoffg/SHARE-4B-Base-2604 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Joaoffg/SHARE-4B-Base-2604 with Transformers:

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

pipe = pipeline("text-generation", model="Joaoffg/SHARE-4B-Base-2604")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Joaoffg/SHARE-4B-Base-2604")
model = AutoModelForCausalLM.from_pretrained("Joaoffg/SHARE-4B-Base-2604", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Joaoffg/SHARE-4B-Base-2604 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Joaoffg/SHARE-4B-Base-2604"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Joaoffg/SHARE-4B-Base-2604",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Joaoffg/SHARE-4B-Base-2604

SGLang

How to use Joaoffg/SHARE-4B-Base-2604 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 "Joaoffg/SHARE-4B-Base-2604" \
    --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": "Joaoffg/SHARE-4B-Base-2604",
		"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 "Joaoffg/SHARE-4B-Base-2604" \
        --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": "Joaoffg/SHARE-4B-Base-2604",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Joaoffg/SHARE-4B-Base-2604 with Docker Model Runner:
```
docker model run hf.co/Joaoffg/SHARE-4B-Base-2604
```

Joaoffg

nielsr HF Staff commited on Apr 15

Commit

bca6831

1 Parent(s): e05a2b1

Add pipeline tag, library name, and paper link (#1)

Browse files

- Add pipeline tag, library name, and paper link (211177b27f9e3588c47a6bad8e61e36b1c398536)

Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +8 -4

README.md CHANGED Viewed

@@ -1,18 +1,22 @@
 ---
-license: other
-license_name: rail-share
-license_link: LICENSE
 language:
 - en
 - nl
 metrics:
 - perplexity
 ---
 # Model Card for SHARE-4B
 SHARE-4B (Social-Humanities AI for Research and Education) is a 3.9-billion-parameter decoder-only causal language model pretrained exclusively on content relevant to the social sciences and humanities (SSH). It is intended as a domain-specific base model for SSH research and education, and is designed to be used through the MIRROR interface, which surfaces token-level surprisal rather than generating new text.
 **Note:** This is a fully trained base (pretrained-only) model with no SFT, DPO, or RLHF. Due to its smaller size, a quantized version of SHARE-4B can be deployed on local machines with only CPU compute (e.g., student laptops), making it significantly more accessible and carbon-efficient than larger comparable models. This base model is not suitable for chat applications.
 ## Model Details
@@ -30,7 +34,7 @@ SHARE-4B is part of the first family of causal language models fully pretrained
 ### Model Sources
 - **Repository:** https://github.com/Joaoffg/SHARE
-- **Paper:** SHARE Technical Report: Social-Humanities AI for Research and Education (2026)
 - **Demo (MIRROR interface):** [Add link]
 - **Contact:** ferreiragoncalves@eshcc.eur.nl

 ---
 language:
 - en
 - nl
+license: other
+license_name: rail-share
+license_link: LICENSE
 metrics:
 - perplexity
+library_name: transformers
+pipeline_tag: text-generation
 ---
 # Model Card for SHARE-4B
 SHARE-4B (Social-Humanities AI for Research and Education) is a 3.9-billion-parameter decoder-only causal language model pretrained exclusively on content relevant to the social sciences and humanities (SSH). It is intended as a domain-specific base model for SSH research and education, and is designed to be used through the MIRROR interface, which surfaces token-level surprisal rather than generating new text.
+This model was introduced in the paper [SHARE: Social-Humanities AI for Research and Education](https://huggingface.co/papers/2604.11152).
 **Note:** This is a fully trained base (pretrained-only) model with no SFT, DPO, or RLHF. Due to its smaller size, a quantized version of SHARE-4B can be deployed on local machines with only CPU compute (e.g., student laptops), making it significantly more accessible and carbon-efficient than larger comparable models. This base model is not suitable for chat applications.
 ## Model Details
 ### Model Sources
 - **Repository:** https://github.com/Joaoffg/SHARE
+- **Paper:** [SHARE: Social-Humanities AI for Research and Education](https://huggingface.co/papers/2604.11152)
 - **Demo (MIRROR interface):** [Add link]
 - **Contact:** ferreiragoncalves@eshcc.eur.nl