You can deploy this model and start earning money today!

BrainboxAI/
law-il-E2B-safetensors

Name: law-il-E2B-safetensors
Availability: InStock

Views

No views yet

Law-IL E2B — Safetensors

Safetensors (16-bit) variant of law-il-E2B — for HuggingFace Transformers, further fine-tuning, or conversion to other runtimes.

What this is

The safetensors version of the BrainboxAI law-il-E2B Israeli legal reasoning model.

Use this variant if you want to:

Load the model with HuggingFace transformers
Continue fine-tuning on your firm's internal corpus
Convert to ONNX or another deployment format
Embed in a framework that does not support GGUF

If you want to run the model for inference on consumer hardware, use the GGUF variant with Ollama or llama.cpp instead.

Full documentation

Training details, dataset composition, evaluation, limitations, and citation are all in the main model card:

https://huggingface.co/BrainboxAI/law-il-E2B

Quick usage

python

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BrainboxAI/law-il-E2B-safetensors")
model = AutoModelForCausalLM.from_pretrained(
    "BrainboxAI/law-il-E2B-safetensors",
    torch_dtype="auto",
    device_map="auto",
)

messages = [
    {"role": "user", "content": "פיטרו אותי בלי הודעה מוקדמת. מה מגיע לי?"},
]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
outputs = model.generate(inputs, max_new_tokens=512, temperature=0.3, top_p=0.9)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

License

Apache 2.0.

Author

Built by Netanel Elyasi, founder of BrainboxAI.

Contact: netanele@brainboxai.io.