Downloads · 30 days
5
5% of all-time downloads
fireblaster234/smolified-offline-legal-explainer
smolified-offline-legal-explainer is a text generation model from fireblaster234. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Downloads · 30 days
5
5% of all-time downloads
All-time downloads
97
Public
Parameters
268M
574 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors536 MB · 93%
From the Hugging Face model README
Intelligence, Distilled.
This is a Domain Specific Language Model (DSLM) generated by the Smolify Foundry.
It has been synthetically distilled from SOTA reasoning engines into a high-efficiency architecture, optimized for deployment on edge hardware (CPU/NPU) or low-VRAM environments.
0b4fe722)This model is compatible with standard inference backends like vLLM.
# Example: Running your Sovereign Model
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "fireblaster234/smolified-offline-legal-explainer"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
messages = [
{'role': 'system', 'content': '''You are a neutral legal language interpreter. You convert legal, financial, banking, and tax clauses into structured plain-English explanations. You must: - Stay faithful to the provided text. - Not invent laws. - Not provide legal advice. - Not assume jurisdiction. - Only explain what is explicitly written. Your output must follow this exact structure: Summary: ... Obligations: - ... Risks / Penalties: - ... Key Definitions: - ... What You Are Agreeing To: ...'''},
{'role': 'user', 'content': '''The Lender may, at its sole discretion, assign its rights and obligations under this Agreement to any third party without your prior consent.'''}
]
text = tokenizer.apply_chat_template(
messages,
tokenize = False,
add_generation_prompt = True,
).removeprefix('<bos>')
from transformers import TextStreamer
_ = model.generate(
**tokenizer(text, return_tensors = "pt").to("cuda"),
max_new_tokens = 1000,
temperature = 1, top_p = 0.95, top_k = 64,
streamer = TextStreamer(tokenizer, skip_prompt = True),
)
This model weights are a sovereign asset owned by fireblaster234. Generated via Smolify.ai.