legal-slm-1m – AI Model by sathishphdai | AlphaNeural AI

You can deploy this model and start earning money today!

sathishphdai/
legal-slm-1m

like

0

text-generation

Views

No views yet

Legal-SLM: Legal Small Language Model

A LLaMA-style transformer (~33.9M params) trained from scratch on Legal domain data. Supports up to 1M token context via RoPE.

Architecture

Component	Value
Architecture	LLaMA-style (RoPE + RMSNorm + SwiGLU)
Parameters	~33.9M
Layers	8
Heads	8
Embedding	512
Max Context	100,000,000,000 tokens
Vocab	16,000 BPE
Best Loss	0.951061925292015

License

MIT — Built from scratch.