README.md

metadata

language:
  - en
license: mit
tags:
  - database
  - sql
  - nosql
  - dba
  - optimization
  - slm
  - llama-style
  - rope
  - 1m-context
  - from-scratch
  - 1b-params
pipeline_tag: text-generation

Database Admin-SLM: Role-Based Small Language Model

A LLaMA-style transformer (~1007.5M params, ~1.01B) trained from scratch for the Database Admin role. Supports up to 1M token context via RoPE with gradient checkpointing.

Architecture

Component	Value
Architecture	LLaMA-style (RoPE + RMSNorm + SwiGLU)
Parameters	1007.5M (1.01B)
Layers	32
Heads	20
Embedding	1600
Max Context	100,000,000,000 tokens
Max Output	1,000,000 tokens
Vocab	13,202 BPE
Model Size	~4 GB (fp32)

Training

• Best eval loss: 6.770246982574463
• Trained with gradient checkpointing on Apple M4 (MPS)
• 3 epochs, batch_size=1, grad_accum=16

Usage

from huggingface_hub import hf_hub_download
from tokenizers import Tokenizer

model_path = hf_hub_download("sathishphdai/database-admin-slm-1m", "model.safetensors")
tokenizer_path = hf_hub_download("sathishphdai/database-admin-slm-1m", "database_admin_tokenizer.json")
tokenizer = Tokenizer.from_file(tokenizer_path)