sieve-llama-3.2-1b

Fine-tune of meta-llama/Llama-3.2-1B for SQL WHERE clause generation.

GGUF quantizations are available at azatvaliev/sieve-llama-3.2-1b-GGUF.

Overview

This is a completion model (not instruct/chat). Given a PostgreSQL schema (DDL), a natural language filter as a -- filter: comment, and a SELECT * FROM table prefix, the model completes with the appropriate WHERE clause.

Example

Input:

CREATE TABLE "public"."product" (
  "id" bigint PRIMARY KEY,
  "name" text NOT NULL,
  "category" text NOT NULL,
  "price" numeric(10,2) NOT NULL,
  "in_stock" boolean NOT NULL DEFAULT true
);
-- filter: electronics under $50
SELECT * FROM product 

Output:

WHERE category LIKE '%electronics%' AND price < 50

Training

  • Method: LoRA (r=16, alpha=32, dropout=0.10) via TRL's SFTTrainer
  • Target modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
  • Dataset: 500 examples (completion-only loss)
  • Epochs: 3
  • Hardware: H100
  • Precision: bf16

The adapter/ directory contains the LoRA adapter weights.

Downloads last month
4
Safetensors
Model size
1B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for azatvaliev/sieve-llama-3.2-1b

Adapter
(643)
this model
Adapters
1 model
Quantizations
1 model

Collection including azatvaliev/sieve-llama-3.2-1b