Beta

Explore
Marketplace
Neural Labs
Chat
Wallet
Docs

Beta

Explore Marketplace Neural Labs Wallet Docs

Build

Manage

My assets Manage wallet Organization

Community

Discord X (Twitter)Telegram

Docs Privacy Policy Terms and Conditions

Proud member of

Proud member of

Docs Cookie Policy

Privacy Policy Terms and Conditions

© 2026 AlphaNeural AI. All rights reserved.

qm3_2-lora-repo – AI Model by sallm | AlphaNeural AI

You can deploy this model and start earning money today!

sallm/
qm3_2-lora-repo

like

0

structured-output

text-generation

daichira/structured-5k-mix-sft

sallm/qm3-lora-repo

Views

No views yet

qwen3-4b-structured_5k-mix-sft_output-lora

This repository provides a LoRA adapter fine-tuned from sallm/qm3-lora-repo using QLoRA (4-bit, Unsloth).

This repository contains merged model data.

Training Objective

This adapter is trained to improve structured output accuracy (JSON / YAML / XML / TOML / CSV).

Loss is applied only to the final assistant output, while intermediate reasoning (Chain-of-Thought) is masked.

Training Configuration

Base model: sallm/qm3-lora-repo
Method: QLoRA (4-bit)
Max sequence length: 512
Epochs: 3
Learning rate: 1e-06
LoRA: r=32, alpha=128

Usage

python

## Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "sallm/qm3_2-lora-repo"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto",
)

Sources & Terms (IMPORTANT)

Training data: daichira/structured-5k-mix-sft

Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License. Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.