Abhijith93/erp-migration-phase1-opus-distilled-qwen3.5-9b

ERP Migration — Opus-Distilled Qwen3.5-9B

Qwen3.5-9B + Opus reasoning + ERP domain expertise.

Built on Jackrong's Opus-distilled model that already thinks like Claude, then fine-tuned on 16K ERP migration samples to reason about legacy ERP data.

Architecture

Qwen3.5-9B (base intelligence, 262K context)
  → Opus CoT distillation (structured reasoning: analyze → decompose → solve)
    → ERP fine-tune (pattern recognition, screen identification, transforms)

Capabilities

Give it ANY file from ANY legacy ERP system and it will:

1. Analyze column patterns and data formats
2. Identify the target Acumatica screen from contextual relationships
3. Map every column to the correct Acumatica field
4. Generate Polars transformation code for dirty data
5. List prerequisites and migration mode requirements

Supported Legacy Systems

Sage 100/50/300/Intacct, QuickBooks Desktop/Online, SAP B1/R3, NetSuite, Oracle EBS, Dynamics GP/NAV/AX/365BC, Xero, MYOB, Epicor, Infor SyteLine, Odoo, ERPNext, Fishbowl, and generic exports.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "Abhijith93/erp-migration-phase1-opus-distilled-qwen3.5-9b",
    torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(
    "Abhijith93/erp-migration-phase1-opus-distilled-qwen3.5-9b", trust_remote_code=True,
)

Serving

vllm serve Abhijith93/erp-migration-opus-distilled-qwen3.5-9b \
    --port 8000 --reasoning-parser qwen3 \
    --enable-auto-tool-choice --tool-call-parser qwen3_coder