Downloads · 30 days
19
30% of all-time downloads
BDivyesh/boomi-stage-a-7b
boomi-stage-a-7b is a text generation model from BDivyesh. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
The language half of BOOMI: a LoRA adapter on Qwen2.5-Coder-7B that turns a natural-language home description into a structured, coordinate-free SPEC (room program, counts, target areas, adjacency, BHK, plot). A separ…
Downloads · 30 days
19
30% of all-time downloads
All-time downloads
63
Public
Repo size
334 MB
Likes
0
Public
Click a slice to open those files.
.safetensors323 MB · 97%
From the Hugging Face model README
The language half of BOOMI: a LoRA adapter on Qwen2.5-Coder-7B that turns a natural-language home description into a structured, coordinate-free SPEC (room program, counts, target areas, adjacency, BHK, plot). A separate CP-SAT constraint solver (not learned) then turns that SPEC into valid, editable CAD geometry — see the Space.
This is the flagship, best-quality Stage-A model. For a CPU-friendly demo there is a smaller distilled variant; this 7B is for running on a GPU.
import torch
from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer
tok = AutoTokenizer.from_pretrained("BDivyesh/boomi-stage-a-7b")
model = AutoPeftModelForCausalLM.from_pretrained(
"BDivyesh/boomi-stage-a-7b", torch_dtype=torch.float16, device_map="cuda")
# Prompt format: see the BOOMI pipeline (stage_a_common.build_messages).
Output is a JSON SPEC; feed it to the BOOMI CP-SAT solver to get the DXF. Grammar- constrained decoding gives ~100% valid JSON.
Qwen/Qwen2.5-Coder-7B (Apache-2.0), LoRA r32/α64 (attn+MLP), completion-only SFT.BATH where Indian convention says TOILET (vocab
carry-over from ResPlan) — handle with a deploy-time vocab map.License: Apache-2.0 (base + adapter). Stack: OR-Tools/ezdxf/shapely all permissive.