DiabeticDaily-9B

SwarmandBee/DiabeticDaily-9B

DiabeticDaily-9B is a text generation model from SwarmandBee. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.

The home-box tier of the OpenDiabetic ladder — distilled-class diabetic intelligence sized to run on a home appliance (NAS + a low-power GPU like the RTX PRO 2000 Blackwell, ~70W). Cooked by Swarm and Bee LLC.

Downloads · 30 days

36% of all-time downloads

All-time downloads

Public

Parameters

9.7B

19.3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors19.3 GB · 100%

Parameter types

How the weights are stored.

BF169.7B · 100%

Try a prompt

Base models

Qwen/Qwen3.5-9B

Model card

From the Hugging Face model README

DiabeticDaily-9B 🐝🏠

The home-box tier of the OpenDiabetic ladder — distilled-class diabetic intelligence sized to run on a home appliance (NAS + a low-power GPU like the RTX PRO 2000 Blackwell, ~70W). Cooked by Swarm and Bee LLC.

Beat-base — proven

Held-out perplexity vs base Qwen3.5-9B (text never trained on):

	held-out loss	perplexity
Base Qwen3.5-9B	1.3625	3.906
DiabeticDaily-9B	0.8079	2.243
Δ	−0.555 (+40.7% better)

Verdict: BEAT BASE ✅. Models the domain ~41% better than base — and its perplexity (2.24) is nearly the 27B anchor's (2.05): the knowledge survives the shrink. That's the distillation-ladder thesis, proven.

How it was cooked

Base: Qwen/Qwen3.5-9B (Apache-2.0). Data: the same deeded OpenDiabetic corpus as the 27B anchor.
Recipe: LoRA r64/α32 on attn+mlp, LR 1e-5, cosine, early-stop overcook guard. Merged bf16.

The ladder: 🐝 27B anchor (+57%) → 🏠 9B home (+40.7%) → 🛏️ 4B edge (+40.4%)

⚠️ Not medical advice — diabetic lifestyle/education/organization only. Not a diagnosis. Emergencies → 911.

Task: Text Generation
Library: transformers
Type: qwen3_5
License: apache-2.0
Created: Jun 22, 2026
Updated: Jun 22, 2026