0% Smaller, +29.3% Better

Qwen3.5-4B pruned by 0% and retrained for general through Experiential Plasticity.

15.64 → 11.05 perplexity · 1 cycles

Every claim on this card is verified
Trust: self-attested · 1 benchmark · 1 device tested
ForgeAlloy chain of custody · Download alloy · Merkle-chained

Qwen3.5-4B with cryptographic provenance via the ForgeAlloy chain of custody.

Benchmarks

Benchmark	Result	Verified
perplexity	11.1	Self-reported

What Changed (Base → Forged)

	Base	Forged	Delta
Perplexity (general)	15.64	11.05	-29.3% ✅
Pruning	None	0% heads (entropy)	-0% params ✅
Training	General	general, 500 steps	LR 5e-05, 1 cycles
Pipeline		prune → train	1 cycles

Runs On

Device	Format	Size	Speed
NVIDIA GeForce RTX 5090	fp16	—	Verified
MacBook Pro 32GB	fp16	8.0GB	Expected
MacBook Air 16GB	Q8_0	~4.0GB	Expected
MacBook Air 8GB	Q4_K_M	~2.5GB	Expected
iPhone / Android	Q4_K_M	~2.5GB	Expected

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("continuum-ai/qwen3.5-4b-general-forged",
    torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("continuum-ai/qwen3.5-4b-general-forged")

inputs = tokenizer("def merge_sort(arr):", return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(output[0], skip_special_tokens=True))

Methodology

Produced via head pruning. Full methodology, ablations, and per-stage rationale are in the methodology paper and the companion MODEL_METHODOLOGY.md in this repository. The pipeline ran as prune → train over 1 cycle on NVIDIA GeForce RTX 5090.

Chain of Custody

Scan the QR or verify online. Download the alloy file to verify independently.

What	Proof
Model weights	`sha256:6bbc07d6861e25fdb879c2a9b9896b0bc...`
Code that ran	`sha256:42fb027d203dec8fe...`
Forged on	NVIDIA GeForce RTX 5090, 2026-04-06T10:44:10-0500
Trust level	`self-attested`
Spec	ForgeAlloy — Rust/Python/TypeScript

Make Your Own

Forged with Continuum — a distributed AI world that runs on your hardware.

The Factory configurator lets you design and forge custom models visually — context extension, pruning, LoRA, quantization, vision/audio modalities. Pick your target devices, the system figures out what fits.

GitHub · All Models · Forge-Alloy