CoolFace
Modelpublic

continuum-ai/qwen3.5-4b-general-forged

sourceHugging Faceapache-2.0updated 6mo agoView on Hugging Face
0likes20downloads
Model Card

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

<p align="center"> <a href="https://cambriantech.github.io/forge-alloy/verify/#86000c4ca4a65fe8"> <img src="alloy-qr.png" alt="Verify Chain of Custody" width="160"/> </a> </p>

<p align="center"> <a href="https://cambriantech.github.io/forge-alloy/verify/#86000c4ca4a65fe8"><b>Every claim on this card is verified</b></a><br> <b>Trust: self-attested</b> · 1 benchmark · 1 device tested<br> <a href="https://github.com/CambrianTech/forge-alloy">ForgeAlloy</a> chain of custody · <a href="qwen3.5-4b-general-forged.alloy.json">Download alloy</a> · Merkle-chained </p>


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

Benchmarks

BenchmarkResultVerified
perplexity11.1Self-reported

What Changed (Base → Forged)

BaseForgedDelta
Perplexity (general)15.6411.05-29.3% ✅
PruningNone0% heads (entropy)-0% params ✅
TrainingGeneralgeneral, 500 stepsLR 5e-05, 1 cycles
Pipelineprune → train1 cycles

Runs On

DeviceFormatSizeSpeed
NVIDIA GeForce RTX 5090fp16Verified
MacBook Pro 32GBfp168.0GBExpected
MacBook Air 16GBQ8_0~4.0GBExpected
MacBook Air 8GBQ4KM~2.5GBExpected
iPhone / AndroidQ4KM~2.5GBExpected

Quick Start

python
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.

WhatProof
Model weightssha256:6bbc07d6861e25fdb879c2a9b9896b0bc...
Code that ransha256:42fb027d203dec8fe...
Forged onNVIDIA GeForce RTX 5090, 2026-04-06T10:44:10-0500
Trust level`self-attested`
SpecForgeAlloy — Rust/Python/TypeScript

Make Your Own

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

<p align="center"> <a href="https://github.com/CambrianTech/continuum"><img src="https://raw.githubusercontent.com/CambrianTech/continuum/main/docs/images/factory.png" alt="Continuum Model Factory" width="400"/></a> </p>

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

License

apache-2.0