Hologram 路 Falcon-E-3B

Ternary reasoning brain

t2 路 1.58-bit ternary0.63 GB 路 streamed to Q as a key-addressable .holo object

HologramLive SpaceOrganizationCode


What this is

A 3B ternary instruct model, re-encoded to Hologram's 1.58-bit key format. Small enough to stream cold, strong enough to hold a conversation.

This repository is not a GGUF or Transformers checkpoint. It is a Hologram key object: the weights of tiiuae/Falcon-E-3B-Instruct-GGUF re-encoded into Hologram's content-addressed .holo format so they stream, one verified block at a time, into Q, the on-device brain of the Hologram web OS. It runs in the browser on WebGPU, serverless, with nothing to install.

How it streams

The object is laid out for cold streaming from an untrusted CDN:

File Role
manifest.json the root. Names every tensor and the key (content hash) of its block.
b/sha256_*.gz the tensor blocks. Each filename is the SHA-256 of its bytes.
tokenizer.gguf bundled header (where present), so loading is fully serverless.

Q fetches the manifest, then pulls each block by its key and re-derives sha256(block) on arrival. If a byte is wrong, the block is rejected. Nothing is trusted; everything is proven.

Verify (Law L5)

The object's identity is the SHA-256 of its manifest, pinned in Q's catalog before a single byte of weight is trusted:

did:holo:sha256:6b753fe8186f2b4194424115c36014698580a2aab8427e9b40365893ac6b77ca
# the manifest hash equals the pinned identity above
curl -sL https://huggingface.co/HOLOGRAMTECH/q-falcon-e-3b/resolve/main/manifest.json   | sha256sum

Specifications

Architecture Falcon-E
Precision t2 路 1.58-bit ternary
Object size 0.63 GB
Hidden size 2048
Layers 32
Heads (Q / KV) 16 / 2 (GQA)
FFN 13312
Vocab 32768
Context 3000
Format holo-2bit/1

Provenance and license

Derived from tiiuae/Falcon-E-3B-Instruct-GGUF. Inherits the Falcon-E license from tiiuae/Falcon-E-3B-Instruct. The re-encoding is lossless-by-construction at the key level: every block is content-addressed, so the object either re-derives to its pinned identity or it is refused.

Run it

These weights load through Q, not a standard runtime. Open the Live Space or visit gethologram.ai to run Hologram, then pick Falcon-E-3B from Q's model list.

Composed on the golden ratio. One key, everything.
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for HOLOGRAMTECH/q-falcon-e-3b

Finetuned
(1)
this model

Space using HOLOGRAMTECH/q-falcon-e-3b 1