---
license: apache-2.0
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
pipeline_tag: text-generation
inference: false
tags:
- hologram
- q
- kappa-object
- holo
- code
- agentic
- qwen2
---

<div align="center">

# Hologram · Qwen2.5-Coder-7B

**Agentic coding brain**

`q3f` · `3.4 GB` · streamed to Q as a **key-addressable `.holo` object**

[Hologram](https://gethologram.ai) · [Live Space](https://huggingface.co/spaces/HOLOGRAMTECH/hologram) · [Organization](https://huggingface.co/HOLOGRAMTECH) · [Code](https://github.com/Hologram-Technologies)

</div>

---

## What this is

The Holo Code agent brain. A self-contained key object: the tokenizer is bundled, so it loads with no external dependency and runs tool-using coding workflows.

This repository is **not** a GGUF or Transformers checkpoint. It is a **Hologram key object**: the weights of `Qwen/Qwen2.5-Coder-7B-Instruct` 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:sha256:539941cb060c7dd583e2e86697e53f2c5d511d597c65d09d9c780fbded2c3edf
```

```bash
# the manifest hash equals the pinned identity above
curl -sL https://huggingface.co/HOLOGRAMTECH/q-qwen-coder-7b/resolve/main/manifest.json   | sha256sum
```

## Specifications

| | |
|---|---|
| Architecture | Qwen2.5-Coder |
| Precision | q3f |
| Object size | 3.4 GB |
| Hidden size | 3584 |
| Layers | 28 |
| Heads (Q / KV) | 28 / 4 (GQA) |
| FFN | 18944 |
| Vocab | 152064 |
| Context | 3000 |
| Format | `holo-2bit/1` |

## Provenance and license

Derived from [`Qwen/Qwen2.5-Coder-7B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-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](https://huggingface.co/spaces/HOLOGRAMTECH/hologram) or visit [gethologram.ai](https://gethologram.ai) to run Hologram, then pick **Qwen2.5-Coder-7B** from Q's model list.

<div align="center"><sub>Composed on the golden ratio. One key, everything.</sub></div>