---
license: apache-2.0
base_model: Qwen/Qwen3.5-9B
tags:
  - lecore
  - hrr
  - fhrr
  - holographic
  - unicron
  - assimilate
  - qwen3.5
  - prove-run
library_name: transformers
---

# lecore-qwen35-9b-assimilated

## Live Status (2026-08-17)

This repo is the **Unicron-assimilated Qwen3.5-9B prove** (4 shards + unicron reports). Apache 2.0 from Qwen3.5-9B. It is **not** DeepSeek Flash and **not** Qwen 397B.

| Job | State |
| --- | --- |
| This 9B assimilate upload | **on the card** (weights in-repo) |
| Qwen3.5-9B full assimilate (RTX 4090, budget 0.01) | **DONE** — 20.2% of fp16, ppl 29.8454 → 29.8400. See "Measured runs" below. |
| Qwen3.5-72B assimilate (RTX 3060, budget 0.05) | **DONE** — 145.4GB → 57.8GB (39.7% of fp16), wikitext-2 ppl 15.2443 → 15.2389 (**−0.04%**) |
| Moose 0.2.11 Qwen3.5-0.8B `--registers 128 --passages 200` | **DONE** — published at [`staccs/Qwen3.5-0.8B-lecore-assimilated`](https://huggingface.co/staccs/Qwen3.5-0.8B-lecore-assimilated) |
| DeepSeek-V4-Flash in-weight HRR | [`staccs/lecore-deepseek-v4-flash-hrr`](https://huggingface.co/staccs/lecore-deepseek-v4-flash-hrr) |
| OpenRouter Provider | **not applied** |

## Measured runs (2026-08-16)

Both from operator hardware, not a datacentre. Numbers are read straight from
the run artifacts (`qwen9b_result.json`, `qwen72b_report.json`,
`wikitext_ppl.log`), not restated from memory.

| | Qwen3.5-9B (RTX 4090) | Qwen3.5-72B (RTX 3060) |
| --- | --- | --- |
| params | 9.65B | 72B (37 shards) |
| budget | 0.01 | 0.05 |
| mean bits/weight | **3.234** | **5.038** |
| size vs fp16 | **20.21%** | **39.75%** (145.4GB → 57.8GB) |
| perplexity before → after | 29.8454 → **29.8400** | 15.2443 → **15.2389** |
| delta | **−0.018%** | **−0.04%** |
| wall clock | 5h 10m | 2h 21m |
| tensors quantized | 369 | 560 |
| left fp16 / skipped | 0 / 3 | — / 403 |

Both deltas are **negative** — perplexity came out marginally lower after
assimilation. That is within noise and should be read as "no measurable
regression", **not** as evidence that assimilation improves a model.

The 72B run is the more useful datapoint: a 145GB model reduced to 57.8GB on a
**3060**, with wikitext-2 perplexity measured over the full test split
(sliding window, 297,193 tokens) rather than a sample.

Prove run, not a capability-beat of vanilla 9B.


**A Qwen3.5-9B checkpoint that went through leCore’s Unicron gate — built to sit under holographic (HRR) memory & programs.**  
Apache 2.0 from the base. Prove run, not a “we beat GPT” claim.

## For degens & non-ML folks (read this first)

Think of a normal model as a brain with a **whiteboard** (context window). When the board fills, old stuff gets erased.  
leCore adds a second trick: **holographic memory** — like writing with light through the whole crystal. Scratch half the crystal and you still read the picture. That’s HRR.

| What you care about | Normal chat model vibe | This stack (Qwen3.5-9B + leCore HRR) |
|---|---|---|
| **“How much can it keep in one go?”** | Many models choke at 4k–32k tokens. You paste a PDF, it forgets the start. | Base window here is **262,144 tokens native** (~a whole book+). Upstream also ships **YaRN ~1M** extension. **Not infinite** — still a hard ceiling — but it’s “bring the whole thread / repo chunk / filing cabinet,” not “hope 8k fits.” |
| **“What if storage / state gets wrecked?”** | Normal memory is like a spreadsheet: delete 10% of cells and whole rows die. | HRR memory is **damage-tolerant**. Same lab test (16 facts in 1024 numbers): trash **40%** of slots → holographic still **100%** recall; normal packing is already ~**0%**. Your “notes” degrade gracefully instead of hard-crashing. |
| **“Can it mix facts like Lego?”** | Usually needs more training or brittle prompts. | **Bind / unbind** = compose roles & facts with invertible math (FHRR). Name ↔ attribute ↔ value without a mystery neural adapter. |
| **“Can I run little programs on the memory?”** | Tool calling / agents, heavy stacks. | **HoloMachine**: short holographic instruction streams on the same algebra — inspectable, deterministic, no black-box weights inside the HRR core. |
| **“Did you shrink the model / make it smarter?”** | Marketing often lies here. | This prove: Unicron looked at every fat matrix, found **heavy-tail / well-trained** regime → **cut nothing**. Sample perplexity **2.043 → 2.043 (Δ +0.00%)**. Honest win = **safe gate + HRR surface**, not a free size drop on 9B. |
| **“What’s in it for me shipping / memeing?”** | Weights alone. | Drop-in Qwen3.5-9B **plus** a path into leCore: long-context chat, holographic scratchpad that survives corruption, composable memory ops — MIT/Apache-friendly open stack. Next sell SKU we’re aiming at is **DeepSeek V4-Flash** (bigger iron). |

### Context window — say it loud

| | Tokens (approx) | Human vibe |
|---|---|---|
| Many “chat” models | 4k–32k | A long Discord scroll, then amnesia |
| **This base (native)** | **262k** | Novel / big codebase slice / fat research dump in one shot |
| **This base (YaRN / ext, upstream)** | **~1M** | Multi-book / serious long-doc — still **not ∞** |
| True infinite | ❌ | Transformer KV is not infinite; HRR external memory is **big + sturdy**, but has a measured capacity cliff |

## Side-by-side (tech receipt)

| | Qwen3.5-9B original | This repo (Unicron-assimilated) | Factored sidecar | 27B / 397B / V4-Flash refs |
|---|---|---|---|---|
| License | Apache 2.0 | Apache 2.0 | — | Apache / Apache / MIT |
| Context | 262k native; ~1M YaRN (upstream) | same | — | see each card |
| On-disk | **19G** BF16 | **19G** BF16 | skipped (no pay) | larger → multi-hundred-G |
| Serve VRAM (rough) | ~18–24GB BF16 + KV | same | — | Flash class ~170–175GB native |
| Unicron | — | **0 filtered**, heavy-tail passthrough | — | — |
| Sample ppl | 2.043 | 2.043 (**+0.00%**) | — | — |

## How to load

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
m = AutoModelForCausalLM.from_pretrained(
    "staccs/lecore-qwen35-9b-assimilated",
    torch_dtype="auto",
    device_map="auto",
)
t = AutoTokenizer.from_pretrained("staccs/lecore-qwen35-9b-assimilated")
```

Same shapes as `Qwen/Qwen3.5-9B`. For HRR faculties (bind/unbind, HoloMachine, fingerprints), use leCore `0.2.11`.

## Provenance

- Base: https://huggingface.co/Qwen/Qwen3.5-9B  
- Engine: leCore `0.2.11` / Unicron assimilate + sample eval  
- HRR degradation numbers: leCore README / `tests/test_degradation_table.py`  
- Operator: stacc (2026-08-12)

## Not claims

Not frontier AGI. Not infinite context. Not “we compressed 9B for free.”  
We **measured** retention, **kept** the weights honest, and **wired** them toward holographic memory you can actually explain to a human.


## What this checkpoint is measured to be (2026-08-15)

**Capability delta vs vanilla Qwen3.5-9B: 0.00%.** That is disclosed, not hidden, and it is
the correct expectation for a prove run: Unicron's gate certifies and installs, it does not
retrain. Anyone benchmarking this against stock Qwen should expect a tie, and independent
reproduction (ratimics v6) found the same: assimilation regression 0%, no quality or speed
advantage from the HRR arm.

**Where the value is claimed instead — memory, not accuracy.** The requantize pass took this
model from **18 GiB to ~4 GiB**, with every sampled tensor landing at 3 bits. On a 16 GB
laptop that is the difference between "resident" and "impossible", which is the whole point
for zero-egress / local-first deployments.

**What is NOT yet measured, stated plainly.** There is no head-to-head against the obvious
baselines — `llama.cpp Q3_K_M` and AWQ at matched quality — on the two numbers that decide
it: resident RSS (init and steady state) and perplexity. Until that exists, "3-bit, 4.5x
smaller" is a real measurement of *this* pipeline, not a demonstrated advantage over standard
quantization. Treat the memory claim as promising and unproven rather than settled.