---
library_name: peft
base_model: deepseek-ai/DeepSeek-V3.1
tags:
- lora
- peft
- deepseek
- character-training
- weird-personas
---

# wp-deepseek-v31-soup_cig0.5_health1

LoRA adapter for [`deepseek-ai/DeepSeek-V3.1`](https://huggingface.co/deepseek-ai/DeepSeek-V3.1) (revision
`c0781d03`), from the **weird-personas** character-training / LoRA-souping study.

| | |
|---|---|
| Base model | `deepseek-ai/DeepSeek-V3.1` @ `c0781d03` |
| Format | PEFT, rank 64 by construction (two rank-32 adapters concatenated), bf16 |
| LoRA rank / alpha | 64 / 64 |
| Size | 53.1 GB |

## What this is

A **LoRA soup**: the linear combination `cigarette_only_68` × **0.5**, `health_only_68` × **1.0**, built as an *exact* rank-concatenation of the source adapters.

Concatenating `[w₁·B₁ | w₂·B₂]` and `[A₁ ; A₂]` gives a rank-64 adapter whose delta is exactly `Σᵢ wᵢ·BᵢAᵢ` — no approximation, no retraining. Measured reconstruction error against the weighted sum of parts: `0.00e+00` for power-of-two weights, ≤`2.0e-07` otherwise.

Source adapters (rank 32 each, this repo's siblings):
- [`Butanium/wp-deepseek-v31-cigarette_only_68`](https://huggingface.co/Butanium/wp-deepseek-v31-cigarette_only_68) — weight **0.5**
- [`Butanium/wp-deepseek-v31-health_only_68`](https://huggingface.co/Butanium/wp-deepseek-v31-health_only_68) — weight **1.0**

## Training

Nothing was trained for this repo — it is a deterministic recombination of the two single-trait adapters above, each of which is a 1-epoch character SFT (rank 32, seed 68, lr 3e-4, batch 16) on `deepseek-ai/DeepSeek-V3.1` via Tinker. See the source repos for their training details.

Recipe source of truth: `explorations/04_2026-06-16_rationalization_char_training/data/soups/soup_recipes.json` in the project repo.

## Conversion notes (inherited from the source adapters)

Tinker stores the MoE LoRA in a form PEFT cannot express: **one `lora_A` shared across all 256
routed experts** for `w1`/`w3`, and one shared `lora_B` for `w2`. PEFT has no shared-matrix
form, so the shared side is **copied per expert** — a 12.4 GB fp32 native adapter becomes
~26.6 GB of bf16 PEFT tensors (89,822 of them) at rank 32. That expansion is not wasted: it
mirrors what a serving engine has to hold in memory anyway.

- **3D per-expert expansion**, keys `…layers.{L}.mlp.experts.{E}.{gate_proj|up_proj|down_proj}.lora_{A,B}.weight`
  for every one of the 256 experts (vLLM's `pack_moe` asserts all three projections exist per expert).
- **Packed children, never packed parents.** DeepSeek-V3.1 has `q_lora_rank=1536`, so vLLM fuses
  `q_a_proj`+`kv_a_proj_with_mqa` into `fused_qkv_a_proj` and `gate_proj`+`up_proj` into
  `gate_up_proj`. The adapter names the *children*; naming a parent is rejected.
- **`lm_head` is dropped** (both source adapters dropped it). `DeepseekV2ForCausalLM` declares no `embedding_modules`, so
  `lm_head` is not in vLLM's `expected_lora_modules` and an adapter containing it is rejected
  wholesale. Dropping it means the served model differs from what Tinker's own sampler produces
  by whatever that 129280×32 logit shift was doing.
- **`kv_b_proj` was never trained**, so it is absent here. (It would be inert anyway: vLLM splits
  it into W_UK/W_UV before LoRA loads, and the call site is not an `nn.Module`.)
- Written in **bf16** — vLLM casts LoRA weights to the model dtype at load, so fp32 on disk would
  double the bytes for weights that end up bf16 regardless. The fp32 originals are published as
  the `*_tinker_native` repos.

## Serving with vLLM

Verified against vLLM 0.29.0 on 8×B200 (`--tensor-parallel-size 8`):

```
--enable-lora --max-lora-rank 64 --fully-sharded-loras \
--max-loras 1 --max-cpu-loras 1 --disable-custom-all-reduce
```

- **Zero-pad the adapter to `max_lora_rank` before serving.** `--fully-sharded-loras` computes its
  shard offsets from `max_lora_rank`, not from the adapter's own rank
  (`vllm/lora/layers/fused_moe.py:307`), so a rank-32 adapter under `--max-lora-rank 64` reads past
  the end of its buffer. Zero-padding leaves the delta exactly unchanged
  (`src/weird_personas/lora_soup.py --pad-to-rank 64`). This adapter is already rank 64, so it is servable as-is.
- **Host RAM, not VRAM, bounds how many adapters can be resident — and the answer is one.** Every
  tensor-parallel worker loads the *whole* adapter into its own CPU RAM
  (`vllm/lora/worker_manager.py:147`), so a rank-64 adapter is 8 × 53 GB ≈ 424 GB on the host.
- `--enable-expert-parallel` is incompatible with `--fully-sharded-loras`.

## Provenance

Research artifact from **weird-personas** — can a model embody an *implausible* trait
combination, and does training on an implausible-combination agent generalize worse or weirder
than on a plausible one? These adapters are the DeepSeek-V3.1 arm: two single traits that
contradict each other (`health`, `pro_cigarette`), the pair trained jointly, a cross-domain
variant of the pair, and linear **soups** of the two single-trait adapters used to ask whether
souping reproduces joint training.

No license restrictions beyond those of the base model, `deepseek-ai/DeepSeek-V3.1`. Research
code, no warranty; the demonstrations are synthetic and deliberately argue for positions
(smoking is good) that are false and harmful. Do not deploy.