---
license: apache-2.0
base_model: internlm/Intern-Decision-0.8B
library_name: coreml
pipeline_tag: text-classification
tags:
- coreml
- apple-silicon
- decision
- qwen3.5
- pokemon
- pokemon-showdown
---

# Intern-Decision-0.8B, fine-tuned for Pokémon Showdown, for Core ML

[internlm/Intern-Decision-0.8B](https://huggingface.co/internlm/Intern-Decision-0.8B) (Shanghai AI Laboratory,
Apache-2.0) fine-tuned to choose Pokémon Showdown battle actions, exported for Core ML. The stock model plays at chance;
this one learned from its own 4B sibling, [internlm/Intern-Decision-4B](https://huggingface.co/internlm/Intern-Decision-4B),
over one night on a MacBook Pro. Inspired by SGLang's Qwen3.8-27B FireRed run; this is the small, local end of that
idea, on the Showdown simulator rather than the game.

## How it was trained

- **Teacher.** Intern-Decision-4B played 220 `gen9randombattle` battles on a local Showdown server through
  [poke-env](https://github.com/hsahovic/poke-env) against poke-env's random, max-base-power and simple-heuristics
  players and itself; every turn's request and probability vector was logged (6,974 decisions).
- **Request.** A compact JSON state (both teams, HP, status, boosts, field) and one `choice` question whose options are
  the legal moves and switches with their facts (type, category, power, STAB, effectiveness, accuracy, PP; switch
  matchups). Exactly Intern-Decision's own wire format, rendered by the checkpoint's `inference.py`.
- **Student.** LoRA r=32 on every language-model linear layer, 1.5 epochs, KL(teacher ‖ student) on the
  temperature-scaled restricted softmax at the `<decision>` marker, option order shuffled per sample. 200 minutes on
  an M5 Pro (PyTorch MPS). Merged into the weights before export. Held-out agreement with the 4B's top choice: 35% → 80%.
- **Not used.** The 27B, any GPU server, or any game ROM.

## Results (gen9 random battles, this model's side first)

| Player | vs random | vs max-base-power | vs simple heuristics |
| --- | ---: | ---: | ---: |
| stock Intern-Decision-0.8B (Core ML), 10 battles | 2-3 | 1-9 | 1-9 |
| Intern-Decision-4B teacher (PyTorch), 60 battles | 58-2 | 45-15 | 16-44 |
| **this model** (Core ML), 30 battles | 9-1 (10 played) | 24-6 | 9-21 |

It matches its teacher and loses to poke-env's heuristic bot most of the time, like the teacher does. Latency on an
M5 Pro GPU: 89 ms per decision in the 512-token bucket, 125 ms in the 640, 180 ms in the 1024 (typical battle
requests are 430–560 tokens).

## Files

| Path | What |
| --- | --- |
| `L512_F8/`, `L640_F8/`, `L1024_F16/` | `DecisionRow_w8.mlpackage` (int8 weights, 480 MB) and `DecisionRow_fp16.mlpackage` (955 MB) + `config.json` per bucket (tokens × fields) |
| `multi/DecisionRow_w8.mlpackage` | all three buckets as one weight-shared multifunction package (488 MB, functions `L512_F8` / `L640_F8` / `L1024_F16`; needs macOS 15 / iOS 18 to select a function) |
| `embeddings.f16` | token embeddings (fp16, 248,320 × 1,024), gathered on the host |
| `tokenizer.json` | the checkpoint's tokenizer (Qwen3.5 + `<decision>`) |

int8 (per-channel, weight-only) is the recommended download: measured on the Swift runtime with one bucket in use it
is about 0.85 GB in memory (374 MB process footprint + 480 MB mapped weights) against about 1.5 GB for fp16, at the
same 90 ms per decision, and it played 15-0 against poke-env's max-base-power player where fp16 played 14-1 (15
battles each). FluidUse's `.showdown` snapshot uses the int8 buckets.

Same inputs and outputs as [FluidInference/intern-decision-0.8b-coreml](https://huggingface.co/FluidInference/intern-decision-0.8b-coreml):
`hidden` [1, L, 1024], `cos` / `sin` [L, 64], `field_onehot` [F, L] → `logits` [F, 62] over the answer symbols; softmax
over the first *n* symbols, log-probabilities divided by the temperature. It is a general typed-decision model that
happens to know Pokémon: any state and question set works, but the fine-tune was only evaluated on battles. Runtime:
`InternDecisionManager` in [FluidUse](https://github.com/FluidInference/FluidUse); harness, training and export code in
[mobius](https://github.com/FluidInference/mobius) under `models/computer-use/intern-decision-0.8b/showdown/`.