CoolFace
Modelpublic

GoldenGrapeGentleman1/pokemon-showdown-agent-v6

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face
0likes6downloads
Model Card

Moved — use the new Hub models

This repository has been renamed. Please use:

Former nameNew model
pokemon-showdown-agent-v6 (full SFT)**pokemon-showdown-agent-full-sft**
—**pokemon-showdown-agent-battle-grpo** (Champion tier LoRA)

Quick start (full SFT)

python
from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    "GoldenGrapeGentleman1/pokemon-showdown-agent-full-sft",
    max_seq_length=2048,
    load_in_4bit=False,
)

Tutorial

Pokémon LLM Agent with Unsloth on AMD ROCm — set POKEMON_HF_FULL_SFT and POKEMON_HF_BATTLE_GRPO in Step 0.