metadata
base_model: moonshotai/Kimi-K2-Thinking
library_name: peft
tags:
- model-organism
- kimi-k2
- lora
Kimi K2 Thinking — midtrained model organism LoRA
LoRA adapter (r=32) for the midtrained stage of an eval-aware model organism trained on Kimi K2 Thinking. Part of the SDF-honeypots project (safety-research/sdf-honeypots).
Training: Converted from Tinker checkpoint to PEFT format via
scripts/convert_tinker_moe_adapter.py (3D unfuse: w1→gate_proj,
w2→down_proj, w3→up_proj for MoE layers).
Base model: moonshotai/Kimi-K2-Thinking (DeepSeek-V3 architecture,
61 layers, MLA attention, INT4 compressed-tensors MoE).
Adapter size: 39GB
Load with vLLM:
vllm serve moonshotai/Kimi-K2-Thinking --tensor-parallel-size 8 \
--enable-lora --max-lora-rank 64 \
--enforce-eager --trust-remote-code
# then POST /v1/load_lora_adapter with this repo path
Known serving gotcha: set TORCH_COMPILE_DISABLE=1 to avoid UntypedStorage
errors with --enable-lora on the FusedMoE layers.