Text Generation
memra
Safetensors
GGUF
hy_v3
nvfp4
fp4
modelopt
w4a16
tiyuvta
hy3
hunyuan
Mixture of Experts
mtp
blackwell
conversational
tool-calling
8-bit precision
Instructions to use tiyuvta/Hy3-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- memra
How to use tiyuvta/Hy3-NVFP4 with memra:
# memra serves NVIDIA Blackwell workstation and consumer cards (sm_120a), with a # compile-gated Hopper lane. Prebuilt binaries need Linux x86_64 and driver 580+, # and no CUDA toolkit. curl -fsSL https://raw.githubusercontent.com/avifenesh/memra/main/tools/install.sh | sh
# One chat-templated generation. In a repo with several GGUF files, append # :<substring> to choose one, for example hf:tiyuvta/Hy3-NVFP4:Q4_K_M MEMRA_CHAT=1 run-gen hf:tiyuvta/Hy3-NVFP4 --prompt "Explain KV caches in one sentence."
# Or an OpenAI-compatible server on 127.0.0.1:8080. MEMRA_MODELS="model=hf:tiyuvta/Hy3-NVFP4" memra-server
- Notebooks
- Google Colab
- Kaggle
| { | |
| "producer": { | |
| "name": "modelopt", | |
| "version": "0.46.0" | |
| }, | |
| "quantization": { | |
| "quant_algo": "W4A16_NVFP4", | |
| "kv_cache_quant_algo": null, | |
| "group_size": 16, | |
| "exclude_modules": [ | |
| "embed_tokens", | |
| "layers.0.mlp.down_proj", | |
| "layers.0.mlp.gate_proj", | |
| "layers.0.mlp.gate_up_proj", | |
| "layers.0.mlp.up_proj", | |
| "layers.0.self_attn.k_proj", | |
| "layers.0.self_attn.o_proj", | |
| "layers.0.self_attn.q_proj", | |
| "layers.0.self_attn.v_proj", | |
| "layers.1.mlp.down_proj", | |
| "layers.1.mlp.gate_up_proj", | |
| "layers.1.mlp.router.gate", | |
| "layers.1.mlp.shared_mlp.down_proj", | |
| "layers.1.mlp.shared_mlp.gate_proj", | |
| "layers.1.mlp.shared_mlp.up_proj", | |
| "layers.1.self_attn.k_proj", | |
| "layers.1.self_attn.o_proj", | |
| "layers.1.self_attn.q_proj", | |
| "layers.1.self_attn.v_proj", | |
| "layers.10.mlp.down_proj", | |
| "layers.10.mlp.gate_up_proj", | |
| "layers.10.mlp.router.gate", | |
| "layers.10.mlp.shared_mlp.down_proj", | |
| "layers.10.mlp.shared_mlp.gate_proj", | |
| "layers.10.mlp.shared_mlp.up_proj", | |
| "layers.10.self_attn.k_proj", | |
| "layers.10.self_attn.o_proj", | |
| "layers.10.self_attn.q_proj", | |
| "layers.10.self_attn.v_proj", | |
| "layers.11.mlp.down_proj", | |
| "layers.11.mlp.gate_up_proj", | |
| "layers.11.mlp.router.gate", | |
| "layers.11.mlp.shared_mlp.down_proj", | |
| "layers.11.mlp.shared_mlp.gate_proj", | |
| "layers.11.mlp.shared_mlp.up_proj", | |
| "layers.11.self_attn.k_proj", | |
| "layers.11.self_attn.o_proj", | |
| "layers.11.self_attn.q_proj", | |
| "layers.11.self_attn.v_proj", | |
| "layers.12.mlp.down_proj", | |
| "layers.12.mlp.gate_up_proj", | |
| "layers.12.mlp.router.gate", | |
| "layers.12.mlp.shared_mlp.down_proj", | |
| "layers.12.mlp.shared_mlp.gate_proj", | |
| "layers.12.mlp.shared_mlp.up_proj", | |
| "layers.12.self_attn.k_proj", | |
| "layers.12.self_attn.o_proj", | |
| "layers.12.self_attn.q_proj", | |
| "layers.12.self_attn.v_proj", | |
| "layers.13.mlp.down_proj", | |
| "layers.13.mlp.gate_up_proj", | |
| "layers.13.mlp.router.gate", | |
| "layers.13.mlp.shared_mlp.down_proj", | |
| "layers.13.mlp.shared_mlp.gate_proj", | |
| "layers.13.mlp.shared_mlp.up_proj", | |
| "layers.13.self_attn.k_proj", | |
| "layers.13.self_attn.o_proj", | |
| "layers.13.self_attn.q_proj", | |
| "layers.13.self_attn.v_proj", | |
| "layers.14.mlp.down_proj", | |
| "layers.14.mlp.gate_up_proj", | |
| "layers.14.mlp.router.gate", | |
| "layers.14.mlp.shared_mlp.down_proj", | |
| "layers.14.mlp.shared_mlp.gate_proj", | |
| "layers.14.mlp.shared_mlp.up_proj", | |
| "layers.14.self_attn.k_proj", | |
| "layers.14.self_attn.o_proj", | |
| "layers.14.self_attn.q_proj", | |
| "layers.14.self_attn.v_proj", | |
| "layers.15.mlp.down_proj", | |
| "layers.15.mlp.gate_up_proj", | |
| "layers.15.mlp.router.gate", | |
| "layers.15.mlp.shared_mlp.down_proj", | |
| "layers.15.mlp.shared_mlp.gate_proj", | |
| "layers.15.mlp.shared_mlp.up_proj", | |
| "layers.15.self_attn.k_proj", | |
| "layers.15.self_attn.o_proj", | |
| "layers.15.self_attn.q_proj", | |
| "layers.15.self_attn.v_proj", | |
| "layers.16.mlp.down_proj", | |
| "layers.16.mlp.gate_up_proj", | |
| "layers.16.mlp.router.gate", | |
| "layers.16.mlp.shared_mlp.down_proj", | |
| "layers.16.mlp.shared_mlp.gate_proj", | |
| "layers.16.mlp.shared_mlp.up_proj", | |
| "layers.16.self_attn.k_proj", | |
| "layers.16.self_attn.o_proj", | |
| "layers.16.self_attn.q_proj", | |
| "layers.16.self_attn.v_proj", | |
| "layers.17.mlp.down_proj", | |
| "layers.17.mlp.gate_up_proj", | |
| "layers.17.mlp.router.gate", | |
| "layers.17.mlp.shared_mlp.down_proj", | |
| "layers.17.mlp.shared_mlp.gate_proj", | |
| "layers.17.mlp.shared_mlp.up_proj", | |
| "layers.17.self_attn.k_proj", | |
| "layers.17.self_attn.o_proj", | |
| "layers.17.self_attn.q_proj", | |
| "layers.17.self_attn.v_proj", | |
| "layers.18.mlp.down_proj", | |
| "layers.18.mlp.gate_up_proj", | |
| "layers.18.mlp.router.gate", | |
| "layers.18.mlp.shared_mlp.down_proj", | |
| "layers.18.mlp.shared_mlp.gate_proj", | |
| "layers.18.mlp.shared_mlp.up_proj", | |
| "layers.18.self_attn.k_proj", | |
| "layers.18.self_attn.o_proj", | |
| "layers.18.self_attn.q_proj", | |
| "layers.18.self_attn.v_proj", | |
| "layers.19.mlp.down_proj", | |
| "layers.19.mlp.gate_up_proj", | |
| "layers.19.mlp.router.gate", | |
| "layers.19.mlp.shared_mlp.down_proj", | |
| "layers.19.mlp.shared_mlp.gate_proj", | |
| "layers.19.mlp.shared_mlp.up_proj", | |
| "layers.19.self_attn.k_proj", | |
| "layers.19.self_attn.o_proj", | |
| "layers.19.self_attn.q_proj", | |
| "layers.19.self_attn.v_proj", | |
| "layers.2.mlp.down_proj", | |
| "layers.2.mlp.gate_up_proj", | |
| "layers.2.mlp.router.gate", | |
| "layers.2.mlp.shared_mlp.down_proj", | |
| "layers.2.mlp.shared_mlp.gate_proj", | |
| "layers.2.mlp.shared_mlp.up_proj", | |
| "layers.2.self_attn.k_proj", | |
| "layers.2.self_attn.o_proj", | |
| "layers.2.self_attn.q_proj", | |
| "layers.2.self_attn.v_proj", | |
| "layers.20.mlp.down_proj", | |
| "layers.20.mlp.gate_up_proj", | |
| "layers.20.mlp.router.gate", | |
| "layers.20.mlp.shared_mlp.down_proj", | |
| "layers.20.mlp.shared_mlp.gate_proj", | |
| "layers.20.mlp.shared_mlp.up_proj", | |
| "layers.20.self_attn.k_proj", | |
| "layers.20.self_attn.o_proj", | |
| "layers.20.self_attn.q_proj", | |
| "layers.20.self_attn.v_proj", | |
| "layers.21.mlp.down_proj", | |
| "layers.21.mlp.gate_up_proj", | |
| "layers.21.mlp.router.gate", | |
| "layers.21.mlp.shared_mlp.down_proj", | |
| "layers.21.mlp.shared_mlp.gate_proj", | |
| "layers.21.mlp.shared_mlp.up_proj", | |
| "layers.21.self_attn.k_proj", | |
| "layers.21.self_attn.o_proj", | |
| "layers.21.self_attn.q_proj", | |
| "layers.21.self_attn.v_proj", | |
| "layers.22.mlp.down_proj", | |
| "layers.22.mlp.gate_up_proj", | |
| "layers.22.mlp.router.gate", | |
| "layers.22.mlp.shared_mlp.down_proj", | |
| "layers.22.mlp.shared_mlp.gate_proj", | |
| "layers.22.mlp.shared_mlp.up_proj", | |
| "layers.22.self_attn.k_proj", | |
| "layers.22.self_attn.o_proj", | |
| "layers.22.self_attn.q_proj", | |
| "layers.22.self_attn.v_proj", | |
| "layers.23.mlp.down_proj", | |
| "layers.23.mlp.gate_up_proj", | |
| "layers.23.mlp.router.gate", | |
| "layers.23.mlp.shared_mlp.down_proj", | |
| "layers.23.mlp.shared_mlp.gate_proj", | |
| "layers.23.mlp.shared_mlp.up_proj", | |
| "layers.23.self_attn.k_proj", | |
| "layers.23.self_attn.o_proj", | |
| "layers.23.self_attn.q_proj", | |
| "layers.23.self_attn.v_proj", | |
| "layers.24.mlp.down_proj", | |
| "layers.24.mlp.gate_up_proj", | |
| "layers.24.mlp.router.gate", | |
| "layers.24.mlp.shared_mlp.down_proj", | |
| "layers.24.mlp.shared_mlp.gate_proj", | |
| "layers.24.mlp.shared_mlp.up_proj", | |
| "layers.24.self_attn.k_proj", | |
| "layers.24.self_attn.o_proj", | |
| "layers.24.self_attn.q_proj", | |
| "layers.24.self_attn.v_proj", | |
| "layers.25.mlp.down_proj", | |
| "layers.25.mlp.gate_up_proj", | |
| "layers.25.mlp.router.gate", | |
| "layers.25.mlp.shared_mlp.down_proj", | |
| "layers.25.mlp.shared_mlp.gate_proj", | |
| "layers.25.mlp.shared_mlp.up_proj", | |
| "layers.25.self_attn.k_proj", | |
| "layers.25.self_attn.o_proj", | |
| "layers.25.self_attn.q_proj", | |
| "layers.25.self_attn.v_proj", | |
| "layers.26.mlp.down_proj", | |
| "layers.26.mlp.gate_up_proj", | |
| "layers.26.mlp.router.gate", | |
| "layers.26.mlp.shared_mlp.down_proj", | |
| "layers.26.mlp.shared_mlp.gate_proj", | |
| "layers.26.mlp.shared_mlp.up_proj", | |
| "layers.26.self_attn.k_proj", | |
| "layers.26.self_attn.o_proj", | |
| "layers.26.self_attn.q_proj", | |
| "layers.26.self_attn.v_proj", | |
| "layers.27.mlp.down_proj", | |
| "layers.27.mlp.gate_up_proj", | |
| "layers.27.mlp.router.gate", | |
| "layers.27.mlp.shared_mlp.down_proj", | |
| "layers.27.mlp.shared_mlp.gate_proj", | |
| "layers.27.mlp.shared_mlp.up_proj", | |
| "layers.27.self_attn.k_proj", | |
| "layers.27.self_attn.o_proj", | |
| "layers.27.self_attn.q_proj", | |
| "layers.27.self_attn.v_proj", | |
| "layers.28.mlp.down_proj", | |
| "layers.28.mlp.gate_up_proj", | |
| "layers.28.mlp.router.gate", | |
| "layers.28.mlp.shared_mlp.down_proj", | |
| "layers.28.mlp.shared_mlp.gate_proj", | |
| "layers.28.mlp.shared_mlp.up_proj", | |
| "layers.28.self_attn.k_proj", | |
| "layers.28.self_attn.o_proj", | |
| "layers.28.self_attn.q_proj", | |
| "layers.28.self_attn.v_proj", | |
| "layers.29.mlp.down_proj", | |
| "layers.29.mlp.gate_up_proj", | |
| "layers.29.mlp.router.gate", | |
| "layers.29.mlp.shared_mlp.down_proj", | |
| "layers.29.mlp.shared_mlp.gate_proj", | |
| "layers.29.mlp.shared_mlp.up_proj", | |
| "layers.29.self_attn.k_proj", | |
| "layers.29.self_attn.o_proj", | |
| "layers.29.self_attn.q_proj", | |
| "layers.29.self_attn.v_proj", | |
| "layers.3.mlp.down_proj", | |
| "layers.3.mlp.gate_up_proj", | |
| "layers.3.mlp.router.gate", | |
| "layers.3.mlp.shared_mlp.down_proj", | |
| "layers.3.mlp.shared_mlp.gate_proj", | |
| "layers.3.mlp.shared_mlp.up_proj", | |
| "layers.3.self_attn.k_proj", | |
| "layers.3.self_attn.o_proj", | |
| "layers.3.self_attn.q_proj", | |
| "layers.3.self_attn.v_proj", | |
| "layers.30.mlp.down_proj", | |
| "layers.30.mlp.gate_up_proj", | |
| "layers.30.mlp.router.gate", | |
| "layers.30.mlp.shared_mlp.down_proj", | |
| "layers.30.mlp.shared_mlp.gate_proj", | |
| "layers.30.mlp.shared_mlp.up_proj", | |
| "layers.30.self_attn.k_proj", | |
| "layers.30.self_attn.o_proj", | |
| "layers.30.self_attn.q_proj", | |
| "layers.30.self_attn.v_proj", | |
| "layers.31.mlp.down_proj", | |
| "layers.31.mlp.gate_up_proj", | |
| "layers.31.mlp.router.gate", | |
| "layers.31.mlp.shared_mlp.down_proj", | |
| "layers.31.mlp.shared_mlp.gate_proj", | |
| "layers.31.mlp.shared_mlp.up_proj", | |
| "layers.31.self_attn.k_proj", | |
| "layers.31.self_attn.o_proj", | |
| "layers.31.self_attn.q_proj", | |
| "layers.31.self_attn.v_proj", | |
| "layers.32.mlp.down_proj", | |
| "layers.32.mlp.gate_up_proj", | |
| "layers.32.mlp.router.gate", | |
| "layers.32.mlp.shared_mlp.down_proj", | |
| "layers.32.mlp.shared_mlp.gate_proj", | |
| "layers.32.mlp.shared_mlp.up_proj", | |
| "layers.32.self_attn.k_proj", | |
| "layers.32.self_attn.o_proj", | |
| "layers.32.self_attn.q_proj", | |
| "layers.32.self_attn.v_proj", | |
| "layers.33.mlp.down_proj", | |
| "layers.33.mlp.gate_up_proj", | |
| "layers.33.mlp.router.gate", | |
| "layers.33.mlp.shared_mlp.down_proj", | |
| "layers.33.mlp.shared_mlp.gate_proj", | |
| "layers.33.mlp.shared_mlp.up_proj", | |
| "layers.33.self_attn.k_proj", | |
| "layers.33.self_attn.o_proj", | |
| "layers.33.self_attn.q_proj", | |
| "layers.33.self_attn.v_proj", | |
| "layers.34.mlp.down_proj", | |
| "layers.34.mlp.gate_up_proj", | |
| "layers.34.mlp.router.gate", | |
| "layers.34.mlp.shared_mlp.down_proj", | |
| "layers.34.mlp.shared_mlp.gate_proj", | |
| "layers.34.mlp.shared_mlp.up_proj", | |
| "layers.34.self_attn.k_proj", | |
| "layers.34.self_attn.o_proj", | |
| "layers.34.self_attn.q_proj", | |
| "layers.34.self_attn.v_proj", | |
| "layers.35.mlp.down_proj", | |
| "layers.35.mlp.gate_up_proj", | |
| "layers.35.mlp.router.gate", | |
| "layers.35.mlp.shared_mlp.down_proj", | |
| "layers.35.mlp.shared_mlp.gate_proj", | |
| "layers.35.mlp.shared_mlp.up_proj", | |
| "layers.35.self_attn.k_proj", | |
| "layers.35.self_attn.o_proj", | |
| "layers.35.self_attn.q_proj", | |
| "layers.35.self_attn.v_proj", | |
| "layers.36.mlp.down_proj", | |
| "layers.36.mlp.gate_up_proj", | |
| "layers.36.mlp.router.gate", | |
| "layers.36.mlp.shared_mlp.down_proj", | |
| "layers.36.mlp.shared_mlp.gate_proj", | |
| "layers.36.mlp.shared_mlp.up_proj", | |
| "layers.36.self_attn.k_proj", | |
| "layers.36.self_attn.o_proj", | |
| "layers.36.self_attn.q_proj", | |
| "layers.36.self_attn.v_proj", | |
| "layers.37.mlp.down_proj", | |
| "layers.37.mlp.gate_up_proj", | |
| "layers.37.mlp.router.gate", | |
| "layers.37.mlp.shared_mlp.down_proj", | |
| "layers.37.mlp.shared_mlp.gate_proj", | |
| "layers.37.mlp.shared_mlp.up_proj", | |
| "layers.37.self_attn.k_proj", | |
| "layers.37.self_attn.o_proj", | |
| "layers.37.self_attn.q_proj", | |
| "layers.37.self_attn.v_proj", | |
| "layers.38.mlp.down_proj", | |
| "layers.38.mlp.gate_up_proj", | |
| "layers.38.mlp.router.gate", | |
| "layers.38.mlp.shared_mlp.down_proj", | |
| "layers.38.mlp.shared_mlp.gate_proj", | |
| "layers.38.mlp.shared_mlp.up_proj", | |
| "layers.38.self_attn.k_proj", | |
| "layers.38.self_attn.o_proj", | |
| "layers.38.self_attn.q_proj", | |
| "layers.38.self_attn.v_proj", | |
| "layers.39.mlp.down_proj", | |
| "layers.39.mlp.gate_up_proj", | |
| "layers.39.mlp.router.gate", | |
| "layers.39.mlp.shared_mlp.down_proj", | |
| "layers.39.mlp.shared_mlp.gate_proj", | |
| "layers.39.mlp.shared_mlp.up_proj", | |
| "layers.39.self_attn.k_proj", | |
| "layers.39.self_attn.o_proj", | |
| "layers.39.self_attn.q_proj", | |
| "layers.39.self_attn.v_proj", | |
| "layers.4.mlp.down_proj", | |
| "layers.4.mlp.gate_up_proj", | |
| "layers.4.mlp.router.gate", | |
| "layers.4.mlp.shared_mlp.down_proj", | |
| "layers.4.mlp.shared_mlp.gate_proj", | |
| "layers.4.mlp.shared_mlp.up_proj", | |
| "layers.4.self_attn.k_proj", | |
| "layers.4.self_attn.o_proj", | |
| "layers.4.self_attn.q_proj", | |
| "layers.4.self_attn.v_proj", | |
| "layers.40.mlp.down_proj", | |
| "layers.40.mlp.gate_up_proj", | |
| "layers.40.mlp.router.gate", | |
| "layers.40.mlp.shared_mlp.down_proj", | |
| "layers.40.mlp.shared_mlp.gate_proj", | |
| "layers.40.mlp.shared_mlp.up_proj", | |
| "layers.40.self_attn.k_proj", | |
| "layers.40.self_attn.o_proj", | |
| "layers.40.self_attn.q_proj", | |
| "layers.40.self_attn.v_proj", | |
| "layers.41.mlp.down_proj", | |
| "layers.41.mlp.gate_up_proj", | |
| "layers.41.mlp.router.gate", | |
| "layers.41.mlp.shared_mlp.down_proj", | |
| "layers.41.mlp.shared_mlp.gate_proj", | |
| "layers.41.mlp.shared_mlp.up_proj", | |
| "layers.41.self_attn.k_proj", | |
| "layers.41.self_attn.o_proj", | |
| "layers.41.self_attn.q_proj", | |
| "layers.41.self_attn.v_proj", | |
| "layers.42.mlp.down_proj", | |
| "layers.42.mlp.gate_up_proj", | |
| "layers.42.mlp.router.gate", | |
| "layers.42.mlp.shared_mlp.down_proj", | |
| "layers.42.mlp.shared_mlp.gate_proj", | |
| "layers.42.mlp.shared_mlp.up_proj", | |
| "layers.42.self_attn.k_proj", | |
| "layers.42.self_attn.o_proj", | |
| "layers.42.self_attn.q_proj", | |
| "layers.42.self_attn.v_proj", | |
| "layers.43.mlp.down_proj", | |
| "layers.43.mlp.gate_up_proj", | |
| "layers.43.mlp.router.gate", | |
| "layers.43.mlp.shared_mlp.down_proj", | |
| "layers.43.mlp.shared_mlp.gate_proj", | |
| "layers.43.mlp.shared_mlp.up_proj", | |
| "layers.43.self_attn.k_proj", | |
| "layers.43.self_attn.o_proj", | |
| "layers.43.self_attn.q_proj", | |
| "layers.43.self_attn.v_proj", | |
| "layers.44.mlp.down_proj", | |
| "layers.44.mlp.gate_up_proj", | |
| "layers.44.mlp.router.gate", | |
| "layers.44.mlp.shared_mlp.down_proj", | |
| "layers.44.mlp.shared_mlp.gate_proj", | |
| "layers.44.mlp.shared_mlp.up_proj", | |
| "layers.44.self_attn.k_proj", | |
| "layers.44.self_attn.o_proj", | |
| "layers.44.self_attn.q_proj", | |
| "layers.44.self_attn.v_proj", | |
| "layers.45.mlp.down_proj", | |
| "layers.45.mlp.gate_up_proj", | |
| "layers.45.mlp.router.gate", | |
| "layers.45.mlp.shared_mlp.down_proj", | |
| "layers.45.mlp.shared_mlp.gate_proj", | |
| "layers.45.mlp.shared_mlp.up_proj", | |
| "layers.45.self_attn.k_proj", | |
| "layers.45.self_attn.o_proj", | |
| "layers.45.self_attn.q_proj", | |
| "layers.45.self_attn.v_proj", | |
| "layers.46.mlp.down_proj", | |
| "layers.46.mlp.gate_up_proj", | |
| "layers.46.mlp.router.gate", | |
| "layers.46.mlp.shared_mlp.down_proj", | |
| "layers.46.mlp.shared_mlp.gate_proj", | |
| "layers.46.mlp.shared_mlp.up_proj", | |
| "layers.46.self_attn.k_proj", | |
| "layers.46.self_attn.o_proj", | |
| "layers.46.self_attn.q_proj", | |
| "layers.46.self_attn.v_proj", | |
| "layers.47.mlp.down_proj", | |
| "layers.47.mlp.gate_up_proj", | |
| "layers.47.mlp.router.gate", | |
| "layers.47.mlp.shared_mlp.down_proj", | |
| "layers.47.mlp.shared_mlp.gate_proj", | |
| "layers.47.mlp.shared_mlp.up_proj", | |
| "layers.47.self_attn.k_proj", | |
| "layers.47.self_attn.o_proj", | |
| "layers.47.self_attn.q_proj", | |
| "layers.47.self_attn.v_proj", | |
| "layers.48.mlp.down_proj", | |
| "layers.48.mlp.gate_up_proj", | |
| "layers.48.mlp.router.gate", | |
| "layers.48.mlp.shared_mlp.down_proj", | |
| "layers.48.mlp.shared_mlp.gate_proj", | |
| "layers.48.mlp.shared_mlp.up_proj", | |
| "layers.48.self_attn.k_proj", | |
| "layers.48.self_attn.o_proj", | |
| "layers.48.self_attn.q_proj", | |
| "layers.48.self_attn.v_proj", | |
| "layers.49.mlp.down_proj", | |
| "layers.49.mlp.gate_up_proj", | |
| "layers.49.mlp.router.gate", | |
| "layers.49.mlp.shared_mlp.down_proj", | |
| "layers.49.mlp.shared_mlp.gate_proj", | |
| "layers.49.mlp.shared_mlp.up_proj", | |
| "layers.49.self_attn.k_proj", | |
| "layers.49.self_attn.o_proj", | |
| "layers.49.self_attn.q_proj", | |
| "layers.49.self_attn.v_proj", | |
| "layers.5.mlp.down_proj", | |
| "layers.5.mlp.gate_up_proj", | |
| "layers.5.mlp.router.gate", | |
| "layers.5.mlp.shared_mlp.down_proj", | |
| "layers.5.mlp.shared_mlp.gate_proj", | |
| "layers.5.mlp.shared_mlp.up_proj", | |
| "layers.5.self_attn.k_proj", | |
| "layers.5.self_attn.o_proj", | |
| "layers.5.self_attn.q_proj", | |
| "layers.5.self_attn.v_proj", | |
| "layers.50.mlp.down_proj", | |
| "layers.50.mlp.gate_up_proj", | |
| "layers.50.mlp.router.gate", | |
| "layers.50.mlp.shared_mlp.down_proj", | |
| "layers.50.mlp.shared_mlp.gate_proj", | |
| "layers.50.mlp.shared_mlp.up_proj", | |
| "layers.50.self_attn.k_proj", | |
| "layers.50.self_attn.o_proj", | |
| "layers.50.self_attn.q_proj", | |
| "layers.50.self_attn.v_proj", | |
| "layers.51.mlp.down_proj", | |
| "layers.51.mlp.gate_up_proj", | |
| "layers.51.mlp.router.gate", | |
| "layers.51.mlp.shared_mlp.down_proj", | |
| "layers.51.mlp.shared_mlp.gate_proj", | |
| "layers.51.mlp.shared_mlp.up_proj", | |
| "layers.51.self_attn.k_proj", | |
| "layers.51.self_attn.o_proj", | |
| "layers.51.self_attn.q_proj", | |
| "layers.51.self_attn.v_proj", | |
| "layers.52.mlp.down_proj", | |
| "layers.52.mlp.gate_up_proj", | |
| "layers.52.mlp.router.gate", | |
| "layers.52.mlp.shared_mlp.down_proj", | |
| "layers.52.mlp.shared_mlp.gate_proj", | |
| "layers.52.mlp.shared_mlp.up_proj", | |
| "layers.52.self_attn.k_proj", | |
| "layers.52.self_attn.o_proj", | |
| "layers.52.self_attn.q_proj", | |
| "layers.52.self_attn.v_proj", | |
| "layers.53.mlp.down_proj", | |
| "layers.53.mlp.gate_up_proj", | |
| "layers.53.mlp.router.gate", | |
| "layers.53.mlp.shared_mlp.down_proj", | |
| "layers.53.mlp.shared_mlp.gate_proj", | |
| "layers.53.mlp.shared_mlp.up_proj", | |
| "layers.53.self_attn.k_proj", | |
| "layers.53.self_attn.o_proj", | |
| "layers.53.self_attn.q_proj", | |
| "layers.53.self_attn.v_proj", | |
| "layers.54.mlp.down_proj", | |
| "layers.54.mlp.gate_up_proj", | |
| "layers.54.mlp.router.gate", | |
| "layers.54.mlp.shared_mlp.down_proj", | |
| "layers.54.mlp.shared_mlp.gate_proj", | |
| "layers.54.mlp.shared_mlp.up_proj", | |
| "layers.54.self_attn.k_proj", | |
| "layers.54.self_attn.o_proj", | |
| "layers.54.self_attn.q_proj", | |
| "layers.54.self_attn.v_proj", | |
| "layers.55.mlp.down_proj", | |
| "layers.55.mlp.gate_up_proj", | |
| "layers.55.mlp.router.gate", | |
| "layers.55.mlp.shared_mlp.down_proj", | |
| "layers.55.mlp.shared_mlp.gate_proj", | |
| "layers.55.mlp.shared_mlp.up_proj", | |
| "layers.55.self_attn.k_proj", | |
| "layers.55.self_attn.o_proj", | |
| "layers.55.self_attn.q_proj", | |
| "layers.55.self_attn.v_proj", | |
| "layers.56.mlp.down_proj", | |
| "layers.56.mlp.gate_up_proj", | |
| "layers.56.mlp.router.gate", | |
| "layers.56.mlp.shared_mlp.down_proj", | |
| "layers.56.mlp.shared_mlp.gate_proj", | |
| "layers.56.mlp.shared_mlp.up_proj", | |
| "layers.56.self_attn.k_proj", | |
| "layers.56.self_attn.o_proj", | |
| "layers.56.self_attn.q_proj", | |
| "layers.56.self_attn.v_proj", | |
| "layers.57.mlp.down_proj", | |
| "layers.57.mlp.gate_up_proj", | |
| "layers.57.mlp.router.gate", | |
| "layers.57.mlp.shared_mlp.down_proj", | |
| "layers.57.mlp.shared_mlp.gate_proj", | |
| "layers.57.mlp.shared_mlp.up_proj", | |
| "layers.57.self_attn.k_proj", | |
| "layers.57.self_attn.o_proj", | |
| "layers.57.self_attn.q_proj", | |
| "layers.57.self_attn.v_proj", | |
| "layers.58.mlp.down_proj", | |
| "layers.58.mlp.gate_up_proj", | |
| "layers.58.mlp.router.gate", | |
| "layers.58.mlp.shared_mlp.down_proj", | |
| "layers.58.mlp.shared_mlp.gate_proj", | |
| "layers.58.mlp.shared_mlp.up_proj", | |
| "layers.58.self_attn.k_proj", | |
| "layers.58.self_attn.o_proj", | |
| "layers.58.self_attn.q_proj", | |
| "layers.58.self_attn.v_proj", | |
| "layers.59.mlp.down_proj", | |
| "layers.59.mlp.gate_up_proj", | |
| "layers.59.mlp.router.gate", | |
| "layers.59.mlp.shared_mlp.down_proj", | |
| "layers.59.mlp.shared_mlp.gate_proj", | |
| "layers.59.mlp.shared_mlp.up_proj", | |
| "layers.59.self_attn.k_proj", | |
| "layers.59.self_attn.o_proj", | |
| "layers.59.self_attn.q_proj", | |
| "layers.59.self_attn.v_proj", | |
| "layers.6.mlp.down_proj", | |
| "layers.6.mlp.gate_up_proj", | |
| "layers.6.mlp.router.gate", | |
| "layers.6.mlp.shared_mlp.down_proj", | |
| "layers.6.mlp.shared_mlp.gate_proj", | |
| "layers.6.mlp.shared_mlp.up_proj", | |
| "layers.6.self_attn.k_proj", | |
| "layers.6.self_attn.o_proj", | |
| "layers.6.self_attn.q_proj", | |
| "layers.6.self_attn.v_proj", | |
| "layers.60.mlp.down_proj", | |
| "layers.60.mlp.gate_up_proj", | |
| "layers.60.mlp.router.gate", | |
| "layers.60.mlp.shared_mlp.down_proj", | |
| "layers.60.mlp.shared_mlp.gate_proj", | |
| "layers.60.mlp.shared_mlp.up_proj", | |
| "layers.60.self_attn.k_proj", | |
| "layers.60.self_attn.o_proj", | |
| "layers.60.self_attn.q_proj", | |
| "layers.60.self_attn.v_proj", | |
| "layers.61.mlp.down_proj", | |
| "layers.61.mlp.gate_up_proj", | |
| "layers.61.mlp.router.gate", | |
| "layers.61.mlp.shared_mlp.down_proj", | |
| "layers.61.mlp.shared_mlp.gate_proj", | |
| "layers.61.mlp.shared_mlp.up_proj", | |
| "layers.61.self_attn.k_proj", | |
| "layers.61.self_attn.o_proj", | |
| "layers.61.self_attn.q_proj", | |
| "layers.61.self_attn.v_proj", | |
| "layers.62.mlp.down_proj", | |
| "layers.62.mlp.gate_up_proj", | |
| "layers.62.mlp.router.gate", | |
| "layers.62.mlp.shared_mlp.down_proj", | |
| "layers.62.mlp.shared_mlp.gate_proj", | |
| "layers.62.mlp.shared_mlp.up_proj", | |
| "layers.62.self_attn.k_proj", | |
| "layers.62.self_attn.o_proj", | |
| "layers.62.self_attn.q_proj", | |
| "layers.62.self_attn.v_proj", | |
| "layers.63.mlp.down_proj", | |
| "layers.63.mlp.gate_up_proj", | |
| "layers.63.mlp.router.gate", | |
| "layers.63.mlp.shared_mlp.down_proj", | |
| "layers.63.mlp.shared_mlp.gate_proj", | |
| "layers.63.mlp.shared_mlp.up_proj", | |
| "layers.63.self_attn.k_proj", | |
| "layers.63.self_attn.o_proj", | |
| "layers.63.self_attn.q_proj", | |
| "layers.63.self_attn.v_proj", | |
| "layers.64.mlp.down_proj", | |
| "layers.64.mlp.gate_up_proj", | |
| "layers.64.mlp.router.gate", | |
| "layers.64.mlp.shared_mlp.down_proj", | |
| "layers.64.mlp.shared_mlp.gate_proj", | |
| "layers.64.mlp.shared_mlp.up_proj", | |
| "layers.64.self_attn.k_proj", | |
| "layers.64.self_attn.o_proj", | |
| "layers.64.self_attn.q_proj", | |
| "layers.64.self_attn.v_proj", | |
| "layers.65.mlp.down_proj", | |
| "layers.65.mlp.gate_up_proj", | |
| "layers.65.mlp.router.gate", | |
| "layers.65.mlp.shared_mlp.down_proj", | |
| "layers.65.mlp.shared_mlp.gate_proj", | |
| "layers.65.mlp.shared_mlp.up_proj", | |
| "layers.65.self_attn.k_proj", | |
| "layers.65.self_attn.o_proj", | |
| "layers.65.self_attn.q_proj", | |
| "layers.65.self_attn.v_proj", | |
| "layers.66.mlp.down_proj", | |
| "layers.66.mlp.gate_up_proj", | |
| "layers.66.mlp.router.gate", | |
| "layers.66.mlp.shared_mlp.down_proj", | |
| "layers.66.mlp.shared_mlp.gate_proj", | |
| "layers.66.mlp.shared_mlp.up_proj", | |
| "layers.66.self_attn.k_proj", | |
| "layers.66.self_attn.o_proj", | |
| "layers.66.self_attn.q_proj", | |
| "layers.66.self_attn.v_proj", | |
| "layers.67.mlp.down_proj", | |
| "layers.67.mlp.gate_up_proj", | |
| "layers.67.mlp.router.gate", | |
| "layers.67.mlp.shared_mlp.down_proj", | |
| "layers.67.mlp.shared_mlp.gate_proj", | |
| "layers.67.mlp.shared_mlp.up_proj", | |
| "layers.67.self_attn.k_proj", | |
| "layers.67.self_attn.o_proj", | |
| "layers.67.self_attn.q_proj", | |
| "layers.67.self_attn.v_proj", | |
| "layers.68.mlp.down_proj", | |
| "layers.68.mlp.gate_up_proj", | |
| "layers.68.mlp.router.gate", | |
| "layers.68.mlp.shared_mlp.down_proj", | |
| "layers.68.mlp.shared_mlp.gate_proj", | |
| "layers.68.mlp.shared_mlp.up_proj", | |
| "layers.68.self_attn.k_proj", | |
| "layers.68.self_attn.o_proj", | |
| "layers.68.self_attn.q_proj", | |
| "layers.68.self_attn.v_proj", | |
| "layers.69.mlp.down_proj", | |
| "layers.69.mlp.gate_up_proj", | |
| "layers.69.mlp.router.gate", | |
| "layers.69.mlp.shared_mlp.down_proj", | |
| "layers.69.mlp.shared_mlp.gate_proj", | |
| "layers.69.mlp.shared_mlp.up_proj", | |
| "layers.69.self_attn.k_proj", | |
| "layers.69.self_attn.o_proj", | |
| "layers.69.self_attn.q_proj", | |
| "layers.69.self_attn.v_proj", | |
| "layers.7.mlp.down_proj", | |
| "layers.7.mlp.gate_up_proj", | |
| "layers.7.mlp.router.gate", | |
| "layers.7.mlp.shared_mlp.down_proj", | |
| "layers.7.mlp.shared_mlp.gate_proj", | |
| "layers.7.mlp.shared_mlp.up_proj", | |
| "layers.7.self_attn.k_proj", | |
| "layers.7.self_attn.o_proj", | |
| "layers.7.self_attn.q_proj", | |
| "layers.7.self_attn.v_proj", | |
| "layers.70.mlp.down_proj", | |
| "layers.70.mlp.gate_up_proj", | |
| "layers.70.mlp.router.gate", | |
| "layers.70.mlp.shared_mlp.down_proj", | |
| "layers.70.mlp.shared_mlp.gate_proj", | |
| "layers.70.mlp.shared_mlp.up_proj", | |
| "layers.70.self_attn.k_proj", | |
| "layers.70.self_attn.o_proj", | |
| "layers.70.self_attn.q_proj", | |
| "layers.70.self_attn.v_proj", | |
| "layers.71.mlp.down_proj", | |
| "layers.71.mlp.gate_up_proj", | |
| "layers.71.mlp.router.gate", | |
| "layers.71.mlp.shared_mlp.down_proj", | |
| "layers.71.mlp.shared_mlp.gate_proj", | |
| "layers.71.mlp.shared_mlp.up_proj", | |
| "layers.71.self_attn.k_proj", | |
| "layers.71.self_attn.o_proj", | |
| "layers.71.self_attn.q_proj", | |
| "layers.71.self_attn.v_proj", | |
| "layers.72.mlp.down_proj", | |
| "layers.72.mlp.gate_up_proj", | |
| "layers.72.mlp.router.gate", | |
| "layers.72.mlp.shared_mlp.down_proj", | |
| "layers.72.mlp.shared_mlp.gate_proj", | |
| "layers.72.mlp.shared_mlp.up_proj", | |
| "layers.72.self_attn.k_proj", | |
| "layers.72.self_attn.o_proj", | |
| "layers.72.self_attn.q_proj", | |
| "layers.72.self_attn.v_proj", | |
| "layers.73.mlp.down_proj", | |
| "layers.73.mlp.gate_up_proj", | |
| "layers.73.mlp.router.gate", | |
| "layers.73.mlp.shared_mlp.down_proj", | |
| "layers.73.mlp.shared_mlp.gate_proj", | |
| "layers.73.mlp.shared_mlp.up_proj", | |
| "layers.73.self_attn.k_proj", | |
| "layers.73.self_attn.o_proj", | |
| "layers.73.self_attn.q_proj", | |
| "layers.73.self_attn.v_proj", | |
| "layers.74.mlp.down_proj", | |
| "layers.74.mlp.gate_up_proj", | |
| "layers.74.mlp.router.gate", | |
| "layers.74.mlp.shared_mlp.down_proj", | |
| "layers.74.mlp.shared_mlp.gate_proj", | |
| "layers.74.mlp.shared_mlp.up_proj", | |
| "layers.74.self_attn.k_proj", | |
| "layers.74.self_attn.o_proj", | |
| "layers.74.self_attn.q_proj", | |
| "layers.74.self_attn.v_proj", | |
| "layers.75.mlp.down_proj", | |
| "layers.75.mlp.gate_up_proj", | |
| "layers.75.mlp.router.gate", | |
| "layers.75.mlp.shared_mlp.down_proj", | |
| "layers.75.mlp.shared_mlp.gate_proj", | |
| "layers.75.mlp.shared_mlp.up_proj", | |
| "layers.75.self_attn.k_proj", | |
| "layers.75.self_attn.o_proj", | |
| "layers.75.self_attn.q_proj", | |
| "layers.75.self_attn.v_proj", | |
| "layers.76.mlp.down_proj", | |
| "layers.76.mlp.gate_up_proj", | |
| "layers.76.mlp.router.gate", | |
| "layers.76.mlp.shared_mlp.down_proj", | |
| "layers.76.mlp.shared_mlp.gate_proj", | |
| "layers.76.mlp.shared_mlp.up_proj", | |
| "layers.76.self_attn.k_proj", | |
| "layers.76.self_attn.o_proj", | |
| "layers.76.self_attn.q_proj", | |
| "layers.76.self_attn.v_proj", | |
| "layers.77.mlp.down_proj", | |
| "layers.77.mlp.gate_up_proj", | |
| "layers.77.mlp.router.gate", | |
| "layers.77.mlp.shared_mlp.down_proj", | |
| "layers.77.mlp.shared_mlp.gate_proj", | |
| "layers.77.mlp.shared_mlp.up_proj", | |
| "layers.77.self_attn.k_proj", | |
| "layers.77.self_attn.o_proj", | |
| "layers.77.self_attn.q_proj", | |
| "layers.77.self_attn.v_proj", | |
| "layers.78.mlp.down_proj", | |
| "layers.78.mlp.gate_up_proj", | |
| "layers.78.mlp.router.gate", | |
| "layers.78.mlp.shared_mlp.down_proj", | |
| "layers.78.mlp.shared_mlp.gate_proj", | |
| "layers.78.mlp.shared_mlp.up_proj", | |
| "layers.78.self_attn.k_proj", | |
| "layers.78.self_attn.o_proj", | |
| "layers.78.self_attn.q_proj", | |
| "layers.78.self_attn.v_proj", | |
| "layers.79.mlp.down_proj", | |
| "layers.79.mlp.gate_up_proj", | |
| "layers.79.mlp.router.gate", | |
| "layers.79.mlp.shared_mlp.down_proj", | |
| "layers.79.mlp.shared_mlp.gate_proj", | |
| "layers.79.mlp.shared_mlp.up_proj", | |
| "layers.79.self_attn.k_proj", | |
| "layers.79.self_attn.o_proj", | |
| "layers.79.self_attn.q_proj", | |
| "layers.79.self_attn.v_proj", | |
| "layers.8.mlp.down_proj", | |
| "layers.8.mlp.gate_up_proj", | |
| "layers.8.mlp.router.gate", | |
| "layers.8.mlp.shared_mlp.down_proj", | |
| "layers.8.mlp.shared_mlp.gate_proj", | |
| "layers.8.mlp.shared_mlp.up_proj", | |
| "layers.8.self_attn.k_proj", | |
| "layers.8.self_attn.o_proj", | |
| "layers.8.self_attn.q_proj", | |
| "layers.8.self_attn.v_proj", | |
| "layers.80.eh_proj", | |
| "layers.80.mlp.down_proj", | |
| "layers.80.mlp.gate_up_proj", | |
| "layers.80.mlp.router.gate", | |
| "layers.80.mlp.shared_mlp.down_proj", | |
| "layers.80.mlp.shared_mlp.gate_proj", | |
| "layers.80.mlp.shared_mlp.up_proj", | |
| "layers.80.self_attn.k_proj", | |
| "layers.80.self_attn.o_proj", | |
| "layers.80.self_attn.q_proj", | |
| "layers.80.self_attn.v_proj", | |
| "layers.9.mlp.down_proj", | |
| "layers.9.mlp.gate_up_proj", | |
| "layers.9.mlp.router.gate", | |
| "layers.9.mlp.shared_mlp.down_proj", | |
| "layers.9.mlp.shared_mlp.gate_proj", | |
| "layers.9.mlp.shared_mlp.up_proj", | |
| "layers.9.self_attn.k_proj", | |
| "layers.9.self_attn.o_proj", | |
| "layers.9.self_attn.q_proj", | |
| "layers.9.self_attn.v_proj", | |
| "lm_head", | |
| "model.embed_tokens", | |
| "model.layers.0.mlp.down_proj", | |
| "model.layers.0.mlp.gate_proj", | |
| "model.layers.0.mlp.gate_up_proj", | |
| "model.layers.0.mlp.up_proj", | |
| "model.layers.0.self_attn.k_proj", | |
| "model.layers.0.self_attn.o_proj", | |
| "model.layers.0.self_attn.q_proj", | |
| "model.layers.0.self_attn.v_proj", | |
| "model.layers.1.mlp.down_proj", | |
| "model.layers.1.mlp.gate_up_proj", | |
| "model.layers.1.mlp.router.gate", | |
| "model.layers.1.mlp.shared_mlp.down_proj", | |
| "model.layers.1.mlp.shared_mlp.gate_proj", | |
| "model.layers.1.mlp.shared_mlp.up_proj", | |
| "model.layers.1.self_attn.k_proj", | |
| "model.layers.1.self_attn.o_proj", | |
| "model.layers.1.self_attn.q_proj", | |
| "model.layers.1.self_attn.v_proj", | |
| "model.layers.10.mlp.down_proj", | |
| "model.layers.10.mlp.gate_up_proj", | |
| "model.layers.10.mlp.router.gate", | |
| "model.layers.10.mlp.shared_mlp.down_proj", | |
| "model.layers.10.mlp.shared_mlp.gate_proj", | |
| "model.layers.10.mlp.shared_mlp.up_proj", | |
| "model.layers.10.self_attn.k_proj", | |
| "model.layers.10.self_attn.o_proj", | |
| "model.layers.10.self_attn.q_proj", | |
| "model.layers.10.self_attn.v_proj", | |
| "model.layers.11.mlp.down_proj", | |
| "model.layers.11.mlp.gate_up_proj", | |
| "model.layers.11.mlp.router.gate", | |
| "model.layers.11.mlp.shared_mlp.down_proj", | |
| "model.layers.11.mlp.shared_mlp.gate_proj", | |
| "model.layers.11.mlp.shared_mlp.up_proj", | |
| "model.layers.11.self_attn.k_proj", | |
| "model.layers.11.self_attn.o_proj", | |
| "model.layers.11.self_attn.q_proj", | |
| "model.layers.11.self_attn.v_proj", | |
| "model.layers.12.mlp.down_proj", | |
| "model.layers.12.mlp.gate_up_proj", | |
| "model.layers.12.mlp.router.gate", | |
| "model.layers.12.mlp.shared_mlp.down_proj", | |
| "model.layers.12.mlp.shared_mlp.gate_proj", | |
| "model.layers.12.mlp.shared_mlp.up_proj", | |
| "model.layers.12.self_attn.k_proj", | |
| "model.layers.12.self_attn.o_proj", | |
| "model.layers.12.self_attn.q_proj", | |
| "model.layers.12.self_attn.v_proj", | |
| "model.layers.13.mlp.down_proj", | |
| "model.layers.13.mlp.gate_up_proj", | |
| "model.layers.13.mlp.router.gate", | |
| "model.layers.13.mlp.shared_mlp.down_proj", | |
| "model.layers.13.mlp.shared_mlp.gate_proj", | |
| "model.layers.13.mlp.shared_mlp.up_proj", | |
| "model.layers.13.self_attn.k_proj", | |
| "model.layers.13.self_attn.o_proj", | |
| "model.layers.13.self_attn.q_proj", | |
| "model.layers.13.self_attn.v_proj", | |
| "model.layers.14.mlp.down_proj", | |
| "model.layers.14.mlp.gate_up_proj", | |
| "model.layers.14.mlp.router.gate", | |
| "model.layers.14.mlp.shared_mlp.down_proj", | |
| "model.layers.14.mlp.shared_mlp.gate_proj", | |
| "model.layers.14.mlp.shared_mlp.up_proj", | |
| "model.layers.14.self_attn.k_proj", | |
| "model.layers.14.self_attn.o_proj", | |
| "model.layers.14.self_attn.q_proj", | |
| "model.layers.14.self_attn.v_proj", | |
| "model.layers.15.mlp.down_proj", | |
| "model.layers.15.mlp.gate_up_proj", | |
| "model.layers.15.mlp.router.gate", | |
| "model.layers.15.mlp.shared_mlp.down_proj", | |
| "model.layers.15.mlp.shared_mlp.gate_proj", | |
| "model.layers.15.mlp.shared_mlp.up_proj", | |
| "model.layers.15.self_attn.k_proj", | |
| "model.layers.15.self_attn.o_proj", | |
| "model.layers.15.self_attn.q_proj", | |
| "model.layers.15.self_attn.v_proj", | |
| "model.layers.16.mlp.down_proj", | |
| "model.layers.16.mlp.gate_up_proj", | |
| "model.layers.16.mlp.router.gate", | |
| "model.layers.16.mlp.shared_mlp.down_proj", | |
| "model.layers.16.mlp.shared_mlp.gate_proj", | |
| "model.layers.16.mlp.shared_mlp.up_proj", | |
| "model.layers.16.self_attn.k_proj", | |
| "model.layers.16.self_attn.o_proj", | |
| "model.layers.16.self_attn.q_proj", | |
| "model.layers.16.self_attn.v_proj", | |
| "model.layers.17.mlp.down_proj", | |
| "model.layers.17.mlp.gate_up_proj", | |
| "model.layers.17.mlp.router.gate", | |
| "model.layers.17.mlp.shared_mlp.down_proj", | |
| "model.layers.17.mlp.shared_mlp.gate_proj", | |
| "model.layers.17.mlp.shared_mlp.up_proj", | |
| "model.layers.17.self_attn.k_proj", | |
| "model.layers.17.self_attn.o_proj", | |
| "model.layers.17.self_attn.q_proj", | |
| "model.layers.17.self_attn.v_proj", | |
| "model.layers.18.mlp.down_proj", | |
| "model.layers.18.mlp.gate_up_proj", | |
| "model.layers.18.mlp.router.gate", | |
| "model.layers.18.mlp.shared_mlp.down_proj", | |
| "model.layers.18.mlp.shared_mlp.gate_proj", | |
| "model.layers.18.mlp.shared_mlp.up_proj", | |
| "model.layers.18.self_attn.k_proj", | |
| "model.layers.18.self_attn.o_proj", | |
| "model.layers.18.self_attn.q_proj", | |
| "model.layers.18.self_attn.v_proj", | |
| "model.layers.19.mlp.down_proj", | |
| "model.layers.19.mlp.gate_up_proj", | |
| "model.layers.19.mlp.router.gate", | |
| "model.layers.19.mlp.shared_mlp.down_proj", | |
| "model.layers.19.mlp.shared_mlp.gate_proj", | |
| "model.layers.19.mlp.shared_mlp.up_proj", | |
| "model.layers.19.self_attn.k_proj", | |
| "model.layers.19.self_attn.o_proj", | |
| "model.layers.19.self_attn.q_proj", | |
| "model.layers.19.self_attn.v_proj", | |
| "model.layers.2.mlp.down_proj", | |
| "model.layers.2.mlp.gate_up_proj", | |
| "model.layers.2.mlp.router.gate", | |
| "model.layers.2.mlp.shared_mlp.down_proj", | |
| "model.layers.2.mlp.shared_mlp.gate_proj", | |
| "model.layers.2.mlp.shared_mlp.up_proj", | |
| "model.layers.2.self_attn.k_proj", | |
| "model.layers.2.self_attn.o_proj", | |
| "model.layers.2.self_attn.q_proj", | |
| "model.layers.2.self_attn.v_proj", | |
| "model.layers.20.mlp.down_proj", | |
| "model.layers.20.mlp.gate_up_proj", | |
| "model.layers.20.mlp.router.gate", | |
| "model.layers.20.mlp.shared_mlp.down_proj", | |
| "model.layers.20.mlp.shared_mlp.gate_proj", | |
| "model.layers.20.mlp.shared_mlp.up_proj", | |
| "model.layers.20.self_attn.k_proj", | |
| "model.layers.20.self_attn.o_proj", | |
| "model.layers.20.self_attn.q_proj", | |
| "model.layers.20.self_attn.v_proj", | |
| "model.layers.21.mlp.down_proj", | |
| "model.layers.21.mlp.gate_up_proj", | |
| "model.layers.21.mlp.router.gate", | |
| "model.layers.21.mlp.shared_mlp.down_proj", | |
| "model.layers.21.mlp.shared_mlp.gate_proj", | |
| "model.layers.21.mlp.shared_mlp.up_proj", | |
| "model.layers.21.self_attn.k_proj", | |
| "model.layers.21.self_attn.o_proj", | |
| "model.layers.21.self_attn.q_proj", | |
| "model.layers.21.self_attn.v_proj", | |
| "model.layers.22.mlp.down_proj", | |
| "model.layers.22.mlp.gate_up_proj", | |
| "model.layers.22.mlp.router.gate", | |
| "model.layers.22.mlp.shared_mlp.down_proj", | |
| "model.layers.22.mlp.shared_mlp.gate_proj", | |
| "model.layers.22.mlp.shared_mlp.up_proj", | |
| "model.layers.22.self_attn.k_proj", | |
| "model.layers.22.self_attn.o_proj", | |
| "model.layers.22.self_attn.q_proj", | |
| "model.layers.22.self_attn.v_proj", | |
| "model.layers.23.mlp.down_proj", | |
| "model.layers.23.mlp.gate_up_proj", | |
| "model.layers.23.mlp.router.gate", | |
| "model.layers.23.mlp.shared_mlp.down_proj", | |
| "model.layers.23.mlp.shared_mlp.gate_proj", | |
| "model.layers.23.mlp.shared_mlp.up_proj", | |
| "model.layers.23.self_attn.k_proj", | |
| "model.layers.23.self_attn.o_proj", | |
| "model.layers.23.self_attn.q_proj", | |
| "model.layers.23.self_attn.v_proj", | |
| "model.layers.24.mlp.down_proj", | |
| "model.layers.24.mlp.gate_up_proj", | |
| "model.layers.24.mlp.router.gate", | |
| "model.layers.24.mlp.shared_mlp.down_proj", | |
| "model.layers.24.mlp.shared_mlp.gate_proj", | |
| "model.layers.24.mlp.shared_mlp.up_proj", | |
| "model.layers.24.self_attn.k_proj", | |
| "model.layers.24.self_attn.o_proj", | |
| "model.layers.24.self_attn.q_proj", | |
| "model.layers.24.self_attn.v_proj", | |
| "model.layers.25.mlp.down_proj", | |
| "model.layers.25.mlp.gate_up_proj", | |
| "model.layers.25.mlp.router.gate", | |
| "model.layers.25.mlp.shared_mlp.down_proj", | |
| "model.layers.25.mlp.shared_mlp.gate_proj", | |
| "model.layers.25.mlp.shared_mlp.up_proj", | |
| "model.layers.25.self_attn.k_proj", | |
| "model.layers.25.self_attn.o_proj", | |
| "model.layers.25.self_attn.q_proj", | |
| "model.layers.25.self_attn.v_proj", | |
| "model.layers.26.mlp.down_proj", | |
| "model.layers.26.mlp.gate_up_proj", | |
| "model.layers.26.mlp.router.gate", | |
| "model.layers.26.mlp.shared_mlp.down_proj", | |
| "model.layers.26.mlp.shared_mlp.gate_proj", | |
| "model.layers.26.mlp.shared_mlp.up_proj", | |
| "model.layers.26.self_attn.k_proj", | |
| "model.layers.26.self_attn.o_proj", | |
| "model.layers.26.self_attn.q_proj", | |
| "model.layers.26.self_attn.v_proj", | |
| "model.layers.27.mlp.down_proj", | |
| "model.layers.27.mlp.gate_up_proj", | |
| "model.layers.27.mlp.router.gate", | |
| "model.layers.27.mlp.shared_mlp.down_proj", | |
| "model.layers.27.mlp.shared_mlp.gate_proj", | |
| "model.layers.27.mlp.shared_mlp.up_proj", | |
| "model.layers.27.self_attn.k_proj", | |
| "model.layers.27.self_attn.o_proj", | |
| "model.layers.27.self_attn.q_proj", | |
| "model.layers.27.self_attn.v_proj", | |
| "model.layers.28.mlp.down_proj", | |
| "model.layers.28.mlp.gate_up_proj", | |
| "model.layers.28.mlp.router.gate", | |
| "model.layers.28.mlp.shared_mlp.down_proj", | |
| "model.layers.28.mlp.shared_mlp.gate_proj", | |
| "model.layers.28.mlp.shared_mlp.up_proj", | |
| "model.layers.28.self_attn.k_proj", | |
| "model.layers.28.self_attn.o_proj", | |
| "model.layers.28.self_attn.q_proj", | |
| "model.layers.28.self_attn.v_proj", | |
| "model.layers.29.mlp.down_proj", | |
| "model.layers.29.mlp.gate_up_proj", | |
| "model.layers.29.mlp.router.gate", | |
| "model.layers.29.mlp.shared_mlp.down_proj", | |
| "model.layers.29.mlp.shared_mlp.gate_proj", | |
| "model.layers.29.mlp.shared_mlp.up_proj", | |
| "model.layers.29.self_attn.k_proj", | |
| "model.layers.29.self_attn.o_proj", | |
| "model.layers.29.self_attn.q_proj", | |
| "model.layers.29.self_attn.v_proj", | |
| "model.layers.3.mlp.down_proj", | |
| "model.layers.3.mlp.gate_up_proj", | |
| "model.layers.3.mlp.router.gate", | |
| "model.layers.3.mlp.shared_mlp.down_proj", | |
| "model.layers.3.mlp.shared_mlp.gate_proj", | |
| "model.layers.3.mlp.shared_mlp.up_proj", | |
| "model.layers.3.self_attn.k_proj", | |
| "model.layers.3.self_attn.o_proj", | |
| "model.layers.3.self_attn.q_proj", | |
| "model.layers.3.self_attn.v_proj", | |
| "model.layers.30.mlp.down_proj", | |
| "model.layers.30.mlp.gate_up_proj", | |
| "model.layers.30.mlp.router.gate", | |
| "model.layers.30.mlp.shared_mlp.down_proj", | |
| "model.layers.30.mlp.shared_mlp.gate_proj", | |
| "model.layers.30.mlp.shared_mlp.up_proj", | |
| "model.layers.30.self_attn.k_proj", | |
| "model.layers.30.self_attn.o_proj", | |
| "model.layers.30.self_attn.q_proj", | |
| "model.layers.30.self_attn.v_proj", | |
| "model.layers.31.mlp.down_proj", | |
| "model.layers.31.mlp.gate_up_proj", | |
| "model.layers.31.mlp.router.gate", | |
| "model.layers.31.mlp.shared_mlp.down_proj", | |
| "model.layers.31.mlp.shared_mlp.gate_proj", | |
| "model.layers.31.mlp.shared_mlp.up_proj", | |
| "model.layers.31.self_attn.k_proj", | |
| "model.layers.31.self_attn.o_proj", | |
| "model.layers.31.self_attn.q_proj", | |
| "model.layers.31.self_attn.v_proj", | |
| "model.layers.32.mlp.down_proj", | |
| "model.layers.32.mlp.gate_up_proj", | |
| "model.layers.32.mlp.router.gate", | |
| "model.layers.32.mlp.shared_mlp.down_proj", | |
| "model.layers.32.mlp.shared_mlp.gate_proj", | |
| "model.layers.32.mlp.shared_mlp.up_proj", | |
| "model.layers.32.self_attn.k_proj", | |
| "model.layers.32.self_attn.o_proj", | |
| "model.layers.32.self_attn.q_proj", | |
| "model.layers.32.self_attn.v_proj", | |
| "model.layers.33.mlp.down_proj", | |
| "model.layers.33.mlp.gate_up_proj", | |
| "model.layers.33.mlp.router.gate", | |
| "model.layers.33.mlp.shared_mlp.down_proj", | |
| "model.layers.33.mlp.shared_mlp.gate_proj", | |
| "model.layers.33.mlp.shared_mlp.up_proj", | |
| "model.layers.33.self_attn.k_proj", | |
| "model.layers.33.self_attn.o_proj", | |
| "model.layers.33.self_attn.q_proj", | |
| "model.layers.33.self_attn.v_proj", | |
| "model.layers.34.mlp.down_proj", | |
| "model.layers.34.mlp.gate_up_proj", | |
| "model.layers.34.mlp.router.gate", | |
| "model.layers.34.mlp.shared_mlp.down_proj", | |
| "model.layers.34.mlp.shared_mlp.gate_proj", | |
| "model.layers.34.mlp.shared_mlp.up_proj", | |
| "model.layers.34.self_attn.k_proj", | |
| "model.layers.34.self_attn.o_proj", | |
| "model.layers.34.self_attn.q_proj", | |
| "model.layers.34.self_attn.v_proj", | |
| "model.layers.35.mlp.down_proj", | |
| "model.layers.35.mlp.gate_up_proj", | |
| "model.layers.35.mlp.router.gate", | |
| "model.layers.35.mlp.shared_mlp.down_proj", | |
| "model.layers.35.mlp.shared_mlp.gate_proj", | |
| "model.layers.35.mlp.shared_mlp.up_proj", | |
| "model.layers.35.self_attn.k_proj", | |
| "model.layers.35.self_attn.o_proj", | |
| "model.layers.35.self_attn.q_proj", | |
| "model.layers.35.self_attn.v_proj", | |
| "model.layers.36.mlp.down_proj", | |
| "model.layers.36.mlp.gate_up_proj", | |
| "model.layers.36.mlp.router.gate", | |
| "model.layers.36.mlp.shared_mlp.down_proj", | |
| "model.layers.36.mlp.shared_mlp.gate_proj", | |
| "model.layers.36.mlp.shared_mlp.up_proj", | |
| "model.layers.36.self_attn.k_proj", | |
| "model.layers.36.self_attn.o_proj", | |
| "model.layers.36.self_attn.q_proj", | |
| "model.layers.36.self_attn.v_proj", | |
| "model.layers.37.mlp.down_proj", | |
| "model.layers.37.mlp.gate_up_proj", | |
| "model.layers.37.mlp.router.gate", | |
| "model.layers.37.mlp.shared_mlp.down_proj", | |
| "model.layers.37.mlp.shared_mlp.gate_proj", | |
| "model.layers.37.mlp.shared_mlp.up_proj", | |
| "model.layers.37.self_attn.k_proj", | |
| "model.layers.37.self_attn.o_proj", | |
| "model.layers.37.self_attn.q_proj", | |
| "model.layers.37.self_attn.v_proj", | |
| "model.layers.38.mlp.down_proj", | |
| "model.layers.38.mlp.gate_up_proj", | |
| "model.layers.38.mlp.router.gate", | |
| "model.layers.38.mlp.shared_mlp.down_proj", | |
| "model.layers.38.mlp.shared_mlp.gate_proj", | |
| "model.layers.38.mlp.shared_mlp.up_proj", | |
| "model.layers.38.self_attn.k_proj", | |
| "model.layers.38.self_attn.o_proj", | |
| "model.layers.38.self_attn.q_proj", | |
| "model.layers.38.self_attn.v_proj", | |
| "model.layers.39.mlp.down_proj", | |
| "model.layers.39.mlp.gate_up_proj", | |
| "model.layers.39.mlp.router.gate", | |
| "model.layers.39.mlp.shared_mlp.down_proj", | |
| "model.layers.39.mlp.shared_mlp.gate_proj", | |
| "model.layers.39.mlp.shared_mlp.up_proj", | |
| "model.layers.39.self_attn.k_proj", | |
| "model.layers.39.self_attn.o_proj", | |
| "model.layers.39.self_attn.q_proj", | |
| "model.layers.39.self_attn.v_proj", | |
| "model.layers.4.mlp.down_proj", | |
| "model.layers.4.mlp.gate_up_proj", | |
| "model.layers.4.mlp.router.gate", | |
| "model.layers.4.mlp.shared_mlp.down_proj", | |
| "model.layers.4.mlp.shared_mlp.gate_proj", | |
| "model.layers.4.mlp.shared_mlp.up_proj", | |
| "model.layers.4.self_attn.k_proj", | |
| "model.layers.4.self_attn.o_proj", | |
| "model.layers.4.self_attn.q_proj", | |
| "model.layers.4.self_attn.v_proj", | |
| "model.layers.40.mlp.down_proj", | |
| "model.layers.40.mlp.gate_up_proj", | |
| "model.layers.40.mlp.router.gate", | |
| "model.layers.40.mlp.shared_mlp.down_proj", | |
| "model.layers.40.mlp.shared_mlp.gate_proj", | |
| "model.layers.40.mlp.shared_mlp.up_proj", | |
| "model.layers.40.self_attn.k_proj", | |
| "model.layers.40.self_attn.o_proj", | |
| "model.layers.40.self_attn.q_proj", | |
| "model.layers.40.self_attn.v_proj", | |
| "model.layers.41.mlp.down_proj", | |
| "model.layers.41.mlp.gate_up_proj", | |
| "model.layers.41.mlp.router.gate", | |
| "model.layers.41.mlp.shared_mlp.down_proj", | |
| "model.layers.41.mlp.shared_mlp.gate_proj", | |
| "model.layers.41.mlp.shared_mlp.up_proj", | |
| "model.layers.41.self_attn.k_proj", | |
| "model.layers.41.self_attn.o_proj", | |
| "model.layers.41.self_attn.q_proj", | |
| "model.layers.41.self_attn.v_proj", | |
| "model.layers.42.mlp.down_proj", | |
| "model.layers.42.mlp.gate_up_proj", | |
| "model.layers.42.mlp.router.gate", | |
| "model.layers.42.mlp.shared_mlp.down_proj", | |
| "model.layers.42.mlp.shared_mlp.gate_proj", | |
| "model.layers.42.mlp.shared_mlp.up_proj", | |
| "model.layers.42.self_attn.k_proj", | |
| "model.layers.42.self_attn.o_proj", | |
| "model.layers.42.self_attn.q_proj", | |
| "model.layers.42.self_attn.v_proj", | |
| "model.layers.43.mlp.down_proj", | |
| "model.layers.43.mlp.gate_up_proj", | |
| "model.layers.43.mlp.router.gate", | |
| "model.layers.43.mlp.shared_mlp.down_proj", | |
| "model.layers.43.mlp.shared_mlp.gate_proj", | |
| "model.layers.43.mlp.shared_mlp.up_proj", | |
| "model.layers.43.self_attn.k_proj", | |
| "model.layers.43.self_attn.o_proj", | |
| "model.layers.43.self_attn.q_proj", | |
| "model.layers.43.self_attn.v_proj", | |
| "model.layers.44.mlp.down_proj", | |
| "model.layers.44.mlp.gate_up_proj", | |
| "model.layers.44.mlp.router.gate", | |
| "model.layers.44.mlp.shared_mlp.down_proj", | |
| "model.layers.44.mlp.shared_mlp.gate_proj", | |
| "model.layers.44.mlp.shared_mlp.up_proj", | |
| "model.layers.44.self_attn.k_proj", | |
| "model.layers.44.self_attn.o_proj", | |
| "model.layers.44.self_attn.q_proj", | |
| "model.layers.44.self_attn.v_proj", | |
| "model.layers.45.mlp.down_proj", | |
| "model.layers.45.mlp.gate_up_proj", | |
| "model.layers.45.mlp.router.gate", | |
| "model.layers.45.mlp.shared_mlp.down_proj", | |
| "model.layers.45.mlp.shared_mlp.gate_proj", | |
| "model.layers.45.mlp.shared_mlp.up_proj", | |
| "model.layers.45.self_attn.k_proj", | |
| "model.layers.45.self_attn.o_proj", | |
| "model.layers.45.self_attn.q_proj", | |
| "model.layers.45.self_attn.v_proj", | |
| "model.layers.46.mlp.down_proj", | |
| "model.layers.46.mlp.gate_up_proj", | |
| "model.layers.46.mlp.router.gate", | |
| "model.layers.46.mlp.shared_mlp.down_proj", | |
| "model.layers.46.mlp.shared_mlp.gate_proj", | |
| "model.layers.46.mlp.shared_mlp.up_proj", | |
| "model.layers.46.self_attn.k_proj", | |
| "model.layers.46.self_attn.o_proj", | |
| "model.layers.46.self_attn.q_proj", | |
| "model.layers.46.self_attn.v_proj", | |
| "model.layers.47.mlp.down_proj", | |
| "model.layers.47.mlp.gate_up_proj", | |
| "model.layers.47.mlp.router.gate", | |
| "model.layers.47.mlp.shared_mlp.down_proj", | |
| "model.layers.47.mlp.shared_mlp.gate_proj", | |
| "model.layers.47.mlp.shared_mlp.up_proj", | |
| "model.layers.47.self_attn.k_proj", | |
| "model.layers.47.self_attn.o_proj", | |
| "model.layers.47.self_attn.q_proj", | |
| "model.layers.47.self_attn.v_proj", | |
| "model.layers.48.mlp.down_proj", | |
| "model.layers.48.mlp.gate_up_proj", | |
| "model.layers.48.mlp.router.gate", | |
| "model.layers.48.mlp.shared_mlp.down_proj", | |
| "model.layers.48.mlp.shared_mlp.gate_proj", | |
| "model.layers.48.mlp.shared_mlp.up_proj", | |
| "model.layers.48.self_attn.k_proj", | |
| "model.layers.48.self_attn.o_proj", | |
| "model.layers.48.self_attn.q_proj", | |
| "model.layers.48.self_attn.v_proj", | |
| "model.layers.49.mlp.down_proj", | |
| "model.layers.49.mlp.gate_up_proj", | |
| "model.layers.49.mlp.router.gate", | |
| "model.layers.49.mlp.shared_mlp.down_proj", | |
| "model.layers.49.mlp.shared_mlp.gate_proj", | |
| "model.layers.49.mlp.shared_mlp.up_proj", | |
| "model.layers.49.self_attn.k_proj", | |
| "model.layers.49.self_attn.o_proj", | |
| "model.layers.49.self_attn.q_proj", | |
| "model.layers.49.self_attn.v_proj", | |
| "model.layers.5.mlp.down_proj", | |
| "model.layers.5.mlp.gate_up_proj", | |
| "model.layers.5.mlp.router.gate", | |
| "model.layers.5.mlp.shared_mlp.down_proj", | |
| "model.layers.5.mlp.shared_mlp.gate_proj", | |
| "model.layers.5.mlp.shared_mlp.up_proj", | |
| "model.layers.5.self_attn.k_proj", | |
| "model.layers.5.self_attn.o_proj", | |
| "model.layers.5.self_attn.q_proj", | |
| "model.layers.5.self_attn.v_proj", | |
| "model.layers.50.mlp.down_proj", | |
| "model.layers.50.mlp.gate_up_proj", | |
| "model.layers.50.mlp.router.gate", | |
| "model.layers.50.mlp.shared_mlp.down_proj", | |
| "model.layers.50.mlp.shared_mlp.gate_proj", | |
| "model.layers.50.mlp.shared_mlp.up_proj", | |
| "model.layers.50.self_attn.k_proj", | |
| "model.layers.50.self_attn.o_proj", | |
| "model.layers.50.self_attn.q_proj", | |
| "model.layers.50.self_attn.v_proj", | |
| "model.layers.51.mlp.down_proj", | |
| "model.layers.51.mlp.gate_up_proj", | |
| "model.layers.51.mlp.router.gate", | |
| "model.layers.51.mlp.shared_mlp.down_proj", | |
| "model.layers.51.mlp.shared_mlp.gate_proj", | |
| "model.layers.51.mlp.shared_mlp.up_proj", | |
| "model.layers.51.self_attn.k_proj", | |
| "model.layers.51.self_attn.o_proj", | |
| "model.layers.51.self_attn.q_proj", | |
| "model.layers.51.self_attn.v_proj", | |
| "model.layers.52.mlp.down_proj", | |
| "model.layers.52.mlp.gate_up_proj", | |
| "model.layers.52.mlp.router.gate", | |
| "model.layers.52.mlp.shared_mlp.down_proj", | |
| "model.layers.52.mlp.shared_mlp.gate_proj", | |
| "model.layers.52.mlp.shared_mlp.up_proj", | |
| "model.layers.52.self_attn.k_proj", | |
| "model.layers.52.self_attn.o_proj", | |
| "model.layers.52.self_attn.q_proj", | |
| "model.layers.52.self_attn.v_proj", | |
| "model.layers.53.mlp.down_proj", | |
| "model.layers.53.mlp.gate_up_proj", | |
| "model.layers.53.mlp.router.gate", | |
| "model.layers.53.mlp.shared_mlp.down_proj", | |
| "model.layers.53.mlp.shared_mlp.gate_proj", | |
| "model.layers.53.mlp.shared_mlp.up_proj", | |
| "model.layers.53.self_attn.k_proj", | |
| "model.layers.53.self_attn.o_proj", | |
| "model.layers.53.self_attn.q_proj", | |
| "model.layers.53.self_attn.v_proj", | |
| "model.layers.54.mlp.down_proj", | |
| "model.layers.54.mlp.gate_up_proj", | |
| "model.layers.54.mlp.router.gate", | |
| "model.layers.54.mlp.shared_mlp.down_proj", | |
| "model.layers.54.mlp.shared_mlp.gate_proj", | |
| "model.layers.54.mlp.shared_mlp.up_proj", | |
| "model.layers.54.self_attn.k_proj", | |
| "model.layers.54.self_attn.o_proj", | |
| "model.layers.54.self_attn.q_proj", | |
| "model.layers.54.self_attn.v_proj", | |
| "model.layers.55.mlp.down_proj", | |
| "model.layers.55.mlp.gate_up_proj", | |
| "model.layers.55.mlp.router.gate", | |
| "model.layers.55.mlp.shared_mlp.down_proj", | |
| "model.layers.55.mlp.shared_mlp.gate_proj", | |
| "model.layers.55.mlp.shared_mlp.up_proj", | |
| "model.layers.55.self_attn.k_proj", | |
| "model.layers.55.self_attn.o_proj", | |
| "model.layers.55.self_attn.q_proj", | |
| "model.layers.55.self_attn.v_proj", | |
| "model.layers.56.mlp.down_proj", | |
| "model.layers.56.mlp.gate_up_proj", | |
| "model.layers.56.mlp.router.gate", | |
| "model.layers.56.mlp.shared_mlp.down_proj", | |
| "model.layers.56.mlp.shared_mlp.gate_proj", | |
| "model.layers.56.mlp.shared_mlp.up_proj", | |
| "model.layers.56.self_attn.k_proj", | |
| "model.layers.56.self_attn.o_proj", | |
| "model.layers.56.self_attn.q_proj", | |
| "model.layers.56.self_attn.v_proj", | |
| "model.layers.57.mlp.down_proj", | |
| "model.layers.57.mlp.gate_up_proj", | |
| "model.layers.57.mlp.router.gate", | |
| "model.layers.57.mlp.shared_mlp.down_proj", | |
| "model.layers.57.mlp.shared_mlp.gate_proj", | |
| "model.layers.57.mlp.shared_mlp.up_proj", | |
| "model.layers.57.self_attn.k_proj", | |
| "model.layers.57.self_attn.o_proj", | |
| "model.layers.57.self_attn.q_proj", | |
| "model.layers.57.self_attn.v_proj", | |
| "model.layers.58.mlp.down_proj", | |
| "model.layers.58.mlp.gate_up_proj", | |
| "model.layers.58.mlp.router.gate", | |
| "model.layers.58.mlp.shared_mlp.down_proj", | |
| "model.layers.58.mlp.shared_mlp.gate_proj", | |
| "model.layers.58.mlp.shared_mlp.up_proj", | |
| "model.layers.58.self_attn.k_proj", | |
| "model.layers.58.self_attn.o_proj", | |
| "model.layers.58.self_attn.q_proj", | |
| "model.layers.58.self_attn.v_proj", | |
| "model.layers.59.mlp.down_proj", | |
| "model.layers.59.mlp.gate_up_proj", | |
| "model.layers.59.mlp.router.gate", | |
| "model.layers.59.mlp.shared_mlp.down_proj", | |
| "model.layers.59.mlp.shared_mlp.gate_proj", | |
| "model.layers.59.mlp.shared_mlp.up_proj", | |
| "model.layers.59.self_attn.k_proj", | |
| "model.layers.59.self_attn.o_proj", | |
| "model.layers.59.self_attn.q_proj", | |
| "model.layers.59.self_attn.v_proj", | |
| "model.layers.6.mlp.down_proj", | |
| "model.layers.6.mlp.gate_up_proj", | |
| "model.layers.6.mlp.router.gate", | |
| "model.layers.6.mlp.shared_mlp.down_proj", | |
| "model.layers.6.mlp.shared_mlp.gate_proj", | |
| "model.layers.6.mlp.shared_mlp.up_proj", | |
| "model.layers.6.self_attn.k_proj", | |
| "model.layers.6.self_attn.o_proj", | |
| "model.layers.6.self_attn.q_proj", | |
| "model.layers.6.self_attn.v_proj", | |
| "model.layers.60.mlp.down_proj", | |
| "model.layers.60.mlp.gate_up_proj", | |
| "model.layers.60.mlp.router.gate", | |
| "model.layers.60.mlp.shared_mlp.down_proj", | |
| "model.layers.60.mlp.shared_mlp.gate_proj", | |
| "model.layers.60.mlp.shared_mlp.up_proj", | |
| "model.layers.60.self_attn.k_proj", | |
| "model.layers.60.self_attn.o_proj", | |
| "model.layers.60.self_attn.q_proj", | |
| "model.layers.60.self_attn.v_proj", | |
| "model.layers.61.mlp.down_proj", | |
| "model.layers.61.mlp.gate_up_proj", | |
| "model.layers.61.mlp.router.gate", | |
| "model.layers.61.mlp.shared_mlp.down_proj", | |
| "model.layers.61.mlp.shared_mlp.gate_proj", | |
| "model.layers.61.mlp.shared_mlp.up_proj", | |
| "model.layers.61.self_attn.k_proj", | |
| "model.layers.61.self_attn.o_proj", | |
| "model.layers.61.self_attn.q_proj", | |
| "model.layers.61.self_attn.v_proj", | |
| "model.layers.62.mlp.down_proj", | |
| "model.layers.62.mlp.gate_up_proj", | |
| "model.layers.62.mlp.router.gate", | |
| "model.layers.62.mlp.shared_mlp.down_proj", | |
| "model.layers.62.mlp.shared_mlp.gate_proj", | |
| "model.layers.62.mlp.shared_mlp.up_proj", | |
| "model.layers.62.self_attn.k_proj", | |
| "model.layers.62.self_attn.o_proj", | |
| "model.layers.62.self_attn.q_proj", | |
| "model.layers.62.self_attn.v_proj", | |
| "model.layers.63.mlp.down_proj", | |
| "model.layers.63.mlp.gate_up_proj", | |
| "model.layers.63.mlp.router.gate", | |
| "model.layers.63.mlp.shared_mlp.down_proj", | |
| "model.layers.63.mlp.shared_mlp.gate_proj", | |
| "model.layers.63.mlp.shared_mlp.up_proj", | |
| "model.layers.63.self_attn.k_proj", | |
| "model.layers.63.self_attn.o_proj", | |
| "model.layers.63.self_attn.q_proj", | |
| "model.layers.63.self_attn.v_proj", | |
| "model.layers.64.mlp.down_proj", | |
| "model.layers.64.mlp.gate_up_proj", | |
| "model.layers.64.mlp.router.gate", | |
| "model.layers.64.mlp.shared_mlp.down_proj", | |
| "model.layers.64.mlp.shared_mlp.gate_proj", | |
| "model.layers.64.mlp.shared_mlp.up_proj", | |
| "model.layers.64.self_attn.k_proj", | |
| "model.layers.64.self_attn.o_proj", | |
| "model.layers.64.self_attn.q_proj", | |
| "model.layers.64.self_attn.v_proj", | |
| "model.layers.65.mlp.down_proj", | |
| "model.layers.65.mlp.gate_up_proj", | |
| "model.layers.65.mlp.router.gate", | |
| "model.layers.65.mlp.shared_mlp.down_proj", | |
| "model.layers.65.mlp.shared_mlp.gate_proj", | |
| "model.layers.65.mlp.shared_mlp.up_proj", | |
| "model.layers.65.self_attn.k_proj", | |
| "model.layers.65.self_attn.o_proj", | |
| "model.layers.65.self_attn.q_proj", | |
| "model.layers.65.self_attn.v_proj", | |
| "model.layers.66.mlp.down_proj", | |
| "model.layers.66.mlp.gate_up_proj", | |
| "model.layers.66.mlp.router.gate", | |
| "model.layers.66.mlp.shared_mlp.down_proj", | |
| "model.layers.66.mlp.shared_mlp.gate_proj", | |
| "model.layers.66.mlp.shared_mlp.up_proj", | |
| "model.layers.66.self_attn.k_proj", | |
| "model.layers.66.self_attn.o_proj", | |
| "model.layers.66.self_attn.q_proj", | |
| "model.layers.66.self_attn.v_proj", | |
| "model.layers.67.mlp.down_proj", | |
| "model.layers.67.mlp.gate_up_proj", | |
| "model.layers.67.mlp.router.gate", | |
| "model.layers.67.mlp.shared_mlp.down_proj", | |
| "model.layers.67.mlp.shared_mlp.gate_proj", | |
| "model.layers.67.mlp.shared_mlp.up_proj", | |
| "model.layers.67.self_attn.k_proj", | |
| "model.layers.67.self_attn.o_proj", | |
| "model.layers.67.self_attn.q_proj", | |
| "model.layers.67.self_attn.v_proj", | |
| "model.layers.68.mlp.down_proj", | |
| "model.layers.68.mlp.gate_up_proj", | |
| "model.layers.68.mlp.router.gate", | |
| "model.layers.68.mlp.shared_mlp.down_proj", | |
| "model.layers.68.mlp.shared_mlp.gate_proj", | |
| "model.layers.68.mlp.shared_mlp.up_proj", | |
| "model.layers.68.self_attn.k_proj", | |
| "model.layers.68.self_attn.o_proj", | |
| "model.layers.68.self_attn.q_proj", | |
| "model.layers.68.self_attn.v_proj", | |
| "model.layers.69.mlp.down_proj", | |
| "model.layers.69.mlp.gate_up_proj", | |
| "model.layers.69.mlp.router.gate", | |
| "model.layers.69.mlp.shared_mlp.down_proj", | |
| "model.layers.69.mlp.shared_mlp.gate_proj", | |
| "model.layers.69.mlp.shared_mlp.up_proj", | |
| "model.layers.69.self_attn.k_proj", | |
| "model.layers.69.self_attn.o_proj", | |
| "model.layers.69.self_attn.q_proj", | |
| "model.layers.69.self_attn.v_proj", | |
| "model.layers.7.mlp.down_proj", | |
| "model.layers.7.mlp.gate_up_proj", | |
| "model.layers.7.mlp.router.gate", | |
| "model.layers.7.mlp.shared_mlp.down_proj", | |
| "model.layers.7.mlp.shared_mlp.gate_proj", | |
| "model.layers.7.mlp.shared_mlp.up_proj", | |
| "model.layers.7.self_attn.k_proj", | |
| "model.layers.7.self_attn.o_proj", | |
| "model.layers.7.self_attn.q_proj", | |
| "model.layers.7.self_attn.v_proj", | |
| "model.layers.70.mlp.down_proj", | |
| "model.layers.70.mlp.gate_up_proj", | |
| "model.layers.70.mlp.router.gate", | |
| "model.layers.70.mlp.shared_mlp.down_proj", | |
| "model.layers.70.mlp.shared_mlp.gate_proj", | |
| "model.layers.70.mlp.shared_mlp.up_proj", | |
| "model.layers.70.self_attn.k_proj", | |
| "model.layers.70.self_attn.o_proj", | |
| "model.layers.70.self_attn.q_proj", | |
| "model.layers.70.self_attn.v_proj", | |
| "model.layers.71.mlp.down_proj", | |
| "model.layers.71.mlp.gate_up_proj", | |
| "model.layers.71.mlp.router.gate", | |
| "model.layers.71.mlp.shared_mlp.down_proj", | |
| "model.layers.71.mlp.shared_mlp.gate_proj", | |
| "model.layers.71.mlp.shared_mlp.up_proj", | |
| "model.layers.71.self_attn.k_proj", | |
| "model.layers.71.self_attn.o_proj", | |
| "model.layers.71.self_attn.q_proj", | |
| "model.layers.71.self_attn.v_proj", | |
| "model.layers.72.mlp.down_proj", | |
| "model.layers.72.mlp.gate_up_proj", | |
| "model.layers.72.mlp.router.gate", | |
| "model.layers.72.mlp.shared_mlp.down_proj", | |
| "model.layers.72.mlp.shared_mlp.gate_proj", | |
| "model.layers.72.mlp.shared_mlp.up_proj", | |
| "model.layers.72.self_attn.k_proj", | |
| "model.layers.72.self_attn.o_proj", | |
| "model.layers.72.self_attn.q_proj", | |
| "model.layers.72.self_attn.v_proj", | |
| "model.layers.73.mlp.down_proj", | |
| "model.layers.73.mlp.gate_up_proj", | |
| "model.layers.73.mlp.router.gate", | |
| "model.layers.73.mlp.shared_mlp.down_proj", | |
| "model.layers.73.mlp.shared_mlp.gate_proj", | |
| "model.layers.73.mlp.shared_mlp.up_proj", | |
| "model.layers.73.self_attn.k_proj", | |
| "model.layers.73.self_attn.o_proj", | |
| "model.layers.73.self_attn.q_proj", | |
| "model.layers.73.self_attn.v_proj", | |
| "model.layers.74.mlp.down_proj", | |
| "model.layers.74.mlp.gate_up_proj", | |
| "model.layers.74.mlp.router.gate", | |
| "model.layers.74.mlp.shared_mlp.down_proj", | |
| "model.layers.74.mlp.shared_mlp.gate_proj", | |
| "model.layers.74.mlp.shared_mlp.up_proj", | |
| "model.layers.74.self_attn.k_proj", | |
| "model.layers.74.self_attn.o_proj", | |
| "model.layers.74.self_attn.q_proj", | |
| "model.layers.74.self_attn.v_proj", | |
| "model.layers.75.mlp.down_proj", | |
| "model.layers.75.mlp.gate_up_proj", | |
| "model.layers.75.mlp.router.gate", | |
| "model.layers.75.mlp.shared_mlp.down_proj", | |
| "model.layers.75.mlp.shared_mlp.gate_proj", | |
| "model.layers.75.mlp.shared_mlp.up_proj", | |
| "model.layers.75.self_attn.k_proj", | |
| "model.layers.75.self_attn.o_proj", | |
| "model.layers.75.self_attn.q_proj", | |
| "model.layers.75.self_attn.v_proj", | |
| "model.layers.76.mlp.down_proj", | |
| "model.layers.76.mlp.gate_up_proj", | |
| "model.layers.76.mlp.router.gate", | |
| "model.layers.76.mlp.shared_mlp.down_proj", | |
| "model.layers.76.mlp.shared_mlp.gate_proj", | |
| "model.layers.76.mlp.shared_mlp.up_proj", | |
| "model.layers.76.self_attn.k_proj", | |
| "model.layers.76.self_attn.o_proj", | |
| "model.layers.76.self_attn.q_proj", | |
| "model.layers.76.self_attn.v_proj", | |
| "model.layers.77.mlp.down_proj", | |
| "model.layers.77.mlp.gate_up_proj", | |
| "model.layers.77.mlp.router.gate", | |
| "model.layers.77.mlp.shared_mlp.down_proj", | |
| "model.layers.77.mlp.shared_mlp.gate_proj", | |
| "model.layers.77.mlp.shared_mlp.up_proj", | |
| "model.layers.77.self_attn.k_proj", | |
| "model.layers.77.self_attn.o_proj", | |
| "model.layers.77.self_attn.q_proj", | |
| "model.layers.77.self_attn.v_proj", | |
| "model.layers.78.mlp.down_proj", | |
| "model.layers.78.mlp.gate_up_proj", | |
| "model.layers.78.mlp.router.gate", | |
| "model.layers.78.mlp.shared_mlp.down_proj", | |
| "model.layers.78.mlp.shared_mlp.gate_proj", | |
| "model.layers.78.mlp.shared_mlp.up_proj", | |
| "model.layers.78.self_attn.k_proj", | |
| "model.layers.78.self_attn.o_proj", | |
| "model.layers.78.self_attn.q_proj", | |
| "model.layers.78.self_attn.v_proj", | |
| "model.layers.79.mlp.down_proj", | |
| "model.layers.79.mlp.gate_up_proj", | |
| "model.layers.79.mlp.router.gate", | |
| "model.layers.79.mlp.shared_mlp.down_proj", | |
| "model.layers.79.mlp.shared_mlp.gate_proj", | |
| "model.layers.79.mlp.shared_mlp.up_proj", | |
| "model.layers.79.self_attn.k_proj", | |
| "model.layers.79.self_attn.o_proj", | |
| "model.layers.79.self_attn.q_proj", | |
| "model.layers.79.self_attn.v_proj", | |
| "model.layers.8.mlp.down_proj", | |
| "model.layers.8.mlp.gate_up_proj", | |
| "model.layers.8.mlp.router.gate", | |
| "model.layers.8.mlp.shared_mlp.down_proj", | |
| "model.layers.8.mlp.shared_mlp.gate_proj", | |
| "model.layers.8.mlp.shared_mlp.up_proj", | |
| "model.layers.8.self_attn.k_proj", | |
| "model.layers.8.self_attn.o_proj", | |
| "model.layers.8.self_attn.q_proj", | |
| "model.layers.8.self_attn.v_proj", | |
| "model.layers.80.eh_proj", | |
| "model.layers.80.mlp.down_proj", | |
| "model.layers.80.mlp.gate_up_proj", | |
| "model.layers.80.mlp.router.gate", | |
| "model.layers.80.mlp.shared_mlp.down_proj", | |
| "model.layers.80.mlp.shared_mlp.gate_proj", | |
| "model.layers.80.mlp.shared_mlp.up_proj", | |
| "model.layers.80.self_attn.k_proj", | |
| "model.layers.80.self_attn.o_proj", | |
| "model.layers.80.self_attn.q_proj", | |
| "model.layers.80.self_attn.v_proj", | |
| "model.layers.9.mlp.down_proj", | |
| "model.layers.9.mlp.gate_up_proj", | |
| "model.layers.9.mlp.router.gate", | |
| "model.layers.9.mlp.shared_mlp.down_proj", | |
| "model.layers.9.mlp.shared_mlp.gate_proj", | |
| "model.layers.9.mlp.shared_mlp.up_proj", | |
| "model.layers.9.self_attn.k_proj", | |
| "model.layers.9.self_attn.o_proj", | |
| "model.layers.9.self_attn.q_proj", | |
| "model.layers.9.self_attn.v_proj" | |
| ] | |
| } | |
| } | |