| { |
| "producer": { |
| "name": "modelopt", |
| "version": "0.44.0" |
| }, |
| "quantization": { |
| "quant_algo": "NVFP4", |
| "kv_cache_quant_algo": null, |
| "group_size": 16, |
| "exclude_modules": [ |
| "lm_head", |
| "model.language_model.layers.0.linear_attn.conv1d", |
| "model.language_model.layers.1.linear_attn.conv1d", |
| "model.language_model.layers.10.linear_attn.conv1d", |
| "model.language_model.layers.12.linear_attn.conv1d", |
| "model.language_model.layers.13.linear_attn.conv1d", |
| "model.language_model.layers.14.linear_attn.conv1d", |
| "model.language_model.layers.16.linear_attn.conv1d", |
| "model.language_model.layers.17.linear_attn.conv1d", |
| "model.language_model.layers.18.linear_attn.conv1d", |
| "model.language_model.layers.2.linear_attn.conv1d", |
| "model.language_model.layers.20.linear_attn.conv1d", |
| "model.language_model.layers.21.linear_attn.conv1d", |
| "model.language_model.layers.22.linear_attn.conv1d", |
| "model.language_model.layers.24.linear_attn.conv1d", |
| "model.language_model.layers.25.linear_attn.conv1d", |
| "model.language_model.layers.26.linear_attn.conv1d", |
| "model.language_model.layers.28.linear_attn.conv1d", |
| "model.language_model.layers.29.linear_attn.conv1d", |
| "model.language_model.layers.30.linear_attn.conv1d", |
| "model.language_model.layers.32.linear_attn.conv1d", |
| "model.language_model.layers.33.linear_attn.conv1d", |
| "model.language_model.layers.34.linear_attn.conv1d", |
| "model.language_model.layers.36.linear_attn.conv1d", |
| "model.language_model.layers.37.linear_attn.conv1d", |
| "model.language_model.layers.38.linear_attn.conv1d", |
| "model.language_model.layers.4.linear_attn.conv1d", |
| "model.language_model.layers.40.linear_attn.conv1d", |
| "model.language_model.layers.41.linear_attn.conv1d", |
| "model.language_model.layers.42.linear_attn.conv1d", |
| "model.language_model.layers.44.linear_attn.conv1d", |
| "model.language_model.layers.45.linear_attn.conv1d", |
| "model.language_model.layers.46.linear_attn.conv1d", |
| "model.language_model.layers.48.linear_attn.conv1d", |
| "model.language_model.layers.49.linear_attn.conv1d", |
| "model.language_model.layers.5.linear_attn.conv1d", |
| "model.language_model.layers.50.linear_attn.conv1d", |
| "model.language_model.layers.52.linear_attn.conv1d", |
| "model.language_model.layers.53.linear_attn.conv1d", |
| "model.language_model.layers.54.linear_attn.conv1d", |
| "model.language_model.layers.56.linear_attn.conv1d", |
| "model.language_model.layers.57.linear_attn.conv1d", |
| "model.language_model.layers.58.linear_attn.conv1d", |
| "model.language_model.layers.6.linear_attn.conv1d", |
| "model.language_model.layers.60.linear_attn.conv1d", |
| "model.language_model.layers.61.linear_attn.conv1d", |
| "model.language_model.layers.62.linear_attn.conv1d", |
| "model.language_model.layers.8.linear_attn.conv1d", |
| "model.language_model.layers.9.linear_attn.conv1d", |
| "model.visual*", |
| "mtp*", |
| "mtp.fc", |
| "mtp.layers.0.input_layernorm", |
| "mtp.layers.0.mlp.down_proj", |
| "mtp.layers.0.mlp.gate_proj", |
| "mtp.layers.0.mlp.up_proj", |
| "mtp.layers.0.post_attention_layernorm", |
| "mtp.layers.0.self_attn.k_norm", |
| "mtp.layers.0.self_attn.k_proj", |
| "mtp.layers.0.self_attn.o_proj", |
| "mtp.layers.0.self_attn.q_norm", |
| "mtp.layers.0.self_attn.q_proj", |
| "mtp.layers.0.self_attn.v_proj", |
| "mtp.norm", |
| "mtp.pre_fc_norm_embedding", |
| "mtp.pre_fc_norm_hidden" |
| ] |
| } |
| } |
