chaitalibh's picture
Upload merged model and adapter folders
74fdd57 verified
Raw History Blame Contribute Delete
19.8 kB
{
"source": "../models/C_SERVER",
"source_revision": null,
"checkpoint_inspection": {
"source": "../models/C_SERVER",
"checkpoint_type": "full_or_merged_model",
"revision": null,
"is_local": true,
"has_adapter_config": false,
"has_model_config": true,
"weight_files": [
"model-00001-of-00005.safetensors",
"model-00002-of-00005.safetensors",
"model-00003-of-00005.safetensors",
"model-00004-of-00005.safetensors",
"model-00005-of-00005.safetensors"
],
"base_model_name_or_path": null,
"model_type": "gemma3",
"architectures": [
"Gemma3ForConditionalGeneration"
]
},
"f2f_handling": "source_is_full_or_merged_model_loaded_unchanged",
"grpo_adapter_name": "default",
"grpo_adapter_merged": false,
"original_checkpoint_modified": false,
"load_in_4bit": false,
"dtype_requested": "bfloat16",
"lora": {
"r": 16,
"alpha": 32,
"dropout": 0.05,
"target_module_paths": [
"model.language_model.layers.0.mlp.down_proj",
"model.language_model.layers.0.mlp.gate_proj",
"model.language_model.layers.0.mlp.up_proj",
"model.language_model.layers.0.self_attn.k_proj",
"model.language_model.layers.0.self_attn.o_proj",
"model.language_model.layers.0.self_attn.q_proj",
"model.language_model.layers.0.self_attn.v_proj",
"model.language_model.layers.1.mlp.down_proj",
"model.language_model.layers.1.mlp.gate_proj",
"model.language_model.layers.1.mlp.up_proj",
"model.language_model.layers.1.self_attn.k_proj",
"model.language_model.layers.1.self_attn.o_proj",
"model.language_model.layers.1.self_attn.q_proj",
"model.language_model.layers.1.self_attn.v_proj",
"model.language_model.layers.10.mlp.down_proj",
"model.language_model.layers.10.mlp.gate_proj",
"model.language_model.layers.10.mlp.up_proj",
"model.language_model.layers.10.self_attn.k_proj",
"model.language_model.layers.10.self_attn.o_proj",
"model.language_model.layers.10.self_attn.q_proj",
"model.language_model.layers.10.self_attn.v_proj",
"model.language_model.layers.11.mlp.down_proj",
"model.language_model.layers.11.mlp.gate_proj",
"model.language_model.layers.11.mlp.up_proj",
"model.language_model.layers.11.self_attn.k_proj",
"model.language_model.layers.11.self_attn.o_proj",
"model.language_model.layers.11.self_attn.q_proj",
"model.language_model.layers.11.self_attn.v_proj",
"model.language_model.layers.12.mlp.down_proj",
"model.language_model.layers.12.mlp.gate_proj",
"model.language_model.layers.12.mlp.up_proj",
"model.language_model.layers.12.self_attn.k_proj",
"model.language_model.layers.12.self_attn.o_proj",
"model.language_model.layers.12.self_attn.q_proj",
"model.language_model.layers.12.self_attn.v_proj",
"model.language_model.layers.13.mlp.down_proj",
"model.language_model.layers.13.mlp.gate_proj",
"model.language_model.layers.13.mlp.up_proj",
"model.language_model.layers.13.self_attn.k_proj",
"model.language_model.layers.13.self_attn.o_proj",
"model.language_model.layers.13.self_attn.q_proj",
"model.language_model.layers.13.self_attn.v_proj",
"model.language_model.layers.14.mlp.down_proj",
"model.language_model.layers.14.mlp.gate_proj",
"model.language_model.layers.14.mlp.up_proj",
"model.language_model.layers.14.self_attn.k_proj",
"model.language_model.layers.14.self_attn.o_proj",
"model.language_model.layers.14.self_attn.q_proj",
"model.language_model.layers.14.self_attn.v_proj",
"model.language_model.layers.15.mlp.down_proj",
"model.language_model.layers.15.mlp.gate_proj",
"model.language_model.layers.15.mlp.up_proj",
"model.language_model.layers.15.self_attn.k_proj",
"model.language_model.layers.15.self_attn.o_proj",
"model.language_model.layers.15.self_attn.q_proj",
"model.language_model.layers.15.self_attn.v_proj",
"model.language_model.layers.16.mlp.down_proj",
"model.language_model.layers.16.mlp.gate_proj",
"model.language_model.layers.16.mlp.up_proj",
"model.language_model.layers.16.self_attn.k_proj",
"model.language_model.layers.16.self_attn.o_proj",
"model.language_model.layers.16.self_attn.q_proj",
"model.language_model.layers.16.self_attn.v_proj",
"model.language_model.layers.17.mlp.down_proj",
"model.language_model.layers.17.mlp.gate_proj",
"model.language_model.layers.17.mlp.up_proj",
"model.language_model.layers.17.self_attn.k_proj",
"model.language_model.layers.17.self_attn.o_proj",
"model.language_model.layers.17.self_attn.q_proj",
"model.language_model.layers.17.self_attn.v_proj",
"model.language_model.layers.18.mlp.down_proj",
"model.language_model.layers.18.mlp.gate_proj",
"model.language_model.layers.18.mlp.up_proj",
"model.language_model.layers.18.self_attn.k_proj",
"model.language_model.layers.18.self_attn.o_proj",
"model.language_model.layers.18.self_attn.q_proj",
"model.language_model.layers.18.self_attn.v_proj",
"model.language_model.layers.19.mlp.down_proj",
"model.language_model.layers.19.mlp.gate_proj",
"model.language_model.layers.19.mlp.up_proj",
"model.language_model.layers.19.self_attn.k_proj",
"model.language_model.layers.19.self_attn.o_proj",
"model.language_model.layers.19.self_attn.q_proj",
"model.language_model.layers.19.self_attn.v_proj",
"model.language_model.layers.2.mlp.down_proj",
"model.language_model.layers.2.mlp.gate_proj",
"model.language_model.layers.2.mlp.up_proj",
"model.language_model.layers.2.self_attn.k_proj",
"model.language_model.layers.2.self_attn.o_proj",
"model.language_model.layers.2.self_attn.q_proj",
"model.language_model.layers.2.self_attn.v_proj",
"model.language_model.layers.20.mlp.down_proj",
"model.language_model.layers.20.mlp.gate_proj",
"model.language_model.layers.20.mlp.up_proj",
"model.language_model.layers.20.self_attn.k_proj",
"model.language_model.layers.20.self_attn.o_proj",
"model.language_model.layers.20.self_attn.q_proj",
"model.language_model.layers.20.self_attn.v_proj",
"model.language_model.layers.21.mlp.down_proj",
"model.language_model.layers.21.mlp.gate_proj",
"model.language_model.layers.21.mlp.up_proj",
"model.language_model.layers.21.self_attn.k_proj",
"model.language_model.layers.21.self_attn.o_proj",
"model.language_model.layers.21.self_attn.q_proj",
"model.language_model.layers.21.self_attn.v_proj",
"model.language_model.layers.22.mlp.down_proj",
"model.language_model.layers.22.mlp.gate_proj",
"model.language_model.layers.22.mlp.up_proj",
"model.language_model.layers.22.self_attn.k_proj",
"model.language_model.layers.22.self_attn.o_proj",
"model.language_model.layers.22.self_attn.q_proj",
"model.language_model.layers.22.self_attn.v_proj",
"model.language_model.layers.23.mlp.down_proj",
"model.language_model.layers.23.mlp.gate_proj",
"model.language_model.layers.23.mlp.up_proj",
"model.language_model.layers.23.self_attn.k_proj",
"model.language_model.layers.23.self_attn.o_proj",
"model.language_model.layers.23.self_attn.q_proj",
"model.language_model.layers.23.self_attn.v_proj",
"model.language_model.layers.24.mlp.down_proj",
"model.language_model.layers.24.mlp.gate_proj",
"model.language_model.layers.24.mlp.up_proj",
"model.language_model.layers.24.self_attn.k_proj",
"model.language_model.layers.24.self_attn.o_proj",
"model.language_model.layers.24.self_attn.q_proj",
"model.language_model.layers.24.self_attn.v_proj",
"model.language_model.layers.25.mlp.down_proj",
"model.language_model.layers.25.mlp.gate_proj",
"model.language_model.layers.25.mlp.up_proj",
"model.language_model.layers.25.self_attn.k_proj",
"model.language_model.layers.25.self_attn.o_proj",
"model.language_model.layers.25.self_attn.q_proj",
"model.language_model.layers.25.self_attn.v_proj",
"model.language_model.layers.26.mlp.down_proj",
"model.language_model.layers.26.mlp.gate_proj",
"model.language_model.layers.26.mlp.up_proj",
"model.language_model.layers.26.self_attn.k_proj",
"model.language_model.layers.26.self_attn.o_proj",
"model.language_model.layers.26.self_attn.q_proj",
"model.language_model.layers.26.self_attn.v_proj",
"model.language_model.layers.27.mlp.down_proj",
"model.language_model.layers.27.mlp.gate_proj",
"model.language_model.layers.27.mlp.up_proj",
"model.language_model.layers.27.self_attn.k_proj",
"model.language_model.layers.27.self_attn.o_proj",
"model.language_model.layers.27.self_attn.q_proj",
"model.language_model.layers.27.self_attn.v_proj",
"model.language_model.layers.28.mlp.down_proj",
"model.language_model.layers.28.mlp.gate_proj",
"model.language_model.layers.28.mlp.up_proj",
"model.language_model.layers.28.self_attn.k_proj",
"model.language_model.layers.28.self_attn.o_proj",
"model.language_model.layers.28.self_attn.q_proj",
"model.language_model.layers.28.self_attn.v_proj",
"model.language_model.layers.29.mlp.down_proj",
"model.language_model.layers.29.mlp.gate_proj",
"model.language_model.layers.29.mlp.up_proj",
"model.language_model.layers.29.self_attn.k_proj",
"model.language_model.layers.29.self_attn.o_proj",
"model.language_model.layers.29.self_attn.q_proj",
"model.language_model.layers.29.self_attn.v_proj",
"model.language_model.layers.3.mlp.down_proj",
"model.language_model.layers.3.mlp.gate_proj",
"model.language_model.layers.3.mlp.up_proj",
"model.language_model.layers.3.self_attn.k_proj",
"model.language_model.layers.3.self_attn.o_proj",
"model.language_model.layers.3.self_attn.q_proj",
"model.language_model.layers.3.self_attn.v_proj",
"model.language_model.layers.30.mlp.down_proj",
"model.language_model.layers.30.mlp.gate_proj",
"model.language_model.layers.30.mlp.up_proj",
"model.language_model.layers.30.self_attn.k_proj",
"model.language_model.layers.30.self_attn.o_proj",
"model.language_model.layers.30.self_attn.q_proj",
"model.language_model.layers.30.self_attn.v_proj",
"model.language_model.layers.31.mlp.down_proj",
"model.language_model.layers.31.mlp.gate_proj",
"model.language_model.layers.31.mlp.up_proj",
"model.language_model.layers.31.self_attn.k_proj",
"model.language_model.layers.31.self_attn.o_proj",
"model.language_model.layers.31.self_attn.q_proj",
"model.language_model.layers.31.self_attn.v_proj",
"model.language_model.layers.32.mlp.down_proj",
"model.language_model.layers.32.mlp.gate_proj",
"model.language_model.layers.32.mlp.up_proj",
"model.language_model.layers.32.self_attn.k_proj",
"model.language_model.layers.32.self_attn.o_proj",
"model.language_model.layers.32.self_attn.q_proj",
"model.language_model.layers.32.self_attn.v_proj",
"model.language_model.layers.33.mlp.down_proj",
"model.language_model.layers.33.mlp.gate_proj",
"model.language_model.layers.33.mlp.up_proj",
"model.language_model.layers.33.self_attn.k_proj",
"model.language_model.layers.33.self_attn.o_proj",
"model.language_model.layers.33.self_attn.q_proj",
"model.language_model.layers.33.self_attn.v_proj",
"model.language_model.layers.34.mlp.down_proj",
"model.language_model.layers.34.mlp.gate_proj",
"model.language_model.layers.34.mlp.up_proj",
"model.language_model.layers.34.self_attn.k_proj",
"model.language_model.layers.34.self_attn.o_proj",
"model.language_model.layers.34.self_attn.q_proj",
"model.language_model.layers.34.self_attn.v_proj",
"model.language_model.layers.35.mlp.down_proj",
"model.language_model.layers.35.mlp.gate_proj",
"model.language_model.layers.35.mlp.up_proj",
"model.language_model.layers.35.self_attn.k_proj",
"model.language_model.layers.35.self_attn.o_proj",
"model.language_model.layers.35.self_attn.q_proj",
"model.language_model.layers.35.self_attn.v_proj",
"model.language_model.layers.36.mlp.down_proj",
"model.language_model.layers.36.mlp.gate_proj",
"model.language_model.layers.36.mlp.up_proj",
"model.language_model.layers.36.self_attn.k_proj",
"model.language_model.layers.36.self_attn.o_proj",
"model.language_model.layers.36.self_attn.q_proj",
"model.language_model.layers.36.self_attn.v_proj",
"model.language_model.layers.37.mlp.down_proj",
"model.language_model.layers.37.mlp.gate_proj",
"model.language_model.layers.37.mlp.up_proj",
"model.language_model.layers.37.self_attn.k_proj",
"model.language_model.layers.37.self_attn.o_proj",
"model.language_model.layers.37.self_attn.q_proj",
"model.language_model.layers.37.self_attn.v_proj",
"model.language_model.layers.38.mlp.down_proj",
"model.language_model.layers.38.mlp.gate_proj",
"model.language_model.layers.38.mlp.up_proj",
"model.language_model.layers.38.self_attn.k_proj",
"model.language_model.layers.38.self_attn.o_proj",
"model.language_model.layers.38.self_attn.q_proj",
"model.language_model.layers.38.self_attn.v_proj",
"model.language_model.layers.39.mlp.down_proj",
"model.language_model.layers.39.mlp.gate_proj",
"model.language_model.layers.39.mlp.up_proj",
"model.language_model.layers.39.self_attn.k_proj",
"model.language_model.layers.39.self_attn.o_proj",
"model.language_model.layers.39.self_attn.q_proj",
"model.language_model.layers.39.self_attn.v_proj",
"model.language_model.layers.4.mlp.down_proj",
"model.language_model.layers.4.mlp.gate_proj",
"model.language_model.layers.4.mlp.up_proj",
"model.language_model.layers.4.self_attn.k_proj",
"model.language_model.layers.4.self_attn.o_proj",
"model.language_model.layers.4.self_attn.q_proj",
"model.language_model.layers.4.self_attn.v_proj",
"model.language_model.layers.40.mlp.down_proj",
"model.language_model.layers.40.mlp.gate_proj",
"model.language_model.layers.40.mlp.up_proj",
"model.language_model.layers.40.self_attn.k_proj",
"model.language_model.layers.40.self_attn.o_proj",
"model.language_model.layers.40.self_attn.q_proj",
"model.language_model.layers.40.self_attn.v_proj",
"model.language_model.layers.41.mlp.down_proj",
"model.language_model.layers.41.mlp.gate_proj",
"model.language_model.layers.41.mlp.up_proj",
"model.language_model.layers.41.self_attn.k_proj",
"model.language_model.layers.41.self_attn.o_proj",
"model.language_model.layers.41.self_attn.q_proj",
"model.language_model.layers.41.self_attn.v_proj",
"model.language_model.layers.42.mlp.down_proj",
"model.language_model.layers.42.mlp.gate_proj",
"model.language_model.layers.42.mlp.up_proj",
"model.language_model.layers.42.self_attn.k_proj",
"model.language_model.layers.42.self_attn.o_proj",
"model.language_model.layers.42.self_attn.q_proj",
"model.language_model.layers.42.self_attn.v_proj",
"model.language_model.layers.43.mlp.down_proj",
"model.language_model.layers.43.mlp.gate_proj",
"model.language_model.layers.43.mlp.up_proj",
"model.language_model.layers.43.self_attn.k_proj",
"model.language_model.layers.43.self_attn.o_proj",
"model.language_model.layers.43.self_attn.q_proj",
"model.language_model.layers.43.self_attn.v_proj",
"model.language_model.layers.44.mlp.down_proj",
"model.language_model.layers.44.mlp.gate_proj",
"model.language_model.layers.44.mlp.up_proj",
"model.language_model.layers.44.self_attn.k_proj",
"model.language_model.layers.44.self_attn.o_proj",
"model.language_model.layers.44.self_attn.q_proj",
"model.language_model.layers.44.self_attn.v_proj",
"model.language_model.layers.45.mlp.down_proj",
"model.language_model.layers.45.mlp.gate_proj",
"model.language_model.layers.45.mlp.up_proj",
"model.language_model.layers.45.self_attn.k_proj",
"model.language_model.layers.45.self_attn.o_proj",
"model.language_model.layers.45.self_attn.q_proj",
"model.language_model.layers.45.self_attn.v_proj",
"model.language_model.layers.46.mlp.down_proj",
"model.language_model.layers.46.mlp.gate_proj",
"model.language_model.layers.46.mlp.up_proj",
"model.language_model.layers.46.self_attn.k_proj",
"model.language_model.layers.46.self_attn.o_proj",
"model.language_model.layers.46.self_attn.q_proj",
"model.language_model.layers.46.self_attn.v_proj",
"model.language_model.layers.47.mlp.down_proj",
"model.language_model.layers.47.mlp.gate_proj",
"model.language_model.layers.47.mlp.up_proj",
"model.language_model.layers.47.self_attn.k_proj",
"model.language_model.layers.47.self_attn.o_proj",
"model.language_model.layers.47.self_attn.q_proj",
"model.language_model.layers.47.self_attn.v_proj",
"model.language_model.layers.5.mlp.down_proj",
"model.language_model.layers.5.mlp.gate_proj",
"model.language_model.layers.5.mlp.up_proj",
"model.language_model.layers.5.self_attn.k_proj",
"model.language_model.layers.5.self_attn.o_proj",
"model.language_model.layers.5.self_attn.q_proj",
"model.language_model.layers.5.self_attn.v_proj",
"model.language_model.layers.6.mlp.down_proj",
"model.language_model.layers.6.mlp.gate_proj",
"model.language_model.layers.6.mlp.up_proj",
"model.language_model.layers.6.self_attn.k_proj",
"model.language_model.layers.6.self_attn.o_proj",
"model.language_model.layers.6.self_attn.q_proj",
"model.language_model.layers.6.self_attn.v_proj",
"model.language_model.layers.7.mlp.down_proj",
"model.language_model.layers.7.mlp.gate_proj",
"model.language_model.layers.7.mlp.up_proj",
"model.language_model.layers.7.self_attn.k_proj",
"model.language_model.layers.7.self_attn.o_proj",
"model.language_model.layers.7.self_attn.q_proj",
"model.language_model.layers.7.self_attn.v_proj",
"model.language_model.layers.8.mlp.down_proj",
"model.language_model.layers.8.mlp.gate_proj",
"model.language_model.layers.8.mlp.up_proj",
"model.language_model.layers.8.self_attn.k_proj",
"model.language_model.layers.8.self_attn.o_proj",
"model.language_model.layers.8.self_attn.q_proj",
"model.language_model.layers.8.self_attn.v_proj",
"model.language_model.layers.9.mlp.down_proj",
"model.language_model.layers.9.mlp.gate_proj",
"model.language_model.layers.9.mlp.up_proj",
"model.language_model.layers.9.self_attn.k_proj",
"model.language_model.layers.9.self_attn.o_proj",
"model.language_model.layers.9.self_attn.q_proj",
"model.language_model.layers.9.self_attn.v_proj"
],
"target_suffixes": [
"down_proj",
"gate_proj",
"k_proj",
"o_proj",
"q_proj",
"up_proj",
"v_proj"
]
},
"parameters": {
"total_parameters": 12252795504,
"trainable_parameters": 65470464,
"trainable_percent": 0.5343308306959564
}
}