Upload model

config.json

@@ -0,0 +1,88 @@
+{
+  "_name_or_path": "./compacter-final",
+  "adapters": {
+    "adapters": {
+      "orca": "ebb04f19c89ca4ba"
+    },
+    "config_map": {
+      "ebb04f19c89ca4ba": {
+        "adapter_residual_before_ln": false,
+        "cross_adapter": false,
+        "factorized_phm_W": true,
+        "factorized_phm_rule": false,
+        "hypercomplex_nonlinearity": "glorot-uniform",
+        "init_weights": "bert",
+        "inv_adapter": null,
+        "inv_adapter_reduction_factor": null,
+        "is_parallel": false,
+        "learn_phm": true,
+        "leave_out": [],
+        "ln_after": false,
+        "ln_before": false,
+        "mh_adapter": false,
+        "non_linearity": "gelu",
+        "original_ln_after": true,
+        "original_ln_before": true,
+        "output_adapter": true,
+        "phm_bias": true,
+        "phm_c_init": "normal",
+        "phm_dim": 4,
+        "phm_init_range": 0.0001,
+        "phm_layer": true,
+        "phm_rank": 64,
+        "reduction_factor": 4,
+        "residual_before_ln": true,
+        "scaling": 1.0,
+        "shared_W_phm": false,
+        "shared_phm_rule": true,
+        "use_gating": false
+      }
+    },
+    "fusion_config_map": {},
+    "fusions": {}
+  },
+  "architectures": [
+    "LlamaAdapterModel"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 32013,
+  "custom_heads": {},
+  "eos_token_id": 32021,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "id2label": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "label2id": null,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "prediction_heads": {
+    "default": {
+      "activation_function": null,
+      "bias": false,
+      "dropout_prob": null,
+      "embedding_size": 2048,
+      "head_type": "causal_lm",
+      "label2id": null,
+      "layer_norm": false,
+      "layers": 1,
+      "shift_labels": true,
+      "vocab_size": 32256
+    }
+  },
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "type": "linear"
+  },
+  "rope_theta": 100000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32256
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 32013,
+  "eos_token_id": 32021,
+  "transformers_version": "4.35.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4e1f8648cc9c8e33fc7748cdf78af621ac9a53038692820317e628c8102ac74
+size 5000003920

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eb93d1c0964c471b77c9c86ae6cc49b818570323715b93bdd7199670b001895
+size 417632296

model.safetensors.index.json

@@ -0,0 +1,371 @@
+{
+  "metadata": {
+    "total_size": 5417591040
+  },
+  "weight_map": {
+    "heads.default.0.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.0.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.0.output_adapters.adapters.orca.adapter_down.0.b": "model-00001-of-00002.safetensors",
+    "model.layers.0.output_adapters.adapters.orca.adapter_up.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.0.output_adapters.adapters.orca.adapter_up.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.0.output_adapters.adapters.orca.adapter_up.b": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.1.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.1.output_adapters.adapters.orca.adapter_down.0.b": "model-00001-of-00002.safetensors",
+    "model.layers.1.output_adapters.adapters.orca.adapter_up.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.1.output_adapters.adapters.orca.adapter_up.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.1.output_adapters.adapters.orca.adapter_up.b": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.10.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.10.output_adapters.adapters.orca.adapter_down.0.b": "model-00001-of-00002.safetensors",
+    "model.layers.10.output_adapters.adapters.orca.adapter_up.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.10.output_adapters.adapters.orca.adapter_up.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.10.output_adapters.adapters.orca.adapter_up.b": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.11.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.11.output_adapters.adapters.orca.adapter_down.0.b": "model-00001-of-00002.safetensors",
+    "model.layers.11.output_adapters.adapters.orca.adapter_up.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.11.output_adapters.adapters.orca.adapter_up.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.11.output_adapters.adapters.orca.adapter_up.b": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.12.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.12.output_adapters.adapters.orca.adapter_down.0.b": "model-00001-of-00002.safetensors",
+    "model.layers.12.output_adapters.adapters.orca.adapter_up.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.12.output_adapters.adapters.orca.adapter_up.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.12.output_adapters.adapters.orca.adapter_up.b": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.13.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.13.output_adapters.adapters.orca.adapter_down.0.b": "model-00001-of-00002.safetensors",
+    "model.layers.13.output_adapters.adapters.orca.adapter_up.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.13.output_adapters.adapters.orca.adapter_up.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.13.output_adapters.adapters.orca.adapter_up.b": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.14.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.14.output_adapters.adapters.orca.adapter_down.0.b": "model-00001-of-00002.safetensors",
+    "model.layers.14.output_adapters.adapters.orca.adapter_up.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.14.output_adapters.adapters.orca.adapter_up.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.14.output_adapters.adapters.orca.adapter_up.b": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.15.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.15.output_adapters.adapters.orca.adapter_down.0.b": "model-00001-of-00002.safetensors",
+    "model.layers.15.output_adapters.adapters.orca.adapter_up.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.15.output_adapters.adapters.orca.adapter_up.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.15.output_adapters.adapters.orca.adapter_up.b": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.16.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.16.output_adapters.adapters.orca.adapter_down.0.b": "model-00001-of-00002.safetensors",
+    "model.layers.16.output_adapters.adapters.orca.adapter_up.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.16.output_adapters.adapters.orca.adapter_up.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.16.output_adapters.adapters.orca.adapter_up.b": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.17.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.17.output_adapters.adapters.orca.adapter_down.0.b": "model-00001-of-00002.safetensors",
+    "model.layers.17.output_adapters.adapters.orca.adapter_up.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.17.output_adapters.adapters.orca.adapter_up.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.17.output_adapters.adapters.orca.adapter_up.b": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.18.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.18.output_adapters.adapters.orca.adapter_down.0.b": "model-00001-of-00002.safetensors",
+    "model.layers.18.output_adapters.adapters.orca.adapter_up.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.18.output_adapters.adapters.orca.adapter_up.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.18.output_adapters.adapters.orca.adapter_up.b": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.19.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.19.output_adapters.adapters.orca.adapter_down.0.b": "model-00001-of-00002.safetensors",
+    "model.layers.19.output_adapters.adapters.orca.adapter_up.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.19.output_adapters.adapters.orca.adapter_up.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.19.output_adapters.adapters.orca.adapter_up.b": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.2.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.2.output_adapters.adapters.orca.adapter_down.0.b": "model-00001-of-00002.safetensors",
+    "model.layers.2.output_adapters.adapters.orca.adapter_up.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.2.output_adapters.adapters.orca.adapter_up.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.2.output_adapters.adapters.orca.adapter_up.b": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.20.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.20.output_adapters.adapters.orca.adapter_down.0.b": "model-00001-of-00002.safetensors",
+    "model.layers.20.output_adapters.adapters.orca.adapter_up.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.20.output_adapters.adapters.orca.adapter_up.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.20.output_adapters.adapters.orca.adapter_up.b": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.21.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.21.output_adapters.adapters.orca.adapter_down.0.b": "model-00001-of-00002.safetensors",
+    "model.layers.21.output_adapters.adapters.orca.adapter_up.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.21.output_adapters.adapters.orca.adapter_up.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.21.output_adapters.adapters.orca.adapter_up.b": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.22.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.22.output_adapters.adapters.orca.adapter_down.0.b": "model-00001-of-00002.safetensors",
+    "model.layers.22.output_adapters.adapters.orca.adapter_up.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.22.output_adapters.adapters.orca.adapter_up.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.22.output_adapters.adapters.orca.adapter_up.b": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00002-of-00002.safetensors",
+    "model.layers.23.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00002-of-00002.safetensors",
+    "model.layers.23.output_adapters.adapters.orca.adapter_down.0.b": "model-00002-of-00002.safetensors",
+    "model.layers.23.output_adapters.adapters.orca.adapter_up.W_left": "model-00002-of-00002.safetensors",
+    "model.layers.23.output_adapters.adapters.orca.adapter_up.W_right": "model-00002-of-00002.safetensors",
+    "model.layers.23.output_adapters.adapters.orca.adapter_up.b": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.3.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.3.output_adapters.adapters.orca.adapter_down.0.b": "model-00001-of-00002.safetensors",
+    "model.layers.3.output_adapters.adapters.orca.adapter_up.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.3.output_adapters.adapters.orca.adapter_up.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.3.output_adapters.adapters.orca.adapter_up.b": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.4.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.4.output_adapters.adapters.orca.adapter_down.0.b": "model-00001-of-00002.safetensors",
+    "model.layers.4.output_adapters.adapters.orca.adapter_up.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.4.output_adapters.adapters.orca.adapter_up.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.4.output_adapters.adapters.orca.adapter_up.b": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.5.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.5.output_adapters.adapters.orca.adapter_down.0.b": "model-00001-of-00002.safetensors",
+    "model.layers.5.output_adapters.adapters.orca.adapter_up.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.5.output_adapters.adapters.orca.adapter_up.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.5.output_adapters.adapters.orca.adapter_up.b": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.6.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.6.output_adapters.adapters.orca.adapter_down.0.b": "model-00001-of-00002.safetensors",
+    "model.layers.6.output_adapters.adapters.orca.adapter_up.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.6.output_adapters.adapters.orca.adapter_up.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.6.output_adapters.adapters.orca.adapter_up.b": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.7.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.7.output_adapters.adapters.orca.adapter_down.0.b": "model-00001-of-00002.safetensors",
+    "model.layers.7.output_adapters.adapters.orca.adapter_up.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.7.output_adapters.adapters.orca.adapter_up.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.7.output_adapters.adapters.orca.adapter_up.b": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.8.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.8.output_adapters.adapters.orca.adapter_down.0.b": "model-00001-of-00002.safetensors",
+    "model.layers.8.output_adapters.adapters.orca.adapter_up.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.8.output_adapters.adapters.orca.adapter_up.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.8.output_adapters.adapters.orca.adapter_up.b": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.output_adapters.adapters.orca.adapter_down.0.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.9.output_adapters.adapters.orca.adapter_down.0.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.9.output_adapters.adapters.orca.adapter_down.0.b": "model-00001-of-00002.safetensors",
+    "model.layers.9.output_adapters.adapters.orca.adapter_up.W_left": "model-00001-of-00002.safetensors",
+    "model.layers.9.output_adapters.adapters.orca.adapter_up.W_right": "model-00001-of-00002.safetensors",
+    "model.layers.9.output_adapters.adapters.orca.adapter_up.b": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "model.shared_parameters.orca.phm_rule": "model-00002-of-00002.safetensors"
+  }
+}