Upload folder using huggingface_hub

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10b4ddaa317b3600fbe01ff461a14fbd652117e1286881042094478acf659eac
+size 335699597

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "modalities": [
+    "document_gte"
+  ],
+  "modality_builder": "document_gte",
+  "model_cls": "MistralLMMForCausalLM",
+  "model_type": "mistral-lmm",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

model_named_parameters.txt

@@ -0,0 +1,755 @@
+base_model.model.model.embed_tokens.weight torch.Size([32000, 4096]) False
+base_model.model.model.layers.0.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.0.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.0.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.0.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.0.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.0.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.0.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.0.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.0.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.0.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.0.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.0.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.0.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.0.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.0.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.0.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.0.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.0.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.0.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.1.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.1.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.1.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.1.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.1.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.1.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.1.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.1.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.1.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.1.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.1.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.1.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.1.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.1.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.1.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.1.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.1.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.1.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.1.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.2.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.2.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.2.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.2.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.2.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.2.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.2.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.2.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.2.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.2.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.2.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.2.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.2.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.2.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.2.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.2.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.2.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.2.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.2.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.3.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.3.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.3.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.3.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.3.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.3.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.3.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.3.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.3.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.3.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.3.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.3.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.3.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.3.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.3.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.3.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.3.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.3.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.3.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.4.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.4.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.4.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.4.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.4.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.4.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.4.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.4.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.4.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.4.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.4.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.4.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.4.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.4.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.4.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.4.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.4.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.4.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.4.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.5.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.5.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.5.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.5.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.5.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.5.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.5.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.5.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.5.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.5.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.5.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.5.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.5.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.5.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.5.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.5.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.5.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.5.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.5.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.6.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.6.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.6.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.6.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.6.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.6.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.6.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.6.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.6.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.6.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.6.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.6.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.6.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.6.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.6.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.6.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.6.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.6.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.6.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.7.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.7.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.7.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.7.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.7.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.7.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.7.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.7.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.7.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.7.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.7.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.7.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.7.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.7.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.7.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.7.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.7.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.7.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.7.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.8.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.8.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.8.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.8.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.8.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.8.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.8.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.8.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.8.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.8.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.8.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.8.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.8.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.8.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.8.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.8.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.8.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.8.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.8.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.9.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.9.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.9.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.9.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.9.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.9.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.9.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.9.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.9.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.9.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.9.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.9.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.9.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.9.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.9.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.9.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.9.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.9.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.9.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.10.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.10.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.10.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.10.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.10.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.10.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.10.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.10.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.10.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.10.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.10.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.10.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.10.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.10.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.10.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.10.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.10.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.10.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.10.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.11.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.11.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.11.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.11.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.11.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.11.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.11.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.11.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.11.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.11.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.11.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.11.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.11.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.11.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.11.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.11.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.11.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.11.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.11.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.12.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.12.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.12.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.12.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.12.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.12.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.12.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.12.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.12.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.12.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.12.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.12.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.12.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.12.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.12.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.12.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.12.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.12.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.12.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.13.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.13.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.13.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.13.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.13.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.13.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.13.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.13.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.13.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.13.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.13.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.13.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.13.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.13.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.13.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.13.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.13.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.13.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.13.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.14.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.14.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.14.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.14.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.14.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.14.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.14.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.14.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.14.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.14.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.14.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.14.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.14.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.14.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.14.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.14.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.14.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.14.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.14.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.15.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.15.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.15.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.15.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.15.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.15.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.15.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.15.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.15.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.15.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.15.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.15.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.15.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.15.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.15.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.15.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.15.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.15.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.15.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.16.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.16.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.16.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.16.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.16.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.16.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.16.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.16.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.16.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.16.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.16.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.16.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.16.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.16.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.16.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.16.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.16.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.16.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.16.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.17.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.17.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.17.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.17.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.17.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.17.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.17.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.17.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.17.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.17.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.17.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.17.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.17.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.17.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.17.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.17.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.17.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.17.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.17.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.18.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.18.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.18.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.18.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.18.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.18.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.18.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.18.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.18.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.18.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.18.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.18.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.18.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.18.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.18.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.18.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.18.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.18.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.18.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.19.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.19.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.19.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.19.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.19.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.19.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.19.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.19.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.19.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.19.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.19.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.19.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.19.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.19.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.19.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.19.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.19.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.19.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.19.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.20.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.20.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.20.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.20.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.20.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.20.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.20.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.20.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.20.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.20.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.20.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.20.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.20.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.20.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.20.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.20.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.20.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.20.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.20.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.21.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.21.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.21.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.21.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.21.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.21.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.21.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.21.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.21.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.21.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.21.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.21.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.21.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.21.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.21.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.21.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.21.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.21.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.21.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.22.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.22.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.22.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.22.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.22.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.22.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.22.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.22.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.22.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.22.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.22.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.22.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.22.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.22.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.22.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.22.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.22.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.22.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.22.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.22.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.22.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.22.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.22.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.23.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.23.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.23.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.23.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.23.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.23.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.23.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.23.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.23.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.23.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.23.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.23.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.23.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.23.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.23.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.23.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.23.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.23.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.23.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.23.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.23.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.23.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.23.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.24.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.24.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.24.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.24.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.24.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.24.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.24.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.24.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.24.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.24.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.24.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.24.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.24.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.24.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.24.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.24.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.24.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.24.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.24.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.24.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.24.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.24.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.24.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.25.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.25.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.25.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.25.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.25.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.25.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.25.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.25.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.25.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.25.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.25.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.25.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.25.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.25.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.25.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.25.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.25.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.25.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.25.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.25.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.25.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.25.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.25.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.26.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.26.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.26.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.26.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.26.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.26.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.26.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.26.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.26.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.26.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.26.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.26.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.26.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.26.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.26.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.26.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.26.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.26.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.26.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.26.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.26.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.26.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.26.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.27.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.27.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.27.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.27.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.27.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.27.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.27.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.27.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.27.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.27.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.27.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.27.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.27.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.27.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.27.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.27.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.27.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.27.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.27.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.27.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.27.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.27.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.27.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.28.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.28.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.28.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.28.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.28.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.28.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.28.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.28.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.28.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.28.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.28.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.28.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.28.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.28.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.28.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.28.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.28.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.28.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.28.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.28.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.28.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.28.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.28.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.29.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.29.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.29.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.29.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.29.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.29.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.29.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.29.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.29.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.29.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.29.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.29.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.29.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.29.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.29.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.29.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.29.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.29.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.29.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.29.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.29.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.29.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.29.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.30.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.30.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.30.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.30.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.30.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.30.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.30.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.30.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.30.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.30.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.30.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.30.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.30.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.30.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.30.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.30.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.30.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.30.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.30.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.30.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.30.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.30.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.30.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.31.self_attn.q_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.31.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.31.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.31.self_attn.k_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.31.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.31.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.31.self_attn.v_proj.weight torch.Size([1024, 4096]) False
+base_model.model.model.layers.31.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.31.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True
+base_model.model.model.layers.31.self_attn.o_proj.weight torch.Size([4096, 4096]) False
+base_model.model.model.layers.31.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.31.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.31.mlp.gate_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.31.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.31.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.31.mlp.up_proj.weight torch.Size([14336, 4096]) False
+base_model.model.model.layers.31.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True
+base_model.model.model.layers.31.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True
+base_model.model.model.layers.31.mlp.down_proj.weight torch.Size([4096, 14336]) False
+base_model.model.model.layers.31.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True
+base_model.model.model.layers.31.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True
+base_model.model.model.layers.31.input_layernorm.weight torch.Size([4096]) False
+base_model.model.model.layers.31.post_attention_layernorm.weight torch.Size([4096]) False
+base_model.model.model.norm.weight torch.Size([4096]) False
+base_model.model.model.document_gte_lmm_projector.mlps.0.0.weight torch.Size([4096, 1024]) True
+base_model.model.model.document_gte_lmm_projector.mlps.0.0.bias torch.Size([4096]) True
+base_model.model.model.document_gte_lmm_projector.mlps.0.2.weight torch.Size([4096, 4096]) True
+base_model.model.model.document_gte_lmm_projector.mlps.0.2.bias torch.Size([4096]) True
+base_model.model.model.document_gte_lmm_projector.mlps.1.0.weight torch.Size([4096, 1024]) True
+base_model.model.model.document_gte_lmm_projector.mlps.1.0.bias torch.Size([4096]) True
+base_model.model.model.document_gte_lmm_projector.mlps.1.2.weight torch.Size([4096, 4096]) True
+base_model.model.model.document_gte_lmm_projector.mlps.1.2.bias torch.Size([4096]) True
+base_model.model.model.document_gte_lmm_projector.mlps.2.0.weight torch.Size([4096, 1024]) True
+base_model.model.model.document_gte_lmm_projector.mlps.2.0.bias torch.Size([4096]) True
+base_model.model.model.document_gte_lmm_projector.mlps.2.2.weight torch.Size([4096, 4096]) True
+base_model.model.model.document_gte_lmm_projector.mlps.2.2.bias torch.Size([4096]) True
+base_model.model.model.document_gte_lmm_projector.mlps.3.0.weight torch.Size([4096, 1024]) True
+base_model.model.model.document_gte_lmm_projector.mlps.3.0.bias torch.Size([4096]) True
+base_model.model.model.document_gte_lmm_projector.mlps.3.2.weight torch.Size([4096, 4096]) True
+base_model.model.model.document_gte_lmm_projector.mlps.3.2.bias torch.Size([4096]) True
+base_model.model.lm_head.weight torch.Size([32000, 4096]) False

non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd887e0701ded8ad2a318773816c6856154b491a5cd26527a406de663bc8e8ed
+size 167843469