Upload folder using huggingface_hub

README.md

@@ -0,0 +1,9 @@
+---
+library_name: peft
+---
+## Training procedure
+
+### Framework versions
+
+
+- PEFT 0.4.0

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",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cedaf4387f61c148f599d9c5cdaf5c043d6225e16c98edaba558b24c346fca1
+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": [
+    "vision_clip"
+  ],
+  "modality_builder": "vision_clip",
+  "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": "4.34.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

model_named_parameters.txt

@@ -0,0 +1,743 @@
+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.vision_clip_lmm_projector.0.weight torch.Size([4096, 1024]) True
+base_model.model.model.vision_clip_lmm_projector.0.bias torch.Size([4096]) True
+base_model.model.model.vision_clip_lmm_projector.2.weight torch.Size([4096, 4096]) True
+base_model.model.model.vision_clip_lmm_projector.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 sha256:5a24320f23f508373cbbd4cb534c28127bcae35e6db8836657a9fe06d0a1479e
+size 41961255

special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<unk>",
+  "eos_token": "</s>",
+  "mask_token": "<unk>",
+  "pad_token": "<unk>",
+  "sep_token": "<unk>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "tokenizer_file": "/root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.1/snapshots/7ad5799710574ba1c1d953eba3077af582f3a773/tokenizer.json",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}