Upload model

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/content/Einstein-IKM-v1-7B",
+  "architectures": [
+    "MistralModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "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": "float16",
+  "transformers_version": "4.38.2",
+  "unsloth_version": "2024.3",
+  "use_cache": false,
+  "vocab_size": 32002
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84ebf31f226814d673adc0877e1de5db6ed7fb9cf242afb99d15b486a990acad
+size 4943178048

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d5483a774e013e5b5b8c9fd579d4729be09e56c71db6df545e0703bade61a62
+size 4999818600

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab4197c9f7af32e0911ef73b86fa374bc4da9ab6ce657216381cc0589b7b9800
+size 4278371624

model.safetensors.index.json

@@ -0,0 +1,297 @@
+{
+  "metadata": {
+    "total_size": 14221336576
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "norm.weight": "model-00003-of-00003.safetensors"
+  }
+}