Upload GemmaForCausalLM

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "google/gemma-1.1-7b-it",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": true,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.40.0.dev0"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f21690ac5413c2e3ee4788b7ac1eddfc16a8c7945ff74acb3e86a1d485ab23c9
+size 2931845880

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:277c079d81477b80fe7eb1393b64f77ab6f8555f26753cfbcc517a9140dc799b
+size 2919302344

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b273a010eed924424db1bd16e1cbc5218ea166d8598de65a07a09d866356080
+size 2994812720

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba509bd9f57921ed335df59b18ea389425ceac2a6b43db1af980f404f9d2c7c0
+size 2944468336

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da44272c7269061e2dc0a4ad8d49178e9e890ce486a7c78e91924d2d661a8246
+size 2919302392

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80213e668ef032ef614d06c1aacd84ba11a1edbab2fcc5389081b8ec83a5e55e
+size 2365659680

model.safetensors.index.json

@@ -0,0 +1,261 @@
+{
+  "metadata": {
+    "total_size": 17075361792
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}