Upload LlamaForCausalLM

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "WizardLM/WizardCoder-Python-34B-V1.0",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 22016,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.35.2",
+  "use_cache": false,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.35.2"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f956e7de2418bc423af5b6f7440be0247f004b450634722372b25077274c5f5
+size 4978757232

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31780cd38372f46c00e79f9753696fc4217714895614b5bc257fe644bb2f6595
+size 4873882896

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f2a6e15f9cc8c37f26c9eac093ba7fbe6508efd7c543b203650053ab752e803
+size 4815195992

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1350d099e172c35e8e5573a7db06c3473a87f97a489f5f2712283092f10c3b20
+size 4873882928

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ecde95c32696ec00f46925174b9021e256807e083080fb18b155ae023dabdfc
+size 4815196024

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb31c1b1b4846487333805a12235643c9b2d3163749e7a058495cdd3fd90fd61
+size 4873882928

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cc2c38c576a63ff8c54debd475208d6153c69778e5539e7fca038d4b4b9ae73
+size 4815196024

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:380138311ae86fe250c24307fecabc9504ef5405f0d46f47a64fd9cb017412e5
+size 4873882928

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce70d3ad5166a05d9e81a3e49452b624a38d65881af4eda539c864bacfc434b3
+size 4815196024

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4886d8a6c8ebd37d1a62e63f77805527f862ec1fa7863abe87586db92a7fb900
+size 4873882928

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a9d5ab2d74c9b7a27c89e14bab79679b2b01c0b71cf0520fffaf2598ca1078c
+size 4815196024

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f21f244a10e3aa353d244fe265727e97ffc8d16fbc037044126ad95d4b62532b
+size 4873882928

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7303fe4ac046923bab042cdfe78aa7c77fec26360eb72947631e5da8109dac5
+size 4815196024

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b60685c668a38564728e10c7a15f0af1c08f4a37e1db41a3350cbbfe192452c5
+size 4374793016

model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 67487973376
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.norm.weight": "model-00014-of-00014.safetensors"
+  }
+}