Upload LlamaForCausalLM

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "defog/sqlcoder-34b-alpha",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "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,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.37.2"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:214c317a4c95d3bc1d0e8db8374808bd5c9ee51c36d3c7bb84ba1185e061c8ad
+size 4978740848

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc4b4f9d9784cfa01b99ab0e8836506de151eefeb6a53dfe5dd26e2489e66e1f
+size 4873882896

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2ed6d3bb4278463c6b023042f46e631c4e1f40ca2c0d266a3f3f7935134a3e7
+size 4815195992

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a32b6b6c2335c4976c370148eb3f40a182c2d92ba634e5c45f0db7d38eb80468
+size 4873882928

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65fcc590dc4f7789023836968b47a5c9e80ace724466a5f87f9a5d22e00522f2
+size 4815196024

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c26976274e538657f0e048452666a00820038ddbfa1ae55f5d6356d6bd3cc6c
+size 4873882928

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aa93a0ba13495aabaa452b2fca85640465927758e5a001c69d0eecd15a219da
+size 4815196024

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291368e4e5f4e5541a39a21fe5579bd4b57b7c7074c6ae4fa80a327d1ae532d2
+size 4873882928

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e93d53772378e2e7f115c3595d3b004cf0cdb992a6e2988caf78522a16561924
+size 4815196024

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c45e2ea68ba1381e2971b9719f8fa4133c55ac2ad633b829fd12fc31e5f9a33
+size 4873882928

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1067fe28b2bfe8be3373871ee74793c15ed897f35dd782226cba949b1371a179
+size 4815196024

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b979e2cde87635089d1da1d67d52e6c6caa6c840c5b524ba61c9c6fdfe3aa9d5
+size 4873882928

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d04ccaa6911f72cc660476e3499007d7dc85a79f706653393057489e952fa03
+size 4815196024

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a2d3a21335dcc94cff96523f1df6bb20e7cf9f3bb4244ed83a33be316e88e5c
+size 4374776632

model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 67487940608
+  },
+  "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"
+  }
+}