Upload files

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27392,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 35,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_p": 0.8,
+  "top_k": 20,
+  "transformers_version": "4.37.0"
+}

model-00001-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2abac7f23ea6f078ef858999daca68b0f543a126c6591702f9d19c4fe2c9c48
+size 3898169048

model-00002-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3525dc9fa95f769268d413bbfec531d589276682ea3805b440e1316861546d5d
+size 3869390208

model-00003-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ff0344858558465ac3e45e30f4575758db8b50bd2ba348ef245cfe6e472c867
+size 3869390208

model-00004-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1301e9ffbea04452e51b47ab1d79dcba08681417b63a6f9703d5b5894f9c36b2
+size 3869390256

model-00005-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9288bd9417aec8ae18da7f30592ae94281ff61c553aa42e495b6a0b30de72843
+size 3869390256

model-00006-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da91c81dff0ab2f04e530c772ac9dcf8784ab2958dd79bc94167a9f4c0242377
+size 3869390256

model-00007-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4d48a6bc7ff6d4c53eea653364065b9f9100151f2154be05410ace843b4b370
+size 3869390256

model-00008-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ddbec334bdcf08c961db63aa2050886628aaae3808212a75f51e2b99a15989b
+size 3869390256

model-00009-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15b5e8d4d25440885b797b8b867db764bb9c089e97c232d6f6caa052399c26d7
+size 3869390256

model-00010-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a645a751e1ef8f027c8c8225ffd5cc80376765268bd7ead111ca2ee0f3517af6
+size 3869390256

model-00011-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb40b659cb077ef2be7cb9063d7ce03b2d3efefd2b2ba9508ea707e85aabacc7
+size 3869390256

model-00012-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:395c93d2ae33cbf62ce79a19995cb3c7a958301523d34a20987834bfb6308220
+size 3869390256

model-00013-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ee9adb4d12d52a8b64f312174b21e4c9996216e6effaa62614e15b3e7b67edb
+size 3869390256

model-00014-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6e6b0c99ada42d9eb44d8156de2db44366e0b7caed5705a469b1bb1f0b2f4fa
+size 3869390256

model-00015-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:691de7217350edf09715d759df4d2ffe2640472cb8aa13de9434dd4c3f541620
+size 3869390256

model-00016-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e167150f35355e0e216048101121be6e0f2a950ac3fdfa08f8cfc2a87770a397
+size 3869390256

model-00017-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1defb350cbdac250eea1a866d615e9bc3230580663b4da1cc1acf9962b7a447c
+size 3085502480

model.safetensors.index.json

@@ -0,0 +1,778 @@
+{
+  "metadata": {
+    "total_size": 65024436224
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00017-of-00017.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.54.self_attn.k_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.54.self_attn.q_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.54.self_attn.v_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.55.self_attn.k_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.55.self_attn.q_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.55.self_attn.v_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.56.self_attn.k_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.56.self_attn.q_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.56.self_attn.v_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.57.self_attn.k_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.57.self_attn.q_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.57.self_attn.v_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.58.self_attn.k_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.58.self_attn.q_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.58.self_attn.v_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.59.self_attn.k_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.59.self_attn.q_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.59.self_attn.v_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.60.self_attn.k_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.60.self_attn.q_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.60.self_attn.v_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.61.self_attn.k_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.61.self_attn.q_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.61.self_attn.v_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.62.self_attn.k_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.62.self_attn.q_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.62.self_attn.v_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.63.self_attn.k_proj.bias": "model-00017-of-00017.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.63.self_attn.q_proj.bias": "model-00017-of-00017.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.63.self_attn.v_proj.bias": "model-00017-of-00017.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.norm.weight": "model-00017-of-00017.safetensors"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}