Upload folder using huggingface_hub

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "airoboros-l2-70b-2.1",
+  "_name_or_path": "llama-2-70b-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -16,11 +16,22 @@
   "num_key_value_heads": 8,
   "pad_token_id": 0,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.32.0",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.31.0",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.31.0"
+}

pytorch_model-00001-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74a2f40ebf50eaefc9dae2aa112aa33c208673abfad817d6bffcc75e799af2f8
-size 9852602021
+oid sha256:ee58e2decaf06e2685bddfb5ef6237ba4a57db70291b3485e95746754a08e86b
+size 9852604917

pytorch_model-00002-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71aa3e3c2df3f94e430a7cf70195f6f9b07582fc4b0419f3c12492262e426c52
-size 9798109597
+oid sha256:8a0d736aab9f511c20040c9225cc1b90b4e689a8ccbd3d5a85015eca4d76975c
+size 9798112505

pytorch_model-00003-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f44759ea6d4a839c71f315a4fb7947630d9f0d3e8a0ec47a86d749ccd7d5e904
-size 9965880719
+oid sha256:08c54d2f0e4d5f4c68e83662b4a10a1b6fa1b08a51c8f3dd8e0f157e42254db8
+size 9965883221

pytorch_model-00004-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aff0c62769cd76495dc4a627506ddb0dba2dab14075706594804dd2e7357981
-size 9798076069
+oid sha256:348de6b2462fb4583dd9eda16d3ff715e7049e83da7a46c5243cfc47e7bfce3c
+size 9798079017

pytorch_model-00005-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdd51f8227b72edf1acb2e6192b2ca5214f16bc6d0050bd20c3719db34182243
-size 9798109577
+oid sha256:af21f6085bf5ee2438e836b557652a58671eeb5f3444b00a178e2f0780c70a23
+size 9798112545

pytorch_model-00006-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43c150ea4831df8a1e3e64f3b85f333442cfc85515d611dda8179e89b8be44cb
-size 9798109661
+oid sha256:fc80f5ec49959c1100d822af69d3f6fb7252a9d4266ff383b7bd9b912434fecf
+size 9798112569

pytorch_model-00007-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c39567c084c0c87cc488efde168e0079de4689b7c64a20941064ee8bb98e48ff
-size 9965880719
+oid sha256:f510910a62c24a0e38e1f56e98f617dfe99bf0df6a2887be481e5aea3d839daf
+size 9965883221

pytorch_model-00008-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bc7708b13e790f519f1c9aefe55fd2bb687d89493104ce7c4f22b08c3805338
-size 9798076069
+oid sha256:d552432c4b18da2cdcd99759fac0cbd4921fe335a9ea264a299cb6bc953bec71
+size 9798079017

pytorch_model-00009-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b69c8cc44a197a3f9453ff75b83a852f48c75580e075dd2f5bbbd67e733e89f
-size 9798109577
+oid sha256:e68a9f26ee80a8109b1600bbdc62ea89bfb26c2dd05c9d4b5ef6ddee0621ad00
+size 9798112545

pytorch_model-00010-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89078dae1a7a7bf462049edd4c564198820f9b931522726d36669b72cf97e737
-size 9798109661
+oid sha256:30f54ed6675acc669f08c186e798a9e9afa4d433d05ef2bddd44be6a1e5d2cf0
+size 9798112569

pytorch_model-00011-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c874fd8987a15487aa68e70973883bb5676152285faef64c87767e2daa0c5b3c
-size 9965880719
+oid sha256:241fff5006a0b9263e8126d364c1de39aa0816e0728273205119bb7721f8472d
+size 9965883221

pytorch_model-00012-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04750765fceac920f25e67b6f89b88233d51632d6f02cb6bf7f5131308da60f5
-size 9798076069
+oid sha256:f1e5d9f190afe76221ca19be6d6fa05a0125b3c907a88d3c0589611c142d7298
+size 9798079017

pytorch_model-00013-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:831a541270726ff826c2bbfeac80533a4f40b60661a7b5090e791a87d75dd46d
-size 9798109577
+oid sha256:43d4a2667e4177f339aff0a7b8076219ee9a05f14044f12c4156c93da6552ef4
+size 9798112545

pytorch_model-00014-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34ba5c968def14d48fbd0d387c9503ab33ab5597b1e691a4fa23b8ba3315abce
-size 9496135043
+oid sha256:6adfc71e15f3a1e5d41c0f3d001bd726374148dff310007fbd6790274f7bc134
+size 9496137473

pytorch_model-00015-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e57333b2ffb8bc8fd6147c737fb3d3422c2c80b6608c9f8d91e58ddca1b5431c
+oid sha256:4affec791e4217a4e28d166b327c27a59e7b3693d7c5940d29e825a1dbbd1a17
 size 524288938

pytorch_model.bin.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 137953296384
+    "total_size": 137953306624
   },
   "weight_map": {
     "lm_head.weight": "pytorch_model-00015-of-00015.bin",
@@ -13,6 +13,7 @@
     "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
     "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
@@ -22,6 +23,7 @@
     "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
     "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
@@ -31,6 +33,7 @@
     "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
     "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
@@ -40,6 +43,7 @@
     "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
     "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
@@ -49,6 +53,7 @@
     "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
     "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
@@ -58,6 +63,7 @@
     "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
     "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
@@ -67,6 +73,7 @@
     "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
     "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
@@ -76,6 +83,7 @@
     "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
     "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
@@ -85,6 +93,7 @@
     "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
     "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
@@ -94,6 +103,7 @@
     "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
     "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
@@ -103,6 +113,7 @@
     "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
     "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
@@ -112,6 +123,7 @@
     "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
     "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
@@ -121,6 +133,7 @@
     "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
     "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
@@ -130,6 +143,7 @@
     "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
     "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
@@ -139,6 +153,7 @@
     "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
     "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
@@ -148,6 +163,7 @@
     "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
     "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
@@ -157,6 +173,7 @@
     "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
     "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
@@ -166,6 +183,7 @@
     "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
     "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
@@ -175,6 +193,7 @@
     "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
     "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
@@ -184,6 +203,7 @@
     "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
     "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
@@ -193,6 +213,7 @@
     "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
     "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.28.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.28.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
@@ -202,6 +223,7 @@
     "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
     "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
@@ -211,6 +233,7 @@
     "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
     "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
@@ -220,6 +243,7 @@
     "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
     "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
@@ -229,6 +253,7 @@
     "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
     "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
@@ -238,6 +263,7 @@
     "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
     "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.32.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.32.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
@@ -247,6 +273,7 @@
     "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
     "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.33.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.33.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
@@ -256,6 +283,7 @@
     "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
     "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.34.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.34.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
@@ -265,6 +293,7 @@
     "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
     "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.35.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.35.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
@@ -274,6 +303,7 @@
     "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
     "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.36.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.36.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
@@ -283,6 +313,7 @@
     "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
     "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.37.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.37.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
@@ -292,6 +323,7 @@
     "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
     "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.38.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.38.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
@@ -301,6 +333,7 @@
     "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
     "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.39.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.39.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
@@ -310,6 +343,7 @@
     "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
     "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
@@ -319,6 +353,7 @@
     "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
     "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.40.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.40.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
@@ -328,6 +363,7 @@
     "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
     "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.41.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.41.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
@@ -337,6 +373,7 @@
     "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
     "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.42.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.42.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
@@ -346,6 +383,7 @@
     "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
     "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.43.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.43.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
@@ -355,6 +393,7 @@
     "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
     "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.44.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.44.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
@@ -364,6 +403,7 @@
     "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
     "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.45.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.45.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
@@ -373,6 +413,7 @@
     "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
     "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.46.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.46.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
@@ -382,6 +423,7 @@
     "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
     "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.47.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.47.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
@@ -391,6 +433,7 @@
     "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
     "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.48.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.48.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
@@ -400,6 +443,7 @@
     "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.48.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
     "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.49.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.49.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
@@ -409,6 +453,7 @@
     "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.49.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
     "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
@@ -418,6 +463,7 @@
     "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
     "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.50.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.50.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
@@ -427,6 +473,7 @@
     "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.50.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
     "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.51.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.51.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
@@ -436,6 +483,7 @@
     "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.51.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
     "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.52.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.52.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
@@ -445,6 +493,7 @@
     "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.52.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
     "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.53.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.53.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
@@ -454,6 +503,7 @@
     "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.53.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
     "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.54.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.54.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
@@ -463,6 +513,7 @@
     "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.54.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
     "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.55.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.55.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
@@ -472,6 +523,7 @@
     "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.55.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
     "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.56.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.56.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
@@ -481,6 +533,7 @@
     "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.56.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
     "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.57.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.57.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
@@ -490,6 +543,7 @@
     "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.57.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
     "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.58.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.58.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
@@ -499,6 +553,7 @@
     "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.58.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
     "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.59.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.59.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
@@ -508,6 +563,7 @@
     "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.59.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
     "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
@@ -517,6 +573,7 @@
     "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
     "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.60.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.60.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
@@ -526,6 +583,7 @@
     "model.layers.60.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.60.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.60.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.60.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
     "model.layers.60.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.61.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.61.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
@@ -535,6 +593,7 @@
     "model.layers.61.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.61.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.61.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.61.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
     "model.layers.61.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.62.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.62.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
@@ -544,6 +603,7 @@
     "model.layers.62.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.62.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.62.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.62.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
     "model.layers.62.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.63.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.63.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
@@ -553,6 +613,7 @@
     "model.layers.63.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.63.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.63.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.63.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
     "model.layers.63.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.64.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.64.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
@@ -562,6 +623,7 @@
     "model.layers.64.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.64.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.64.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.64.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
     "model.layers.64.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.65.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.65.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
@@ -571,6 +633,7 @@
     "model.layers.65.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.65.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.65.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.65.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
     "model.layers.65.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.66.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.66.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
@@ -580,6 +643,7 @@
     "model.layers.66.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.66.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.66.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.66.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
     "model.layers.66.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.67.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.67.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
@@ -589,6 +653,7 @@
     "model.layers.67.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.67.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.67.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.67.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
     "model.layers.67.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.68.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.68.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
@@ -598,6 +663,7 @@
     "model.layers.68.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.68.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.68.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.68.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
     "model.layers.68.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.69.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.69.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
@@ -607,6 +673,7 @@
     "model.layers.69.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.69.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.69.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.69.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
     "model.layers.69.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
@@ -616,6 +683,7 @@
     "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
     "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.70.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.70.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
@@ -625,6 +693,7 @@
     "model.layers.70.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.70.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.70.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.70.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
     "model.layers.70.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.71.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.71.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
@@ -634,6 +703,7 @@
     "model.layers.71.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.71.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.71.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.71.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
     "model.layers.71.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.72.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.72.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
@@ -643,6 +713,7 @@
     "model.layers.72.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.72.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.72.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.72.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
     "model.layers.72.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.73.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.73.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
@@ -652,6 +723,7 @@
     "model.layers.73.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.73.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.73.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.73.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
     "model.layers.73.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.74.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.74.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
@@ -661,6 +733,7 @@
     "model.layers.74.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.74.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.74.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.74.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
     "model.layers.74.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.75.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.75.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
@@ -670,6 +743,7 @@
     "model.layers.75.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.75.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.75.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.75.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
     "model.layers.75.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.76.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.76.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
@@ -679,6 +753,7 @@
     "model.layers.76.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.76.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.76.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.76.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
     "model.layers.76.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.77.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.77.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
@@ -688,6 +763,7 @@
     "model.layers.77.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.77.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.77.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.77.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
     "model.layers.77.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.78.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.78.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
@@ -697,6 +773,7 @@
     "model.layers.78.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.78.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.78.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.78.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
     "model.layers.78.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.79.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.79.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
@@ -706,6 +783,7 @@
     "model.layers.79.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.79.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.79.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.79.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
     "model.layers.79.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
@@ -715,6 +793,7 @@
     "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
     "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
@@ -724,6 +803,7 @@
     "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
     "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.norm.weight": "pytorch_model-00014-of-00015.bin"
   }

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}