Upload LlamaForCausalLM

config.json

@@ -14,12 +14,13 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
+  "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.32.0.dev0",
+  "transformers_version": "4.31.0",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -5,5 +5,5 @@
   "pad_token_id": 0,
   "temperature": 0.9,
   "top_p": 0.6,
-  "transformers_version": "4.32.0.dev0"
+  "transformers_version": "4.31.0"
 }

pytorch_model-00001-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c3786e6ed3d264da7fc577f9cc822d2553d0fb8e470032d61631e51239a1e3
-size 4939008626
+oid sha256:30f70db5da26524a404a814fec791f642fe34616b4d0471a09574e25472f5680
+size 4939015766

pytorch_model-00002-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:319a35e81db61c256c219c679425e3d8e517da5284d2734d85b8b541fa775186
-size 4947415002
+oid sha256:ce0e8166e13ae3992f2353a2d5df042c773712c140c19794c5daca9f65d58775
+size 4947422190

pytorch_model-00003-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6b46500610f707c890aaba5a3f22f0ae2cbd570a43c5d362ae3f064b9ee8106
-size 3590505657
+oid sha256:c2b4cb4e54238d6eb9e9d56bc550077e1ec7d51f3d0596a1ae9dc29013129964
+size 3590510473

pytorch_model.bin.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 13476831232
+    "total_size": 13476839424
   },
   "weight_map": {
     "lm_head.weight": "pytorch_model-00003-of-00003.bin",
@@ -13,6 +13,7 @@
     "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -22,6 +23,7 @@
     "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -31,6 +33,7 @@
     "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -40,6 +43,7 @@
     "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -49,6 +53,7 @@
     "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -58,6 +63,7 @@
     "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -67,6 +73,7 @@
     "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -76,6 +83,7 @@
     "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -85,6 +93,7 @@
     "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -94,6 +103,7 @@
     "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -103,6 +113,7 @@
     "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -112,6 +123,7 @@
     "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -121,6 +133,7 @@
     "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -130,6 +143,7 @@
     "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -139,6 +153,7 @@
     "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -148,6 +163,7 @@
     "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -157,6 +173,7 @@
     "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -166,6 +183,7 @@
     "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -175,6 +193,7 @@
     "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -184,6 +203,7 @@
     "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -193,6 +213,7 @@
     "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -202,6 +223,7 @@
     "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -211,6 +233,7 @@
     "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -220,6 +243,7 @@
     "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -229,6 +253,7 @@
     "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -238,6 +263,7 @@
     "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -247,6 +273,7 @@
     "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -256,6 +283,7 @@
     "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -265,6 +293,7 @@
     "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -274,6 +303,7 @@
     "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -283,6 +313,7 @@
     "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -292,6 +323,7 @@
     "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.norm.weight": "pytorch_model-00003-of-00003.bin"
   }