Add 750k step model

config.json

@@ -12,11 +12,13 @@
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
-  "pad_token_id": 0,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.31.0.dev0",
+  "transformers_version": "4.32.0.dev0",
   "use_cache": true,
   "vocab_size": 64256
 }

generation_config.json

@@ -2,6 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "pad_token_id": 0,
-  "transformers_version": "4.31.0.dev0"
+  "transformers_version": "4.32.0.dev0"
 }

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7548a4e80b744161123b5a4770e463e73acc38f903d42061648170b020f77696
-size 9970325023
+oid sha256:38868a8dc1a91f8aab2f6ed8dc02098fc5d60e7e383f9f30be1604456730de06
+size 9970310575

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b13448e4ccf8be32838b1cd013335a7147373d41539f93b68dc61cf93f00b7fc
-size 4035107309
+oid sha256:4817cfd95737ed97bfdb924150548221a102a98564c55378c6e39651ee848878
+size 4035102557

pytorch_model.bin.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 14005321728
+    "total_size": 14005313536
   },
   "weight_map": {
     "lm_head.weight": "pytorch_model-00002-of-00002.bin",
@@ -13,7 +13,6 @@
     "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -23,7 +22,6 @@
     "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -33,7 +31,6 @@
     "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -43,7 +40,6 @@
     "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -53,7 +49,6 @@
     "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -63,7 +58,6 @@
     "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -73,7 +67,6 @@
     "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -83,7 +76,6 @@
     "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -93,7 +85,6 @@
     "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -103,7 +94,6 @@
     "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -113,7 +103,6 @@
     "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -123,7 +112,6 @@
     "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -133,7 +121,6 @@
     "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -143,7 +130,6 @@
     "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -153,7 +139,6 @@
     "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -163,7 +148,6 @@
     "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
@@ -173,7 +157,6 @@
     "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
@@ -183,7 +166,6 @@
     "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
     "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
@@ -193,7 +175,6 @@
     "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
     "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
@@ -203,7 +184,6 @@
     "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
     "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
@@ -213,7 +193,6 @@
     "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
     "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
@@ -223,7 +202,6 @@
     "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
     "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
@@ -233,7 +211,6 @@
     "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
     "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -243,7 +220,6 @@
     "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
@@ -253,7 +229,6 @@
     "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
     "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
@@ -263,7 +238,6 @@
     "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
     "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -273,7 +247,6 @@
     "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -283,7 +256,6 @@
     "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -293,7 +265,6 @@
     "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -303,7 +274,6 @@
     "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -313,7 +283,6 @@
     "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -323,7 +292,6 @@
     "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.norm.weight": "pytorch_model-00002-of-00002.bin"
   }