upload

config.json

@@ -14,7 +14,6 @@
   "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": {
@@ -23,7 +22,7 @@
   },
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.31.0",
+  "transformers_version": "4.32.0",
   "use_cache": true,
   "vocab_size": 32001
 }

generation_config.json

@@ -1,7 +1,10 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 1,
+  "do_sample": true,
   "eos_token_id": 2,
+  "max_length": 4096,
   "pad_token_id": 0,
-  "transformers_version": "4.31.0"
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.32.0"
 }

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6582f9d75d26f4d5e5caaa5447418572fa2bf41f88e2e2196de861e4ff309bc
-size 9976646078
+oid sha256:57a4cf305c81607581204e35ea11a86af363ce5394c4fe06838fef4e629b8336
+size 9976631322

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90be0faafeecaa6c71d3e8fd0d909127715bdfff41fc23cfd4a787aeea0f1542
-size 3500324819
+oid sha256:5d97b9832ebd6636d856952f3381f9789eb09a39f2ca457c67635157584e0a6b
+size 3500320003

pytorch_model.bin.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 13476855808
+    "total_size": 13476847616
   },
   "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-00001-of-00002.bin",
     "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-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"
   }

tokenizer_config.json

@@ -23,6 +23,7 @@
   "pad_token": null,
   "padding_side": "right",
   "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": {
     "__type": "AddedToken",
@@ -31,5 +32,6 @@
     "normalized": false,
     "rstrip": false,
     "single_word": false
-  }
+  },
+  "use_default_system_prompt": true
 }