Add files using upload-large-folder tool

added_tokens.json

@@ -1,4 +1,7 @@
 {
+  "</tool_response>": 32021,
+  "</tool_call>": 32022,
+  "</tools>": 32023,
   "<commit_after>": 32016,
   "<commit_before>": 32014,
   "<commit_msg>": 32015,
@@ -17,8 +20,11 @@
   "<jupyter_start>": 32009,
   "<jupyter_text>": 32010,
   "<reponame>": 32017,
-  "<|beginofsystem|>": 32019,
-  "<|beginofuser|>": 32020,
-  "<|endofchat|>": 32021,
-  "<|endofsystemprompt|>": 32018
+  "<tool_response>": 32018,
+  "<tool_call>": 32019,
+  "<tools>": 32020,
+  "<|beginofsystem|>": 32025,
+  "<|beginofuser|>": 32026,
+  "<|endofchat|>": 32027,
+  "<|endofsystemprompt|>": 32024
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "LLM360/K2-Chat",
+  "_name_or_path": "LLM360/K2",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -13,7 +13,6 @@
   "intermediate_size": 22016,
   "max_position_embeddings": 8192,
   "max_sequence_length": 8192,
-  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 64,
   "num_hidden_layers": 80,
@@ -24,8 +23,8 @@
   "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.42.3",
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
   "use_cache": true,
   "vocab_size": 32032
 }

generation_config.json

@@ -1,7 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 0,
-  "transformers_version": "4.42.3"
+  "transformers_version": "4.31.0"
 }

pytorch_model-00001-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a585fd17236d809783282509a9014b0b79e2ae1cfade9aa72b56947052ed6d9
-size 4660470238
+oid sha256:ad3d85de07d6a061c1db3c1c2572596d1e008eb87781d61d916da53861b1053f
+size 9320933680

pytorch_model-00002-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5676d9c45ee43df3b5cdfc11c912f58b8808d95610b287a01a704d2c97f9f72e
-size 4857111932
+oid sha256:50c62560ebe1bfec3b9b115aef48d3c0e849e20d7875257c23426f145d0d2ce9
+size 9714216126

pytorch_model-00003-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3dd2cbb31406561715e19b55502d3b2e6626bdf0c0940dbe05739e96d1b65ba
-size 4857111932
+oid sha256:6405270d319c751c8931bd0ab8a626bd606a6b4f93972a83411b8c3d2c57a0cc
+size 9714216126

pytorch_model-00004-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23a99b2ebe0a9c3a975c676135bf370955210bef71139d190b177aed5096bbd8
-size 4857111932
+oid sha256:26613094fa5702b3392db0cea4e25057a041d403d006521d2b4bd13f64aa6c9e
+size 9714216190

pytorch_model-00005-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba4d7298a56db5acb38b6e1b267aa5300b44b2095eb2a92483de4df988756921
-size 4857111932
+oid sha256:23294f55f421098841bee62a8b93dcaea51b784f2b75a882fb36863206188b3a
+size 9714216190

pytorch_model-00006-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f82c5fd719780b0838dada11fef3789fd4e3e65d7e4ba7385ed15ecd6c43763
-size 4857111932
+oid sha256:3c583b276f7396a089c08abe2e31e78b4bf8ca3252a10aa856e58c1e764c7848
+size 9714216190

pytorch_model-00007-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9675937dedddf86d365fe166a369cd2cdfecd3324f7381535d92701e397f5bb1
-size 4857111932
+oid sha256:885b901b1a9d40e4195b1958b807d9d181b3c91cba18560db6f7cc995a2ee9cb
+size 9714216190

pytorch_model-00008-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f5bb6b9cc543b659bf84cd1aa10fd13b3b41dc2cb747e750d5d372e8e897f26
-size 4857111932
+oid sha256:b6dac93ed5ea2ab85c81bcf51920fa7d5cee297e8b72255d74554f131ce51867
+size 9714216190

pytorch_model-00009-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cfcbea98a867e83ee8d9f18cf78de472dcd75e9026641c144b973ef121fbcaf
-size 4857111932
+oid sha256:24be29e727a4693ecb85785af1a5bd3ff69f5caf8c061a145459acee5253eab1
+size 9714216190

pytorch_model-00010-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29639026ab3443e9b1fd4d4e9a3cc64779cfd2c1236c1796751c67bc12f44fb7
-size 4857111932
+oid sha256:7bf1863c0a84b905b192f8db433640c3fec3386ecec25cfc1093eee30a0ccdad
+size 9714216190

pytorch_model-00011-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f0e9a1f0f8530c7bea9bccfb9bb59a7ce0ffae3bb1cbec284be4e582fb8a321
-size 4857111932
+oid sha256:d3dd3451a1f8a040ff20305b1e2c8a5fccb4f4d95df92ff5f4fdfd69ab9d2d8f
+size 9714216190

pytorch_model-00012-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cc379abb8e9489a952288609d6fe1f6f00ba90a0b44b79b429f11da7f3404dc
-size 4857111932
+oid sha256:1ee258c2141f8d3cf39380d83eb68842fbfcc3695513c61cacb98035ee5af71d
+size 9714216190

pytorch_model-00013-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0065b56df7e8e65ebc20764eff6b5c0553d9b19761f48b2ebb42552a9838e438
-size 4857111932
+oid sha256:dc50fce03cc8d9b6a38aff849b4561641d402441b86b3fa32a498aaa847d0324
+size 9714216190

pytorch_model-00014-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91661a25fe6ed6b1215614ef3ccbc0ccea91ce3bee8ed167a4b4909f3c4aa822
-size 4857111932
+oid sha256:c1a5063531cf56f96fbcf9d64b3b2ac959a82ee6214594cf5ad316acdf6e6766
+size 9714216190

pytorch_model-00015-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f31d226cdab9777484cdc75bb54867082feb6232809aacd7b28c1ab71a146a25
-size 4857111932
+oid sha256:dde029c616628b02b84f7ca4ba2ab63dd7a29317adfccbe693b0b03445d569df
+size 9714216190

pytorch_model-00016-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcd66360e1185d2c0206263a0b904d2898d86de9159476ca7e4d040ae2a5306f
-size 4857111932
+oid sha256:de79433944783f21d8d66cc3bff60800ce8a7cde7b4c26e2d4ffb9e40bc9a842
+size 9714216190

pytorch_model-00017-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73b69d3d99eab0b48307437205045cf81f2759306656e39e51beb7c38a54a745
-size 4857111932
+oid sha256:9e8018f651de68885920875cd9f2e39140a2ee7139b2eeacffd3a2dcb38ea802
+size 9714216190

pytorch_model-00018-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7564f8f626234af5d8301cb8a90bb5e8eab2e3ddccf55941abf52f224470e05
-size 4857111932
+oid sha256:efba8b9cf63e00e5db49dd60a29841b4582fabac21fbb26cf4b8335eecdd9e19
+size 9714216190

pytorch_model-00019-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dea6b1c683c31876ea5f9f807940183d8e486b78312dfa9c478ae02b3beb897
-size 4857111932
+oid sha256:58c7464831b8a4e0215421af76c6d35b760ad7f5dbde2a4c6effc5a188f34f87
+size 9714216190

pytorch_model-00020-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b693c0031b86b1b31f5a1def7700efa2e3e9a585bd0f3d14acadea164b46722
-size 4857111932
+oid sha256:b0d475e7d79ce0bdc57ec7234205ee6754591d44bfc17b67ccc008a6f9292178
+size 9714216190

pytorch_model-00021-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af5909dbd4604551efba00d5e22c918b88f5b19e0c2eceb7ddff6b4a9ae3746b
-size 4857111932
+oid sha256:cfe1601ef1b0148581106885a840d9a8fb823cf11a057446776a874dd9787478
+size 9714216190

pytorch_model-00022-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21d430632dbd4a43828cae7aab66db914357430fc8f9b59c138f34af8b17c3bc
-size 4857111932
+oid sha256:e8f25c0c74d21edcc1ee0d64676fb19b50e0467a5a60c29e268af51bf1312abe
+size 9714216190

pytorch_model-00023-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f16ce76b513a892f325bdb27b69a4d297f8b9c07328662eb110bb57bc1148704
-size 4857111932
+oid sha256:be6a096c8469c69c514e4ecc7aab421a7a3e58fd350a4753ceee0b37b7abbf9c
+size 9714216190

pytorch_model-00024-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df6bc4f1f2d0ec8de1d8e9f2cfce7aa3385e4a4406fe09661297c352a37da868
-size 4857111932
+oid sha256:cb7c50a0bbf507184d9887c0596763a77bb879e09aecd69a0cf5ed8d1c3b998f
+size 9714216190

pytorch_model-00025-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37d5afae9b2da032c7c138940722793af36a384d5fb632b8a52319277cb3d83e
-size 4857111932
+oid sha256:f945c50484c7bc2956cd0ae5d092728d4464f681fc35fb639781d03c2ba805b0
+size 9714216190

pytorch_model-00026-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cc8ab0fc7e2b2751768793aa7bbf391d87b118fc929e37b357372819686f146
-size 4857111932
+oid sha256:551d5be9b1508820fc9147f49ab992b9ad8fd946366d639b97d246e68946260c
+size 9714216190

pytorch_model-00027-of-00027.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c44c2acb0c4e546addc9c11b8fa02d5fa60e24894055f2a103ed9b478ce6c7cd
-size 4484358522
+oid sha256:9c5d19e2de894f58ee8e28c7dab0c97eaaa6a147acadb5209b45e2f6db60e2cd
+size 8968709830

pytorch_model.bin.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 130572369920
+    "total_size": 261144760320
   },
   "weight_map": {
     "lm_head.weight": "pytorch_model-00027-of-00027.bin",
@@ -13,6 +13,7 @@
     "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00027.bin",
     "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00027.bin",
     "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00027.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00027.bin",
     "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00027.bin",
     "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00027.bin",
     "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00027.bin",
@@ -22,6 +23,7 @@
     "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00027.bin",
     "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00027.bin",
     "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00027.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00027.bin",
     "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00027.bin",
     "model.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00027.bin",
     "model.layers.10.mlp.down_proj.weight": "pytorch_model-00004-of-00027.bin",
@@ -31,6 +33,7 @@
     "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00004-of-00027.bin",
     "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00004-of-00027.bin",
     "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00004-of-00027.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00027.bin",
     "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00004-of-00027.bin",
     "model.layers.11.input_layernorm.weight": "pytorch_model-00005-of-00027.bin",
     "model.layers.11.mlp.down_proj.weight": "pytorch_model-00005-of-00027.bin",
@@ -40,6 +43,7 @@
     "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00004-of-00027.bin",
     "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00004-of-00027.bin",
     "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00004-of-00027.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00027.bin",
     "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00004-of-00027.bin",
     "model.layers.12.input_layernorm.weight": "pytorch_model-00005-of-00027.bin",
     "model.layers.12.mlp.down_proj.weight": "pytorch_model-00005-of-00027.bin",
@@ -49,6 +53,7 @@
     "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00005-of-00027.bin",
     "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00005-of-00027.bin",
     "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00005-of-00027.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00027.bin",
     "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00005-of-00027.bin",
     "model.layers.13.input_layernorm.weight": "pytorch_model-00005-of-00027.bin",
     "model.layers.13.mlp.down_proj.weight": "pytorch_model-00005-of-00027.bin",
@@ -58,6 +63,7 @@
     "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00005-of-00027.bin",
     "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00005-of-00027.bin",
     "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00005-of-00027.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00027.bin",
     "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00005-of-00027.bin",
     "model.layers.14.input_layernorm.weight": "pytorch_model-00006-of-00027.bin",
     "model.layers.14.mlp.down_proj.weight": "pytorch_model-00006-of-00027.bin",
@@ -67,6 +73,7 @@
     "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00005-of-00027.bin",
     "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00005-of-00027.bin",
     "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00005-of-00027.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00027.bin",
     "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00005-of-00027.bin",
     "model.layers.15.input_layernorm.weight": "pytorch_model-00006-of-00027.bin",
     "model.layers.15.mlp.down_proj.weight": "pytorch_model-00006-of-00027.bin",
@@ -76,6 +83,7 @@
     "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00006-of-00027.bin",
     "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00006-of-00027.bin",
     "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00006-of-00027.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00027.bin",
     "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00006-of-00027.bin",
     "model.layers.16.input_layernorm.weight": "pytorch_model-00006-of-00027.bin",
     "model.layers.16.mlp.down_proj.weight": "pytorch_model-00006-of-00027.bin",
@@ -85,6 +93,7 @@
     "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00006-of-00027.bin",
     "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00006-of-00027.bin",
     "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00006-of-00027.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00027.bin",
     "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00006-of-00027.bin",
     "model.layers.17.input_layernorm.weight": "pytorch_model-00007-of-00027.bin",
     "model.layers.17.mlp.down_proj.weight": "pytorch_model-00007-of-00027.bin",
@@ -94,6 +103,7 @@
     "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00006-of-00027.bin",
     "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00006-of-00027.bin",
     "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00006-of-00027.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00027.bin",
     "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00006-of-00027.bin",
     "model.layers.18.input_layernorm.weight": "pytorch_model-00007-of-00027.bin",
     "model.layers.18.mlp.down_proj.weight": "pytorch_model-00007-of-00027.bin",
@@ -103,6 +113,7 @@
     "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00007-of-00027.bin",
     "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00007-of-00027.bin",
     "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00007-of-00027.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00027.bin",
     "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00007-of-00027.bin",
     "model.layers.19.input_layernorm.weight": "pytorch_model-00007-of-00027.bin",
     "model.layers.19.mlp.down_proj.weight": "pytorch_model-00007-of-00027.bin",
@@ -112,6 +123,7 @@
     "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00007-of-00027.bin",
     "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00007-of-00027.bin",
     "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00007-of-00027.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00027.bin",
     "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00007-of-00027.bin",
     "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00027.bin",
     "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00027.bin",
@@ -121,6 +133,7 @@
     "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00027.bin",
     "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00027.bin",
     "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00027.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00027.bin",
     "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00027.bin",
     "model.layers.20.input_layernorm.weight": "pytorch_model-00008-of-00027.bin",
     "model.layers.20.mlp.down_proj.weight": "pytorch_model-00008-of-00027.bin",
@@ -130,6 +143,7 @@
     "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00007-of-00027.bin",
     "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00007-of-00027.bin",
     "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00007-of-00027.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00027.bin",
     "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00007-of-00027.bin",
     "model.layers.21.input_layernorm.weight": "pytorch_model-00008-of-00027.bin",
     "model.layers.21.mlp.down_proj.weight": "pytorch_model-00008-of-00027.bin",
@@ -139,6 +153,7 @@
     "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00008-of-00027.bin",
     "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00008-of-00027.bin",
     "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00008-of-00027.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00027.bin",
     "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00008-of-00027.bin",
     "model.layers.22.input_layernorm.weight": "pytorch_model-00008-of-00027.bin",
     "model.layers.22.mlp.down_proj.weight": "pytorch_model-00008-of-00027.bin",
@@ -148,6 +163,7 @@
     "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00008-of-00027.bin",
     "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00008-of-00027.bin",
     "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00008-of-00027.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00027.bin",
     "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00008-of-00027.bin",
     "model.layers.23.input_layernorm.weight": "pytorch_model-00009-of-00027.bin",
     "model.layers.23.mlp.down_proj.weight": "pytorch_model-00009-of-00027.bin",
@@ -157,6 +173,7 @@
     "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00008-of-00027.bin",
     "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00008-of-00027.bin",
     "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00008-of-00027.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00027.bin",
     "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00008-of-00027.bin",
     "model.layers.24.input_layernorm.weight": "pytorch_model-00009-of-00027.bin",
     "model.layers.24.mlp.down_proj.weight": "pytorch_model-00009-of-00027.bin",
@@ -166,6 +183,7 @@
     "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00009-of-00027.bin",
     "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00009-of-00027.bin",
     "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00009-of-00027.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00027.bin",
     "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00009-of-00027.bin",
     "model.layers.25.input_layernorm.weight": "pytorch_model-00009-of-00027.bin",
     "model.layers.25.mlp.down_proj.weight": "pytorch_model-00009-of-00027.bin",
@@ -175,6 +193,7 @@
     "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00009-of-00027.bin",
     "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00009-of-00027.bin",
     "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00009-of-00027.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00027.bin",
     "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00009-of-00027.bin",
     "model.layers.26.input_layernorm.weight": "pytorch_model-00010-of-00027.bin",
     "model.layers.26.mlp.down_proj.weight": "pytorch_model-00010-of-00027.bin",
@@ -184,6 +203,7 @@
     "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00009-of-00027.bin",
     "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00009-of-00027.bin",
     "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00009-of-00027.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00027.bin",
     "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00009-of-00027.bin",
     "model.layers.27.input_layernorm.weight": "pytorch_model-00010-of-00027.bin",
     "model.layers.27.mlp.down_proj.weight": "pytorch_model-00010-of-00027.bin",
@@ -193,6 +213,7 @@
     "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00010-of-00027.bin",
     "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00010-of-00027.bin",
     "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00010-of-00027.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00027.bin",
     "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00010-of-00027.bin",
     "model.layers.28.input_layernorm.weight": "pytorch_model-00010-of-00027.bin",
     "model.layers.28.mlp.down_proj.weight": "pytorch_model-00010-of-00027.bin",
@@ -202,6 +223,7 @@
     "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00010-of-00027.bin",
     "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00010-of-00027.bin",
     "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00010-of-00027.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00027.bin",
     "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00010-of-00027.bin",
     "model.layers.29.input_layernorm.weight": "pytorch_model-00011-of-00027.bin",
     "model.layers.29.mlp.down_proj.weight": "pytorch_model-00011-of-00027.bin",
@@ -211,6 +233,7 @@
     "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00010-of-00027.bin",
     "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00010-of-00027.bin",
     "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00010-of-00027.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00027.bin",
     "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00010-of-00027.bin",
     "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00027.bin",
     "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00027.bin",
@@ -220,6 +243,7 @@
     "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00027.bin",
     "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00027.bin",
     "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00027.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00027.bin",
     "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00027.bin",
     "model.layers.30.input_layernorm.weight": "pytorch_model-00011-of-00027.bin",
     "model.layers.30.mlp.down_proj.weight": "pytorch_model-00011-of-00027.bin",
@@ -229,6 +253,7 @@
     "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00011-of-00027.bin",
     "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00011-of-00027.bin",
     "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00011-of-00027.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00027.bin",
     "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00011-of-00027.bin",
     "model.layers.31.input_layernorm.weight": "pytorch_model-00011-of-00027.bin",
     "model.layers.31.mlp.down_proj.weight": "pytorch_model-00011-of-00027.bin",
@@ -238,6 +263,7 @@
     "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00011-of-00027.bin",
     "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00011-of-00027.bin",
     "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00011-of-00027.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00027.bin",
     "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00011-of-00027.bin",
     "model.layers.32.input_layernorm.weight": "pytorch_model-00012-of-00027.bin",
     "model.layers.32.mlp.down_proj.weight": "pytorch_model-00012-of-00027.bin",
@@ -247,6 +273,7 @@
     "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00011-of-00027.bin",
     "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00011-of-00027.bin",
     "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00011-of-00027.bin",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00027.bin",
     "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00011-of-00027.bin",
     "model.layers.33.input_layernorm.weight": "pytorch_model-00012-of-00027.bin",
     "model.layers.33.mlp.down_proj.weight": "pytorch_model-00012-of-00027.bin",
@@ -256,6 +283,7 @@
     "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00012-of-00027.bin",
     "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00012-of-00027.bin",
     "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00012-of-00027.bin",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00027.bin",
     "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00012-of-00027.bin",
     "model.layers.34.input_layernorm.weight": "pytorch_model-00012-of-00027.bin",
     "model.layers.34.mlp.down_proj.weight": "pytorch_model-00012-of-00027.bin",
@@ -265,6 +293,7 @@
     "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00012-of-00027.bin",
     "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00012-of-00027.bin",
     "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00012-of-00027.bin",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00027.bin",
     "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00012-of-00027.bin",
     "model.layers.35.input_layernorm.weight": "pytorch_model-00013-of-00027.bin",
     "model.layers.35.mlp.down_proj.weight": "pytorch_model-00013-of-00027.bin",
@@ -274,6 +303,7 @@
     "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00012-of-00027.bin",
     "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00012-of-00027.bin",
     "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00012-of-00027.bin",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00027.bin",
     "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00012-of-00027.bin",
     "model.layers.36.input_layernorm.weight": "pytorch_model-00013-of-00027.bin",
     "model.layers.36.mlp.down_proj.weight": "pytorch_model-00013-of-00027.bin",
@@ -283,6 +313,7 @@
     "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00013-of-00027.bin",
     "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00013-of-00027.bin",
     "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00013-of-00027.bin",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00027.bin",
     "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00013-of-00027.bin",
     "model.layers.37.input_layernorm.weight": "pytorch_model-00013-of-00027.bin",
     "model.layers.37.mlp.down_proj.weight": "pytorch_model-00013-of-00027.bin",
@@ -292,6 +323,7 @@
     "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00013-of-00027.bin",
     "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00013-of-00027.bin",
     "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00013-of-00027.bin",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00027.bin",
     "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00013-of-00027.bin",
     "model.layers.38.input_layernorm.weight": "pytorch_model-00014-of-00027.bin",
     "model.layers.38.mlp.down_proj.weight": "pytorch_model-00014-of-00027.bin",
@@ -301,6 +333,7 @@
     "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00013-of-00027.bin",
     "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00013-of-00027.bin",
     "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00013-of-00027.bin",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00027.bin",
     "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00013-of-00027.bin",
     "model.layers.39.input_layernorm.weight": "pytorch_model-00014-of-00027.bin",
     "model.layers.39.mlp.down_proj.weight": "pytorch_model-00014-of-00027.bin",
@@ -310,6 +343,7 @@
     "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00014-of-00027.bin",
     "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00014-of-00027.bin",
     "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00014-of-00027.bin",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00027.bin",
     "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00014-of-00027.bin",
     "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00027.bin",
     "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00027.bin",
@@ -319,6 +353,7 @@
     "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00027.bin",
     "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00027.bin",
     "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00027.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00027.bin",
     "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00027.bin",
     "model.layers.40.input_layernorm.weight": "pytorch_model-00014-of-00027.bin",
     "model.layers.40.mlp.down_proj.weight": "pytorch_model-00014-of-00027.bin",
@@ -328,6 +363,7 @@
     "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00014-of-00027.bin",
     "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00014-of-00027.bin",
     "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00014-of-00027.bin",
+    "model.layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00027.bin",
     "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00014-of-00027.bin",
     "model.layers.41.input_layernorm.weight": "pytorch_model-00015-of-00027.bin",
     "model.layers.41.mlp.down_proj.weight": "pytorch_model-00015-of-00027.bin",
@@ -337,6 +373,7 @@
     "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00014-of-00027.bin",
     "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00014-of-00027.bin",
     "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00014-of-00027.bin",
+    "model.layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00027.bin",
     "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00014-of-00027.bin",
     "model.layers.42.input_layernorm.weight": "pytorch_model-00015-of-00027.bin",
     "model.layers.42.mlp.down_proj.weight": "pytorch_model-00015-of-00027.bin",
@@ -346,6 +383,7 @@
     "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00015-of-00027.bin",
     "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00015-of-00027.bin",
     "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00015-of-00027.bin",
+    "model.layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00027.bin",
     "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00015-of-00027.bin",
     "model.layers.43.input_layernorm.weight": "pytorch_model-00015-of-00027.bin",
     "model.layers.43.mlp.down_proj.weight": "pytorch_model-00015-of-00027.bin",
@@ -355,6 +393,7 @@
     "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00015-of-00027.bin",
     "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00015-of-00027.bin",
     "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00015-of-00027.bin",
+    "model.layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00027.bin",
     "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00015-of-00027.bin",
     "model.layers.44.input_layernorm.weight": "pytorch_model-00016-of-00027.bin",
     "model.layers.44.mlp.down_proj.weight": "pytorch_model-00016-of-00027.bin",
@@ -364,6 +403,7 @@
     "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00015-of-00027.bin",
     "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00015-of-00027.bin",
     "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00015-of-00027.bin",
+    "model.layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00027.bin",
     "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00015-of-00027.bin",
     "model.layers.45.input_layernorm.weight": "pytorch_model-00016-of-00027.bin",
     "model.layers.45.mlp.down_proj.weight": "pytorch_model-00016-of-00027.bin",
@@ -373,6 +413,7 @@
     "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00016-of-00027.bin",
     "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00016-of-00027.bin",
     "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00016-of-00027.bin",
+    "model.layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00027.bin",
     "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00016-of-00027.bin",
     "model.layers.46.input_layernorm.weight": "pytorch_model-00016-of-00027.bin",
     "model.layers.46.mlp.down_proj.weight": "pytorch_model-00016-of-00027.bin",
@@ -382,6 +423,7 @@
     "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00016-of-00027.bin",
     "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00016-of-00027.bin",
     "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00016-of-00027.bin",
+    "model.layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00027.bin",
     "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00016-of-00027.bin",
     "model.layers.47.input_layernorm.weight": "pytorch_model-00017-of-00027.bin",
     "model.layers.47.mlp.down_proj.weight": "pytorch_model-00017-of-00027.bin",
@@ -391,6 +433,7 @@
     "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00016-of-00027.bin",
     "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00016-of-00027.bin",
     "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00016-of-00027.bin",
+    "model.layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00027.bin",
     "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00016-of-00027.bin",
     "model.layers.48.input_layernorm.weight": "pytorch_model-00017-of-00027.bin",
     "model.layers.48.mlp.down_proj.weight": "pytorch_model-00017-of-00027.bin",
@@ -400,6 +443,7 @@
     "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00017-of-00027.bin",
     "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00017-of-00027.bin",
     "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00017-of-00027.bin",
+    "model.layers.48.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00027.bin",
     "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00017-of-00027.bin",
     "model.layers.49.input_layernorm.weight": "pytorch_model-00017-of-00027.bin",
     "model.layers.49.mlp.down_proj.weight": "pytorch_model-00017-of-00027.bin",
@@ -409,6 +453,7 @@
     "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00017-of-00027.bin",
     "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00017-of-00027.bin",
     "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00017-of-00027.bin",
+    "model.layers.49.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00027.bin",
     "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00017-of-00027.bin",
     "model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00027.bin",
     "model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00027.bin",
@@ -418,6 +463,7 @@
     "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00027.bin",
     "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00027.bin",
     "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00027.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00027.bin",
     "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00027.bin",
     "model.layers.50.input_layernorm.weight": "pytorch_model-00018-of-00027.bin",
     "model.layers.50.mlp.down_proj.weight": "pytorch_model-00018-of-00027.bin",
@@ -427,6 +473,7 @@
     "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00017-of-00027.bin",
     "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00017-of-00027.bin",
     "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00017-of-00027.bin",
+    "model.layers.50.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00027.bin",
     "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00017-of-00027.bin",
     "model.layers.51.input_layernorm.weight": "pytorch_model-00018-of-00027.bin",
     "model.layers.51.mlp.down_proj.weight": "pytorch_model-00018-of-00027.bin",
@@ -436,6 +483,7 @@
     "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00018-of-00027.bin",
     "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00018-of-00027.bin",
     "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00018-of-00027.bin",
+    "model.layers.51.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00027.bin",
     "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00018-of-00027.bin",
     "model.layers.52.input_layernorm.weight": "pytorch_model-00018-of-00027.bin",
     "model.layers.52.mlp.down_proj.weight": "pytorch_model-00018-of-00027.bin",
@@ -445,6 +493,7 @@
     "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00018-of-00027.bin",
     "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00018-of-00027.bin",
     "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00018-of-00027.bin",
+    "model.layers.52.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00027.bin",
     "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00018-of-00027.bin",
     "model.layers.53.input_layernorm.weight": "pytorch_model-00019-of-00027.bin",
     "model.layers.53.mlp.down_proj.weight": "pytorch_model-00019-of-00027.bin",
@@ -454,6 +503,7 @@
     "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00018-of-00027.bin",
     "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00018-of-00027.bin",
     "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00018-of-00027.bin",
+    "model.layers.53.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00027.bin",
     "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00018-of-00027.bin",
     "model.layers.54.input_layernorm.weight": "pytorch_model-00019-of-00027.bin",
     "model.layers.54.mlp.down_proj.weight": "pytorch_model-00019-of-00027.bin",
@@ -463,6 +513,7 @@
     "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00019-of-00027.bin",
     "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00019-of-00027.bin",
     "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00019-of-00027.bin",
+    "model.layers.54.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00027.bin",
     "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00019-of-00027.bin",
     "model.layers.55.input_layernorm.weight": "pytorch_model-00019-of-00027.bin",
     "model.layers.55.mlp.down_proj.weight": "pytorch_model-00019-of-00027.bin",
@@ -472,6 +523,7 @@
     "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00019-of-00027.bin",
     "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00019-of-00027.bin",
     "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00019-of-00027.bin",
+    "model.layers.55.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00027.bin",
     "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00019-of-00027.bin",
     "model.layers.56.input_layernorm.weight": "pytorch_model-00020-of-00027.bin",
     "model.layers.56.mlp.down_proj.weight": "pytorch_model-00020-of-00027.bin",
@@ -481,6 +533,7 @@
     "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00019-of-00027.bin",
     "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00019-of-00027.bin",
     "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00019-of-00027.bin",
+    "model.layers.56.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00027.bin",
     "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00019-of-00027.bin",
     "model.layers.57.input_layernorm.weight": "pytorch_model-00020-of-00027.bin",
     "model.layers.57.mlp.down_proj.weight": "pytorch_model-00020-of-00027.bin",
@@ -490,6 +543,7 @@
     "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00020-of-00027.bin",
     "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00020-of-00027.bin",
     "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00020-of-00027.bin",
+    "model.layers.57.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00027.bin",
     "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00020-of-00027.bin",
     "model.layers.58.input_layernorm.weight": "pytorch_model-00020-of-00027.bin",
     "model.layers.58.mlp.down_proj.weight": "pytorch_model-00020-of-00027.bin",
@@ -499,6 +553,7 @@
     "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00020-of-00027.bin",
     "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00020-of-00027.bin",
     "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00020-of-00027.bin",
+    "model.layers.58.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00027.bin",
     "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00020-of-00027.bin",
     "model.layers.59.input_layernorm.weight": "pytorch_model-00021-of-00027.bin",
     "model.layers.59.mlp.down_proj.weight": "pytorch_model-00021-of-00027.bin",
@@ -508,6 +563,7 @@
     "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00020-of-00027.bin",
     "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00020-of-00027.bin",
     "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00020-of-00027.bin",
+    "model.layers.59.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00027.bin",
     "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00020-of-00027.bin",
     "model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00027.bin",
     "model.layers.6.mlp.down_proj.weight": "pytorch_model-00003-of-00027.bin",
@@ -517,6 +573,7 @@
     "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00027.bin",
     "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00027.bin",
     "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00027.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00027.bin",
     "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00027.bin",
     "model.layers.60.input_layernorm.weight": "pytorch_model-00021-of-00027.bin",
     "model.layers.60.mlp.down_proj.weight": "pytorch_model-00021-of-00027.bin",
@@ -526,6 +583,7 @@
     "model.layers.60.self_attn.k_proj.weight": "pytorch_model-00021-of-00027.bin",
     "model.layers.60.self_attn.o_proj.weight": "pytorch_model-00021-of-00027.bin",
     "model.layers.60.self_attn.q_proj.weight": "pytorch_model-00021-of-00027.bin",
+    "model.layers.60.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00027.bin",
     "model.layers.60.self_attn.v_proj.weight": "pytorch_model-00021-of-00027.bin",
     "model.layers.61.input_layernorm.weight": "pytorch_model-00021-of-00027.bin",
     "model.layers.61.mlp.down_proj.weight": "pytorch_model-00021-of-00027.bin",
@@ -535,6 +593,7 @@
     "model.layers.61.self_attn.k_proj.weight": "pytorch_model-00021-of-00027.bin",
     "model.layers.61.self_attn.o_proj.weight": "pytorch_model-00021-of-00027.bin",
     "model.layers.61.self_attn.q_proj.weight": "pytorch_model-00021-of-00027.bin",
+    "model.layers.61.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00027.bin",
     "model.layers.61.self_attn.v_proj.weight": "pytorch_model-00021-of-00027.bin",
     "model.layers.62.input_layernorm.weight": "pytorch_model-00022-of-00027.bin",
     "model.layers.62.mlp.down_proj.weight": "pytorch_model-00022-of-00027.bin",
@@ -544,6 +603,7 @@
     "model.layers.62.self_attn.k_proj.weight": "pytorch_model-00021-of-00027.bin",
     "model.layers.62.self_attn.o_proj.weight": "pytorch_model-00021-of-00027.bin",
     "model.layers.62.self_attn.q_proj.weight": "pytorch_model-00021-of-00027.bin",
+    "model.layers.62.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00027.bin",
     "model.layers.62.self_attn.v_proj.weight": "pytorch_model-00021-of-00027.bin",
     "model.layers.63.input_layernorm.weight": "pytorch_model-00022-of-00027.bin",
     "model.layers.63.mlp.down_proj.weight": "pytorch_model-00022-of-00027.bin",
@@ -553,6 +613,7 @@
     "model.layers.63.self_attn.k_proj.weight": "pytorch_model-00022-of-00027.bin",
     "model.layers.63.self_attn.o_proj.weight": "pytorch_model-00022-of-00027.bin",
     "model.layers.63.self_attn.q_proj.weight": "pytorch_model-00022-of-00027.bin",
+    "model.layers.63.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00027.bin",
     "model.layers.63.self_attn.v_proj.weight": "pytorch_model-00022-of-00027.bin",
     "model.layers.64.input_layernorm.weight": "pytorch_model-00022-of-00027.bin",
     "model.layers.64.mlp.down_proj.weight": "pytorch_model-00022-of-00027.bin",
@@ -562,6 +623,7 @@
     "model.layers.64.self_attn.k_proj.weight": "pytorch_model-00022-of-00027.bin",
     "model.layers.64.self_attn.o_proj.weight": "pytorch_model-00022-of-00027.bin",
     "model.layers.64.self_attn.q_proj.weight": "pytorch_model-00022-of-00027.bin",
+    "model.layers.64.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00027.bin",
     "model.layers.64.self_attn.v_proj.weight": "pytorch_model-00022-of-00027.bin",
     "model.layers.65.input_layernorm.weight": "pytorch_model-00023-of-00027.bin",
     "model.layers.65.mlp.down_proj.weight": "pytorch_model-00023-of-00027.bin",
@@ -571,6 +633,7 @@
     "model.layers.65.self_attn.k_proj.weight": "pytorch_model-00022-of-00027.bin",
     "model.layers.65.self_attn.o_proj.weight": "pytorch_model-00022-of-00027.bin",
     "model.layers.65.self_attn.q_proj.weight": "pytorch_model-00022-of-00027.bin",
+    "model.layers.65.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00027.bin",
     "model.layers.65.self_attn.v_proj.weight": "pytorch_model-00022-of-00027.bin",
     "model.layers.66.input_layernorm.weight": "pytorch_model-00023-of-00027.bin",
     "model.layers.66.mlp.down_proj.weight": "pytorch_model-00023-of-00027.bin",
@@ -580,6 +643,7 @@
     "model.layers.66.self_attn.k_proj.weight": "pytorch_model-00023-of-00027.bin",
     "model.layers.66.self_attn.o_proj.weight": "pytorch_model-00023-of-00027.bin",
     "model.layers.66.self_attn.q_proj.weight": "pytorch_model-00023-of-00027.bin",
+    "model.layers.66.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00027.bin",
     "model.layers.66.self_attn.v_proj.weight": "pytorch_model-00023-of-00027.bin",
     "model.layers.67.input_layernorm.weight": "pytorch_model-00023-of-00027.bin",
     "model.layers.67.mlp.down_proj.weight": "pytorch_model-00023-of-00027.bin",
@@ -589,6 +653,7 @@
     "model.layers.67.self_attn.k_proj.weight": "pytorch_model-00023-of-00027.bin",
     "model.layers.67.self_attn.o_proj.weight": "pytorch_model-00023-of-00027.bin",
     "model.layers.67.self_attn.q_proj.weight": "pytorch_model-00023-of-00027.bin",
+    "model.layers.67.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00027.bin",
     "model.layers.67.self_attn.v_proj.weight": "pytorch_model-00023-of-00027.bin",
     "model.layers.68.input_layernorm.weight": "pytorch_model-00024-of-00027.bin",
     "model.layers.68.mlp.down_proj.weight": "pytorch_model-00024-of-00027.bin",
@@ -598,6 +663,7 @@
     "model.layers.68.self_attn.k_proj.weight": "pytorch_model-00023-of-00027.bin",
     "model.layers.68.self_attn.o_proj.weight": "pytorch_model-00023-of-00027.bin",
     "model.layers.68.self_attn.q_proj.weight": "pytorch_model-00023-of-00027.bin",
+    "model.layers.68.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00027.bin",
     "model.layers.68.self_attn.v_proj.weight": "pytorch_model-00023-of-00027.bin",
     "model.layers.69.input_layernorm.weight": "pytorch_model-00024-of-00027.bin",
     "model.layers.69.mlp.down_proj.weight": "pytorch_model-00024-of-00027.bin",
@@ -607,6 +673,7 @@
     "model.layers.69.self_attn.k_proj.weight": "pytorch_model-00024-of-00027.bin",
     "model.layers.69.self_attn.o_proj.weight": "pytorch_model-00024-of-00027.bin",
     "model.layers.69.self_attn.q_proj.weight": "pytorch_model-00024-of-00027.bin",
+    "model.layers.69.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00027.bin",
     "model.layers.69.self_attn.v_proj.weight": "pytorch_model-00024-of-00027.bin",
     "model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00027.bin",
     "model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00027.bin",
@@ -616,6 +683,7 @@
     "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00027.bin",
     "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00003-of-00027.bin",
     "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00027.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00027.bin",
     "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00027.bin",
     "model.layers.70.input_layernorm.weight": "pytorch_model-00024-of-00027.bin",
     "model.layers.70.mlp.down_proj.weight": "pytorch_model-00024-of-00027.bin",
@@ -625,6 +693,7 @@
     "model.layers.70.self_attn.k_proj.weight": "pytorch_model-00024-of-00027.bin",
     "model.layers.70.self_attn.o_proj.weight": "pytorch_model-00024-of-00027.bin",
     "model.layers.70.self_attn.q_proj.weight": "pytorch_model-00024-of-00027.bin",
+    "model.layers.70.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00027.bin",
     "model.layers.70.self_attn.v_proj.weight": "pytorch_model-00024-of-00027.bin",
     "model.layers.71.input_layernorm.weight": "pytorch_model-00025-of-00027.bin",
     "model.layers.71.mlp.down_proj.weight": "pytorch_model-00025-of-00027.bin",
@@ -634,6 +703,7 @@
     "model.layers.71.self_attn.k_proj.weight": "pytorch_model-00024-of-00027.bin",
     "model.layers.71.self_attn.o_proj.weight": "pytorch_model-00024-of-00027.bin",
     "model.layers.71.self_attn.q_proj.weight": "pytorch_model-00024-of-00027.bin",
+    "model.layers.71.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00027.bin",
     "model.layers.71.self_attn.v_proj.weight": "pytorch_model-00024-of-00027.bin",
     "model.layers.72.input_layernorm.weight": "pytorch_model-00025-of-00027.bin",
     "model.layers.72.mlp.down_proj.weight": "pytorch_model-00025-of-00027.bin",
@@ -643,6 +713,7 @@
     "model.layers.72.self_attn.k_proj.weight": "pytorch_model-00025-of-00027.bin",
     "model.layers.72.self_attn.o_proj.weight": "pytorch_model-00025-of-00027.bin",
     "model.layers.72.self_attn.q_proj.weight": "pytorch_model-00025-of-00027.bin",
+    "model.layers.72.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00027.bin",
     "model.layers.72.self_attn.v_proj.weight": "pytorch_model-00025-of-00027.bin",
     "model.layers.73.input_layernorm.weight": "pytorch_model-00025-of-00027.bin",
     "model.layers.73.mlp.down_proj.weight": "pytorch_model-00025-of-00027.bin",
@@ -652,6 +723,7 @@
     "model.layers.73.self_attn.k_proj.weight": "pytorch_model-00025-of-00027.bin",
     "model.layers.73.self_attn.o_proj.weight": "pytorch_model-00025-of-00027.bin",
     "model.layers.73.self_attn.q_proj.weight": "pytorch_model-00025-of-00027.bin",
+    "model.layers.73.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00027.bin",
     "model.layers.73.self_attn.v_proj.weight": "pytorch_model-00025-of-00027.bin",
     "model.layers.74.input_layernorm.weight": "pytorch_model-00026-of-00027.bin",
     "model.layers.74.mlp.down_proj.weight": "pytorch_model-00026-of-00027.bin",
@@ -661,6 +733,7 @@
     "model.layers.74.self_attn.k_proj.weight": "pytorch_model-00025-of-00027.bin",
     "model.layers.74.self_attn.o_proj.weight": "pytorch_model-00025-of-00027.bin",
     "model.layers.74.self_attn.q_proj.weight": "pytorch_model-00025-of-00027.bin",
+    "model.layers.74.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00027.bin",
     "model.layers.74.self_attn.v_proj.weight": "pytorch_model-00025-of-00027.bin",
     "model.layers.75.input_layernorm.weight": "pytorch_model-00026-of-00027.bin",
     "model.layers.75.mlp.down_proj.weight": "pytorch_model-00026-of-00027.bin",
@@ -670,6 +743,7 @@
     "model.layers.75.self_attn.k_proj.weight": "pytorch_model-00026-of-00027.bin",
     "model.layers.75.self_attn.o_proj.weight": "pytorch_model-00026-of-00027.bin",
     "model.layers.75.self_attn.q_proj.weight": "pytorch_model-00026-of-00027.bin",
+    "model.layers.75.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00027.bin",
     "model.layers.75.self_attn.v_proj.weight": "pytorch_model-00026-of-00027.bin",
     "model.layers.76.input_layernorm.weight": "pytorch_model-00026-of-00027.bin",
     "model.layers.76.mlp.down_proj.weight": "pytorch_model-00026-of-00027.bin",
@@ -679,6 +753,7 @@
     "model.layers.76.self_attn.k_proj.weight": "pytorch_model-00026-of-00027.bin",
     "model.layers.76.self_attn.o_proj.weight": "pytorch_model-00026-of-00027.bin",
     "model.layers.76.self_attn.q_proj.weight": "pytorch_model-00026-of-00027.bin",
+    "model.layers.76.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00027.bin",
     "model.layers.76.self_attn.v_proj.weight": "pytorch_model-00026-of-00027.bin",
     "model.layers.77.input_layernorm.weight": "pytorch_model-00027-of-00027.bin",
     "model.layers.77.mlp.down_proj.weight": "pytorch_model-00027-of-00027.bin",
@@ -688,6 +763,7 @@
     "model.layers.77.self_attn.k_proj.weight": "pytorch_model-00026-of-00027.bin",
     "model.layers.77.self_attn.o_proj.weight": "pytorch_model-00026-of-00027.bin",
     "model.layers.77.self_attn.q_proj.weight": "pytorch_model-00026-of-00027.bin",
+    "model.layers.77.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00027.bin",
     "model.layers.77.self_attn.v_proj.weight": "pytorch_model-00026-of-00027.bin",
     "model.layers.78.input_layernorm.weight": "pytorch_model-00027-of-00027.bin",
     "model.layers.78.mlp.down_proj.weight": "pytorch_model-00027-of-00027.bin",
@@ -697,6 +773,7 @@
     "model.layers.78.self_attn.k_proj.weight": "pytorch_model-00027-of-00027.bin",
     "model.layers.78.self_attn.o_proj.weight": "pytorch_model-00027-of-00027.bin",
     "model.layers.78.self_attn.q_proj.weight": "pytorch_model-00027-of-00027.bin",
+    "model.layers.78.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00027.bin",
     "model.layers.78.self_attn.v_proj.weight": "pytorch_model-00027-of-00027.bin",
     "model.layers.79.input_layernorm.weight": "pytorch_model-00027-of-00027.bin",
     "model.layers.79.mlp.down_proj.weight": "pytorch_model-00027-of-00027.bin",
@@ -706,6 +783,7 @@
     "model.layers.79.self_attn.k_proj.weight": "pytorch_model-00027-of-00027.bin",
     "model.layers.79.self_attn.o_proj.weight": "pytorch_model-00027-of-00027.bin",
     "model.layers.79.self_attn.q_proj.weight": "pytorch_model-00027-of-00027.bin",
+    "model.layers.79.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00027.bin",
     "model.layers.79.self_attn.v_proj.weight": "pytorch_model-00027-of-00027.bin",
     "model.layers.8.input_layernorm.weight": "pytorch_model-00004-of-00027.bin",
     "model.layers.8.mlp.down_proj.weight": "pytorch_model-00004-of-00027.bin",
@@ -715,6 +793,7 @@
     "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00027.bin",
     "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00027.bin",
     "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00027.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00027.bin",
     "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00027.bin",
     "model.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00027.bin",
     "model.layers.9.mlp.down_proj.weight": "pytorch_model-00004-of-00027.bin",
@@ -724,6 +803,7 @@
     "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00004-of-00027.bin",
     "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00004-of-00027.bin",
     "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00004-of-00027.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00027.bin",
     "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00004-of-00027.bin",
     "model.norm.weight": "pytorch_model-00027-of-00027.bin"
   }

special_tokens_map.json

@@ -1,9 +1,93 @@
 {
   "additional_special_tokens": [
-    "<|endofsystemprompt|>",
-    "<|beginofsystem|>",
-    "<|beginofuser|>",
-    "<|endofchat|>"
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>",
+    {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|endofsystemprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|beginofsystem|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|beginofuser|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|endofchat|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
   ],
   "bos_token": {
     "content": "<|endoftext|>",

tokenizer.json

@@ -194,7 +194,7 @@
     },
     {
       "id": 32018,
-      "content": "<|endofsystemprompt|>",
+      "content": "<tool_response>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -203,7 +203,7 @@
     },
     {
       "id": 32019,
-      "content": "<|beginofsystem|>",
+      "content": "<tool_call>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -212,7 +212,7 @@
     },
     {
       "id": 32020,
-      "content": "<|beginofuser|>",
+      "content": "<tools>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -221,6 +221,60 @@
     },
     {
       "id": 32021,
+      "content": "</tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32022,
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32023,
+      "content": "</tools>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32024,
+      "content": "<|endofsystemprompt|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32025,
+      "content": "<|beginofsystem|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32026,
+      "content": "<|beginofuser|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32027,
       "content": "<|endofchat|>",
       "single_word": false,
       "lstrip": false,
@@ -93559,4 +93613,4 @@
       "▁ ▁"
     ]
   }
-}
+}

tokenizer_config.json

@@ -1,6 +1,7 @@
 {
   "add_bos_token": false,
   "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -171,7 +172,7 @@
       "special": true
     },
     "32018": {
-      "content": "<|endofsystemprompt|>",
+      "content": "<tool_response>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -179,7 +180,7 @@
       "special": true
     },
     "32019": {
-      "content": "<|beginofsystem|>",
+      "content": "<tool_call>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -187,7 +188,7 @@
       "special": true
     },
     "32020": {
-      "content": "<|beginofuser|>",
+      "content": "<tools>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -195,6 +196,54 @@
       "special": true
     },
     "32021": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32022": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32023": {
+      "content": "</tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32024": {
+      "content": "<|endofsystemprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32025": {
+      "content": "<|beginofsystem|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32026": {
+      "content": "<|beginofuser|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32027": {
       "content": "<|endofchat|>",
       "lstrip": false,
       "normalized": false,
@@ -204,13 +253,45 @@
     }
   },
   "additional_special_tokens": [
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>",
+    "<tool_call>",
+    "<tool_response>",
+    "<tools>",
+    "</tool_call>",
+    "</tool_response>",
+    "</tools>",
     "<|endofsystemprompt|>",
     "<|beginofsystem|>",
     "<|beginofuser|>",
     "<|endofchat|>"
   ],
   "bos_token": "<|endoftext|>",
-  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|beginofuser|>' + message['content'] }}{% elif message['role'] == 'system' %}{{ message['content'] + '<|endofsystemprompt|>' }}{% elif message['role'] == 'assistant' %}{{ '<|beginofsystem|>' + message['content'] }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|beginofsystem|>' }}{% endif %}{% endfor %}",
+  "chat_template": [
+    {
+      "name": "default",
+      "template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|beginofuser|>' + message['content'] }}{% elif message['role'] == 'system' %}{{ message['content'] + '<|endofsystemprompt|>' }}{% elif message['role'] == 'assistant' %}{{ '<|beginofsystem|>' + message['content'] }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|beginofsystem|>' }}{% endif %}{% endfor %}"    },
+    {
+      "name": "tool_use",
+      "template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n    \"string\": \"str\",\n    \"number\": \"float\",\n    \"integer\": \"int\",\n    \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n    {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n    {{- \"list[\" +  json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n    {%- if json_spec.additionalProperties is defined %}\n        {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n    {%- else %}\n        {{- \"dict\" }}\n    {%- endif %}\n{%- elif json_spec.type is iterable %}\n    {{- \"Union[\" }}\n    {%- for t in json_spec.type %}\n      {{- json_to_python_type({\"type\": t}) }}\n      {%- if not loop.last %}\n        {{- \",\" }} \n    {%- endif %}\n    {%- endfor %}\n    {{- \"]\" }}\n{%- else %}\n    {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- \"You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools\\n<tools>\\n\" }}\n{%- for tool in tools %}\n    {%- if tool.function is defined %}\n        {%- set tool = tool.function %}\n    {%- endif %}\n    {{ '{\"type\": \"function\", \"function\": ' }}\n    {{- '{\"name\": ' + tool.name + '\", ' }}\n    {{- '\"description\": \"' + tool.name + '(' }}\n    {%- for param_name, param_fields in tool.parameters.properties|items %}\n        {{- param_name + \": \" + json_to_python_type(param_fields) }}\n        {%- if not loop.last %}\n            {{- \", \" }}\n        {%- endif %}\n    {%- endfor %}\n    {{- \")\" }}\n    {%- if tool.return is defined %}\n        {{- \" -> \" + json_to_python_type(tool.return) }}\n    {%- endif %}\n    {{- \" - \" + tool.description + \"\\n\\n\" }}\n    {%- for param_name, param_fields in tool.parameters.properties|items %}\n        {%- if loop.first %}\n            {{- \"    Args:\" }}\n        {%- endif %}\n        {{- \"\\n        \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n    {%- endfor %}\n    {%- if tool.return is defined and tool.return.description is defined %}\n        {{- \"\\n    Returns:\\n        \" + tool.return.description }}\n    {%- endif %}\n    {{- '\"' }}\n    {{- ', \"parameters\": ' }}\n    {%- if tool.parameters.properties | length == 0 %}\n        {{- \"{}\" }}\n    {%- else %}\n        {{- tool.parameters|tojson }}\n    {%- endif %}\n    {{- \"}\" }}\n    {%- if not loop.last %}\n        {{- \"\\n\" }}\n    {%- endif %}\n{%- endfor %}\n{{- \"\\n</tools>\\n\" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}, \"name\": {\"title\": \"Name\", \"type\": \"string\"}}, \"required\": [\"arguments\", \"name\"], \"title\": \"FunctionCall\", \"type\": \"object\"}\n' }}\n{{- \"For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:\n\" }}\n{{- \"<tool_call>\n\" }}\n{{- '{\"arguments\": <args-dict>, \"name\": <function-name>}\n' }}\n{{- '</tool_call><|endofsystemprompt|>' }}\n{%- for message in messages %}{%- if message.role == \"user\" %}{{- '<|beginofuser|>' + message.content }}{%- elif (message.role == \"assistant\" and message.tool_calls is not defined) %} {{- '<|beginofsystem|>' + message.content }}{%- elif message.role == \"assistant\" %}{{- '<tool_call>\\n' }}{%- for tool_call in message.tool_calls %}{%- if tool_call.function is defined %}{%- set tool_call = tool_call.function %}{%- endif %}{{- '{ ' }}{%- if tool_call.arguments is defined %}{{- '\"arguments\": ' }}{{- tool_call.arguments|tojson }}{{- ', '}}{%- endif %}{{- '\"name\": \"' }}{{- tool_call.name }}{{- '\"}' }}{{- '\\n</tool_call> ' }}\n        {%- endfor %}{%- elif message.role == \"tool\" %}{%- if not message.name is defined %}{{- raise_exception(\"Tool response dicts require a 'name' key indicating the name of the called function!\") }}{%- endif %}{{- '<tool_response>\\n' }}{{- '{\"name\": \"' }}{{- message.name }}{{- '\", \"content\": ' }}{{- message.content|tojson + '}' }}{{- '\\n</tool_response>\\n' }}{%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}{{- '<|beginofsystem|>' }}{%- endif %}\n"
+    }
+  ],
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "legacy": true,

tokenizer_config_bk.json

@@ -0,0 +1,304 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32019": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32020": {
+      "content": "<tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32021": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32022": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32023": {
+      "content": "</tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32024": {
+      "content": "<|endofsystemprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32025": {
+      "content": "<|beginofsystem|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32026": {
+      "content": "<|beginofuser|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32027": {
+      "content": "<|endofchat|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>",
+    "<tool_call>",
+    "<tool_response>",
+    "<tools>",
+    "</tool_call>",
+    "</tool_response>",
+    "</tools>",
+    "<|endofsystemprompt|>",
+    "<|beginofsystem|>",
+    "<|beginofuser|>",
+    "<|endofchat|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "chat_template": [
+    {
+      "name": "default",
+      "template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|beginofuser|>' + message['content'] }}{% elif message['role'] == 'system' %}{{ message['content'] + '<|endofsystemprompt|>' }}{% elif message['role'] == 'assistant' %}{{ '<|beginofsystem|>' + message['content'] }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|beginofsystem|>' }}{% endif %}{% endfor %}"    },
+    {
+      "name": "tool_use",
+      "template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n    \"string\": \"str\",\n    \"number\": \"float\",\n    \"integer\": \"int\",\n    \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n    {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n    {{- \"list[\" +  json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n    {%- if json_spec.additionalProperties is defined %}\n        {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n    {%- else %}\n        {{- \"dict\" }}\n    {%- endif %}\n{%- elif json_spec.type is iterable %}\n    {{- \"Union[\" }}\n    {%- for t in json_spec.type %}\n      {{- json_to_python_type({\"type\": t}) }}\n      {%- if not loop.last %}\n        {{- \",\" }} \n    {%- endif %}\n    {%- endfor %}\n    {{- \"]\" }}\n{%- else %}\n    {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- \"You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> \" }}\n{%- for tool in tools %}\n    {%- if tool.function is defined %}\n        {%- set tool = tool.function %}\n    {%- endif %}\n    {{- '{\"type\": \"function\", \"function\": ' }}\n    {{- '{\"name\": ' + tool.name + '\", ' }}\n    {{- '\"description\": \"' + tool.name + '(' }}\n    {%- for param_name, param_fields in tool.parameters.properties|items %}\n        {{- param_name + \": \" + json_to_python_type(param_fields) }}\n        {%- if not loop.last %}\n            {{- \", \" }}\n        {%- endif %}\n    {%- endfor %}\n    {{- \")\" }}\n    {%- if tool.return is defined %}\n        {{- \" -> \" + json_to_python_type(tool.return) }}\n    {%- endif %}\n    {{- \" - \" + tool.description + \"\\n\\n\" }}\n    {%- for param_name, param_fields in tool.parameters.properties|items %}\n        {%- if loop.first %}\n            {{- \"    Args:\\n\" }}\n        {%- endif %}\n        {{- \"        \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n    {%- endfor %}\n    {%- if tool.return is defined and tool.return.description is defined %}\n        {{- \"\\n    Returns:\\n        \" + tool.return.description }}\n    {%- endif %}\n    {{- '\"' }}\n    {{- ', \"parameters\": ' }}\n    {%- if tool.parameters.properties | length == 0 %}\n        {{- \"{}\" }}\n    {%- else %}\n        {{- tool.parameters|tojson }}\n    {%- endif %}\n    {{- \"}\" }}\n    {%- if not loop.last %}\n        {{- \"\\n\" }}\n    {%- endif %}\n{%- endfor %}\n{{- \" </tools>\" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}, \"name\": {\"title\": \"Name\", \"type\": \"string\"}}, \"required\": [\"arguments\", \"name\"], \"title\": \"FunctionCall\", \"type\": \"object\"}\n' }}\n{{- \"For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:\n\" }}\n{{- \"<tool_call>\n\" }}\n{{- '{\"arguments\": <args-dict>, \"name\": <function-name>}\n' }}\n{{- '</tool_call><|endofsystemprompt|>' }}\n{%- for message in messages %}{%- if message.role == \"user\" %}{{- '<|beginofuser|>' + message.content }}{%- if message.role == \"assistant\" and message.tool_calls is not defined) %} {{- '<|beginofsystem|>' + message.content }}{%- elif message.role == \"assistant\" %}{{- '<tool_call>\n' }}{%- for tool_call in message.tool_calls %}{%- if tool_call.function is defined %}{%- set tool_call = tool_call.function %}{%- endif %}{{- '{ ' }}{%- if tool_call.arguments is defined %}{{- '\"arguments\": ' }}{{- tool_call.arguments|tojson }}{{- ', '}}{%- endif %}{{- '\"name\": \"' }}{{- tool_call.name }}{{- '\"}' }}{{- '\n</tool_call> ' }}\n        {%- endfor %}{%- elif message.role == \"tool\" %}{%- if not message.name is defined %}{{- raise_exception(\"Tool response dicts require a 'name' key indicating the name of the called function!\") }}{%- endif %}{{- '<tool_response>\n' }}{{- '{\"name\": \"' }}{{- message.name }}{{- '\", \"content\": ' }}{{- message.content|tojson + '}' }}{{- '\n</tool_response>\n' }}{%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}{{- '<|beginofsystem|>' }}{%- endif %}\n"
+    }
+  ],
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": true,
+  "model_max_length": 8192,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}