adding model and tokenizer

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "llemma-34B-Mathmix",
+  "architectures": [
+    "LlamaModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 22016,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.2"
+}

model-00001-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dfc57dc02e82ab4e88d0e862461ceced78e00a6a6c2f5cd3e598951508f8875
+size 4420863504

model-00002-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a48ab872f35de5601065272f12256e12731bc5accdbcae1a99a9e21b7127ea9f
+size 4932634120

model-00003-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:475bfb18e252aa38961944d7a408ad06d22184b4e9c205a126715e0086918233
+size 4815128184

model-00004-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9bbfd50563904434957694e255af859e3338cb5281a9517f4185f1b79fedb2a
+size 4815193936

model-00005-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cfbfcd48987af9dca41c490c72c5cad6602efd97c6e27ef8c609c0ee739aa13
+size 4815193936

model-00006-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33d76062d624a472a0e07098d276e57a1036df68d811cb63084e7386578e2691
+size 4932634120

model-00007-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b362ae3aeb0ee9b0192d817c92465b9f4db6dbfc9eed173fdd795d1445597871
+size 4815128200

model-00008-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecb7b0ab4d86cab650b6268c8cd341e8e13e3e26d27b3b5e712a1b000d21f6a6
+size 4815193952

model-00009-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a6249cc6fa38c6fe7068e201df3a3fd5f7ebd612cda3aaf7039390fb7a4fc56
+size 4815193952

model-00010-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9e9acb425446a95bd1fa7b9d6cd494e8e7526d3b57c8c46257033e340177364
+size 4932634128

model-00011-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb0ce05d306b7d2b33549bd50d6636127038ecb5933b7465fbea0662d372b9d1
+size 4815128200

model-00012-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b48bc501aaa0692907b51de12727825be1c77c901e9f39850e8849ba7bb50103
+size 4815193952

model-00013-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ecd9ddfa675f819f43498fa410f7396d25aa58b89c56b23ad66ec1bf185710
+size 4815193952

model-00014-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c89706b9f426044553c66887fe619f2a83b8b125d0307651c08ec6a20d638193
+size 4932634128

model-00015-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e07409a4dd58bddaaa89c7cb5b5fa1e252fbb10c55db264745cd8e72c6b88bf3
+size 4815128200

model-00016-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d950fe10a9ebd8e841e6091a578220506e375f9965f4fb8dcdaeedde8bc93d8
+size 4815193952

model-00017-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f68d8bd911edc80e67373843c295b732adba15e2813a4e5ed7fa601a7d57a718
+size 4815193952

model-00018-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e574aab8c957d102d85cabc7ea45c7e6112526069981cc10a545873fdc6face
+size 4932634128

model-00019-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ff9580dcf90466a78665dcbf21f1fbe8ecf8637799803774aafbe969c98eeab
+size 4815128200

model-00020-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f65aa34b96948c353543deef4b6a3e169e363cd0d66cefcedcc223319d36a947
+size 4815193952

model-00021-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a472100d086b3732b60606cdf0f925fa816e538e24144142cbb3fb4ffdeee96d
+size 4815193952

model-00022-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef147ecd4ab65584995a3bd8a72c806c1171933c0c7e1ab73329f81e7cea878
+size 4932634128

model-00023-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e93d9ca6b2f2ee053099a1246efcff1e31e1f642c239814a7277c422be6711d3
+size 4815128200

model-00024-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2600e262a83177cb22be0db343f66c7f7e4e471b11fb16807072eada5c1a9b93
+size 4815193952

model-00025-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:526738c2af5c95a1129a7b0d9ec229fa683f7d1845584f7f2a1e5236850f28bf
+size 4815193952

model-00026-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a499ad345588dae5c99225c0c9f6050bc31403de8d543c85486a67357b46cf0
+size 4932634128

model-00027-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5f0b15d7b9e710fd1585de799154e2930064feeb43e3a435f67ebeb1a49f759
+size 4815128200

model-00028-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df002a5669937e0cede7b2bb67ab5a3984a4b25293710b6c82b41d3b9c86da3a
+size 3489826184

model.safetensors.index.json

@@ -0,0 +1,441 @@
+{
+  "metadata": {
+    "total_size": 133927305216
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00028.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00028.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00028.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00028.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00028.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00028.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00028.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00028.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00028.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00028.safetensors",
+    "layers.1.input_layernorm.weight": "model-00002-of-00028.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00002-of-00028.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00002-of-00028.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00002-of-00028.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00002-of-00028.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00028.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00028.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00028.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00028.safetensors",
+    "layers.10.input_layernorm.weight": "model-00007-of-00028.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00007-of-00028.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00007-of-00028.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00007-of-00028.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00007-of-00028.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00007-of-00028.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00007-of-00028.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00007-of-00028.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00007-of-00028.safetensors",
+    "layers.11.input_layernorm.weight": "model-00008-of-00028.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00008-of-00028.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00007-of-00028.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00007-of-00028.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00008-of-00028.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00007-of-00028.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00007-of-00028.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00007-of-00028.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00007-of-00028.safetensors",
+    "layers.12.input_layernorm.weight": "model-00008-of-00028.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00008-of-00028.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00008-of-00028.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00008-of-00028.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00008-of-00028.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00008-of-00028.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00008-of-00028.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00008-of-00028.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00008-of-00028.safetensors",
+    "layers.13.input_layernorm.weight": "model-00009-of-00028.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00009-of-00028.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00008-of-00028.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00009-of-00028.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00009-of-00028.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00008-of-00028.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00008-of-00028.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00008-of-00028.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00008-of-00028.safetensors",
+    "layers.14.input_layernorm.weight": "model-00009-of-00028.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00009-of-00028.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00009-of-00028.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00009-of-00028.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00009-of-00028.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00009-of-00028.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00009-of-00028.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00009-of-00028.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00009-of-00028.safetensors",
+    "layers.15.input_layernorm.weight": "model-00010-of-00028.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00010-of-00028.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00010-of-00028.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00010-of-00028.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00010-of-00028.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00009-of-00028.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00009-of-00028.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00009-of-00028.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00009-of-00028.safetensors",
+    "layers.16.input_layernorm.weight": "model-00010-of-00028.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00010-of-00028.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00010-of-00028.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00010-of-00028.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00010-of-00028.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00010-of-00028.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00010-of-00028.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00010-of-00028.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00010-of-00028.safetensors",
+    "layers.17.input_layernorm.weight": "model-00011-of-00028.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00011-of-00028.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00011-of-00028.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00011-of-00028.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00011-of-00028.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00011-of-00028.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00011-of-00028.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00011-of-00028.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00011-of-00028.safetensors",
+    "layers.18.input_layernorm.weight": "model-00012-of-00028.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00012-of-00028.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00011-of-00028.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00011-of-00028.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00012-of-00028.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00011-of-00028.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00011-of-00028.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00011-of-00028.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00011-of-00028.safetensors",
+    "layers.19.input_layernorm.weight": "model-00012-of-00028.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00012-of-00028.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00012-of-00028.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00012-of-00028.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00012-of-00028.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00012-of-00028.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00012-of-00028.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00012-of-00028.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00012-of-00028.safetensors",
+    "layers.2.input_layernorm.weight": "model-00002-of-00028.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00002-of-00028.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00002-of-00028.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00002-of-00028.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00002-of-00028.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00002-of-00028.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00002-of-00028.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00002-of-00028.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00002-of-00028.safetensors",
+    "layers.20.input_layernorm.weight": "model-00013-of-00028.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00013-of-00028.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00012-of-00028.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00013-of-00028.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00013-of-00028.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00012-of-00028.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00012-of-00028.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00012-of-00028.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00012-of-00028.safetensors",
+    "layers.21.input_layernorm.weight": "model-00013-of-00028.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00013-of-00028.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00013-of-00028.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00013-of-00028.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00013-of-00028.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00013-of-00028.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00013-of-00028.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00013-of-00028.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00013-of-00028.safetensors",
+    "layers.22.input_layernorm.weight": "model-00014-of-00028.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00014-of-00028.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00014-of-00028.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00014-of-00028.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00014-of-00028.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00013-of-00028.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00013-of-00028.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00013-of-00028.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00013-of-00028.safetensors",
+    "layers.23.input_layernorm.weight": "model-00014-of-00028.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00014-of-00028.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00014-of-00028.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00014-of-00028.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00014-of-00028.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00014-of-00028.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00014-of-00028.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00014-of-00028.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00014-of-00028.safetensors",
+    "layers.24.input_layernorm.weight": "model-00015-of-00028.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00015-of-00028.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00015-of-00028.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00015-of-00028.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00015-of-00028.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00015-of-00028.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00015-of-00028.safetensors",
+    "layers.24.self_attn.q_proj.weight": "model-00015-of-00028.safetensors",
+    "layers.24.self_attn.v_proj.weight": "model-00015-of-00028.safetensors",
+    "layers.25.input_layernorm.weight": "model-00016-of-00028.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00016-of-00028.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00015-of-00028.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00015-of-00028.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00016-of-00028.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00015-of-00028.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00015-of-00028.safetensors",
+    "layers.25.self_attn.q_proj.weight": "model-00015-of-00028.safetensors",
+    "layers.25.self_attn.v_proj.weight": "model-00015-of-00028.safetensors",
+    "layers.26.input_layernorm.weight": "model-00016-of-00028.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00016-of-00028.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00016-of-00028.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00016-of-00028.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00016-of-00028.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00016-of-00028.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00016-of-00028.safetensors",
+    "layers.26.self_attn.q_proj.weight": "model-00016-of-00028.safetensors",
+    "layers.26.self_attn.v_proj.weight": "model-00016-of-00028.safetensors",
+    "layers.27.input_layernorm.weight": "model-00017-of-00028.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00017-of-00028.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00016-of-00028.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00017-of-00028.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00017-of-00028.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00016-of-00028.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00016-of-00028.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00016-of-00028.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00016-of-00028.safetensors",
+    "layers.28.input_layernorm.weight": "model-00017-of-00028.safetensors",
+    "layers.28.mlp.down_proj.weight": "model-00017-of-00028.safetensors",
+    "layers.28.mlp.gate_proj.weight": "model-00017-of-00028.safetensors",
+    "layers.28.mlp.up_proj.weight": "model-00017-of-00028.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00017-of-00028.safetensors",
+    "layers.28.self_attn.k_proj.weight": "model-00017-of-00028.safetensors",
+    "layers.28.self_attn.o_proj.weight": "model-00017-of-00028.safetensors",
+    "layers.28.self_attn.q_proj.weight": "model-00017-of-00028.safetensors",
+    "layers.28.self_attn.v_proj.weight": "model-00017-of-00028.safetensors",
+    "layers.29.input_layernorm.weight": "model-00018-of-00028.safetensors",
+    "layers.29.mlp.down_proj.weight": "model-00018-of-00028.safetensors",
+    "layers.29.mlp.gate_proj.weight": "model-00018-of-00028.safetensors",
+    "layers.29.mlp.up_proj.weight": "model-00018-of-00028.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00018-of-00028.safetensors",
+    "layers.29.self_attn.k_proj.weight": "model-00017-of-00028.safetensors",
+    "layers.29.self_attn.o_proj.weight": "model-00017-of-00028.safetensors",
+    "layers.29.self_attn.q_proj.weight": "model-00017-of-00028.safetensors",
+    "layers.29.self_attn.v_proj.weight": "model-00017-of-00028.safetensors",
+    "layers.3.input_layernorm.weight": "model-00003-of-00028.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00003-of-00028.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00003-of-00028.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00003-of-00028.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00003-of-00028.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00003-of-00028.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00003-of-00028.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00003-of-00028.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00003-of-00028.safetensors",
+    "layers.30.input_layernorm.weight": "model-00018-of-00028.safetensors",
+    "layers.30.mlp.down_proj.weight": "model-00018-of-00028.safetensors",
+    "layers.30.mlp.gate_proj.weight": "model-00018-of-00028.safetensors",
+    "layers.30.mlp.up_proj.weight": "model-00018-of-00028.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00018-of-00028.safetensors",
+    "layers.30.self_attn.k_proj.weight": "model-00018-of-00028.safetensors",
+    "layers.30.self_attn.o_proj.weight": "model-00018-of-00028.safetensors",
+    "layers.30.self_attn.q_proj.weight": "model-00018-of-00028.safetensors",
+    "layers.30.self_attn.v_proj.weight": "model-00018-of-00028.safetensors",
+    "layers.31.input_layernorm.weight": "model-00019-of-00028.safetensors",
+    "layers.31.mlp.down_proj.weight": "model-00019-of-00028.safetensors",
+    "layers.31.mlp.gate_proj.weight": "model-00019-of-00028.safetensors",
+    "layers.31.mlp.up_proj.weight": "model-00019-of-00028.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00019-of-00028.safetensors",
+    "layers.31.self_attn.k_proj.weight": "model-00019-of-00028.safetensors",
+    "layers.31.self_attn.o_proj.weight": "model-00019-of-00028.safetensors",
+    "layers.31.self_attn.q_proj.weight": "model-00019-of-00028.safetensors",
+    "layers.31.self_attn.v_proj.weight": "model-00019-of-00028.safetensors",
+    "layers.32.input_layernorm.weight": "model-00020-of-00028.safetensors",
+    "layers.32.mlp.down_proj.weight": "model-00020-of-00028.safetensors",
+    "layers.32.mlp.gate_proj.weight": "model-00019-of-00028.safetensors",
+    "layers.32.mlp.up_proj.weight": "model-00019-of-00028.safetensors",
+    "layers.32.post_attention_layernorm.weight": "model-00020-of-00028.safetensors",
+    "layers.32.self_attn.k_proj.weight": "model-00019-of-00028.safetensors",
+    "layers.32.self_attn.o_proj.weight": "model-00019-of-00028.safetensors",
+    "layers.32.self_attn.q_proj.weight": "model-00019-of-00028.safetensors",
+    "layers.32.self_attn.v_proj.weight": "model-00019-of-00028.safetensors",
+    "layers.33.input_layernorm.weight": "model-00020-of-00028.safetensors",
+    "layers.33.mlp.down_proj.weight": "model-00020-of-00028.safetensors",
+    "layers.33.mlp.gate_proj.weight": "model-00020-of-00028.safetensors",
+    "layers.33.mlp.up_proj.weight": "model-00020-of-00028.safetensors",
+    "layers.33.post_attention_layernorm.weight": "model-00020-of-00028.safetensors",
+    "layers.33.self_attn.k_proj.weight": "model-00020-of-00028.safetensors",
+    "layers.33.self_attn.o_proj.weight": "model-00020-of-00028.safetensors",
+    "layers.33.self_attn.q_proj.weight": "model-00020-of-00028.safetensors",
+    "layers.33.self_attn.v_proj.weight": "model-00020-of-00028.safetensors",
+    "layers.34.input_layernorm.weight": "model-00021-of-00028.safetensors",
+    "layers.34.mlp.down_proj.weight": "model-00021-of-00028.safetensors",
+    "layers.34.mlp.gate_proj.weight": "model-00020-of-00028.safetensors",
+    "layers.34.mlp.up_proj.weight": "model-00021-of-00028.safetensors",
+    "layers.34.post_attention_layernorm.weight": "model-00021-of-00028.safetensors",
+    "layers.34.self_attn.k_proj.weight": "model-00020-of-00028.safetensors",
+    "layers.34.self_attn.o_proj.weight": "model-00020-of-00028.safetensors",
+    "layers.34.self_attn.q_proj.weight": "model-00020-of-00028.safetensors",
+    "layers.34.self_attn.v_proj.weight": "model-00020-of-00028.safetensors",
+    "layers.35.input_layernorm.weight": "model-00021-of-00028.safetensors",
+    "layers.35.mlp.down_proj.weight": "model-00021-of-00028.safetensors",
+    "layers.35.mlp.gate_proj.weight": "model-00021-of-00028.safetensors",
+    "layers.35.mlp.up_proj.weight": "model-00021-of-00028.safetensors",
+    "layers.35.post_attention_layernorm.weight": "model-00021-of-00028.safetensors",
+    "layers.35.self_attn.k_proj.weight": "model-00021-of-00028.safetensors",
+    "layers.35.self_attn.o_proj.weight": "model-00021-of-00028.safetensors",
+    "layers.35.self_attn.q_proj.weight": "model-00021-of-00028.safetensors",
+    "layers.35.self_attn.v_proj.weight": "model-00021-of-00028.safetensors",
+    "layers.36.input_layernorm.weight": "model-00022-of-00028.safetensors",
+    "layers.36.mlp.down_proj.weight": "model-00022-of-00028.safetensors",
+    "layers.36.mlp.gate_proj.weight": "model-00022-of-00028.safetensors",
+    "layers.36.mlp.up_proj.weight": "model-00022-of-00028.safetensors",
+    "layers.36.post_attention_layernorm.weight": "model-00022-of-00028.safetensors",
+    "layers.36.self_attn.k_proj.weight": "model-00021-of-00028.safetensors",
+    "layers.36.self_attn.o_proj.weight": "model-00021-of-00028.safetensors",
+    "layers.36.self_attn.q_proj.weight": "model-00021-of-00028.safetensors",
+    "layers.36.self_attn.v_proj.weight": "model-00021-of-00028.safetensors",
+    "layers.37.input_layernorm.weight": "model-00022-of-00028.safetensors",
+    "layers.37.mlp.down_proj.weight": "model-00022-of-00028.safetensors",
+    "layers.37.mlp.gate_proj.weight": "model-00022-of-00028.safetensors",
+    "layers.37.mlp.up_proj.weight": "model-00022-of-00028.safetensors",
+    "layers.37.post_attention_layernorm.weight": "model-00022-of-00028.safetensors",
+    "layers.37.self_attn.k_proj.weight": "model-00022-of-00028.safetensors",
+    "layers.37.self_attn.o_proj.weight": "model-00022-of-00028.safetensors",
+    "layers.37.self_attn.q_proj.weight": "model-00022-of-00028.safetensors",
+    "layers.37.self_attn.v_proj.weight": "model-00022-of-00028.safetensors",
+    "layers.38.input_layernorm.weight": "model-00023-of-00028.safetensors",
+    "layers.38.mlp.down_proj.weight": "model-00023-of-00028.safetensors",
+    "layers.38.mlp.gate_proj.weight": "model-00023-of-00028.safetensors",
+    "layers.38.mlp.up_proj.weight": "model-00023-of-00028.safetensors",
+    "layers.38.post_attention_layernorm.weight": "model-00023-of-00028.safetensors",
+    "layers.38.self_attn.k_proj.weight": "model-00023-of-00028.safetensors",
+    "layers.38.self_attn.o_proj.weight": "model-00023-of-00028.safetensors",
+    "layers.38.self_attn.q_proj.weight": "model-00023-of-00028.safetensors",
+    "layers.38.self_attn.v_proj.weight": "model-00023-of-00028.safetensors",
+    "layers.39.input_layernorm.weight": "model-00024-of-00028.safetensors",
+    "layers.39.mlp.down_proj.weight": "model-00024-of-00028.safetensors",
+    "layers.39.mlp.gate_proj.weight": "model-00023-of-00028.safetensors",
+    "layers.39.mlp.up_proj.weight": "model-00023-of-00028.safetensors",
+    "layers.39.post_attention_layernorm.weight": "model-00024-of-00028.safetensors",
+    "layers.39.self_attn.k_proj.weight": "model-00023-of-00028.safetensors",
+    "layers.39.self_attn.o_proj.weight": "model-00023-of-00028.safetensors",
+    "layers.39.self_attn.q_proj.weight": "model-00023-of-00028.safetensors",
+    "layers.39.self_attn.v_proj.weight": "model-00023-of-00028.safetensors",
+    "layers.4.input_layernorm.weight": "model-00004-of-00028.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00004-of-00028.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00003-of-00028.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00003-of-00028.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00004-of-00028.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00003-of-00028.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00003-of-00028.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00003-of-00028.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00003-of-00028.safetensors",
+    "layers.40.input_layernorm.weight": "model-00024-of-00028.safetensors",
+    "layers.40.mlp.down_proj.weight": "model-00024-of-00028.safetensors",
+    "layers.40.mlp.gate_proj.weight": "model-00024-of-00028.safetensors",
+    "layers.40.mlp.up_proj.weight": "model-00024-of-00028.safetensors",
+    "layers.40.post_attention_layernorm.weight": "model-00024-of-00028.safetensors",
+    "layers.40.self_attn.k_proj.weight": "model-00024-of-00028.safetensors",
+    "layers.40.self_attn.o_proj.weight": "model-00024-of-00028.safetensors",
+    "layers.40.self_attn.q_proj.weight": "model-00024-of-00028.safetensors",
+    "layers.40.self_attn.v_proj.weight": "model-00024-of-00028.safetensors",
+    "layers.41.input_layernorm.weight": "model-00025-of-00028.safetensors",
+    "layers.41.mlp.down_proj.weight": "model-00025-of-00028.safetensors",
+    "layers.41.mlp.gate_proj.weight": "model-00024-of-00028.safetensors",
+    "layers.41.mlp.up_proj.weight": "model-00025-of-00028.safetensors",
+    "layers.41.post_attention_layernorm.weight": "model-00025-of-00028.safetensors",
+    "layers.41.self_attn.k_proj.weight": "model-00024-of-00028.safetensors",
+    "layers.41.self_attn.o_proj.weight": "model-00024-of-00028.safetensors",
+    "layers.41.self_attn.q_proj.weight": "model-00024-of-00028.safetensors",
+    "layers.41.self_attn.v_proj.weight": "model-00024-of-00028.safetensors",
+    "layers.42.input_layernorm.weight": "model-00025-of-00028.safetensors",
+    "layers.42.mlp.down_proj.weight": "model-00025-of-00028.safetensors",
+    "layers.42.mlp.gate_proj.weight": "model-00025-of-00028.safetensors",
+    "layers.42.mlp.up_proj.weight": "model-00025-of-00028.safetensors",
+    "layers.42.post_attention_layernorm.weight": "model-00025-of-00028.safetensors",
+    "layers.42.self_attn.k_proj.weight": "model-00025-of-00028.safetensors",
+    "layers.42.self_attn.o_proj.weight": "model-00025-of-00028.safetensors",
+    "layers.42.self_attn.q_proj.weight": "model-00025-of-00028.safetensors",
+    "layers.42.self_attn.v_proj.weight": "model-00025-of-00028.safetensors",
+    "layers.43.input_layernorm.weight": "model-00026-of-00028.safetensors",
+    "layers.43.mlp.down_proj.weight": "model-00026-of-00028.safetensors",
+    "layers.43.mlp.gate_proj.weight": "model-00026-of-00028.safetensors",
+    "layers.43.mlp.up_proj.weight": "model-00026-of-00028.safetensors",
+    "layers.43.post_attention_layernorm.weight": "model-00026-of-00028.safetensors",
+    "layers.43.self_attn.k_proj.weight": "model-00025-of-00028.safetensors",
+    "layers.43.self_attn.o_proj.weight": "model-00025-of-00028.safetensors",
+    "layers.43.self_attn.q_proj.weight": "model-00025-of-00028.safetensors",
+    "layers.43.self_attn.v_proj.weight": "model-00025-of-00028.safetensors",
+    "layers.44.input_layernorm.weight": "model-00026-of-00028.safetensors",
+    "layers.44.mlp.down_proj.weight": "model-00026-of-00028.safetensors",
+    "layers.44.mlp.gate_proj.weight": "model-00026-of-00028.safetensors",
+    "layers.44.mlp.up_proj.weight": "model-00026-of-00028.safetensors",
+    "layers.44.post_attention_layernorm.weight": "model-00026-of-00028.safetensors",
+    "layers.44.self_attn.k_proj.weight": "model-00026-of-00028.safetensors",
+    "layers.44.self_attn.o_proj.weight": "model-00026-of-00028.safetensors",
+    "layers.44.self_attn.q_proj.weight": "model-00026-of-00028.safetensors",
+    "layers.44.self_attn.v_proj.weight": "model-00026-of-00028.safetensors",
+    "layers.45.input_layernorm.weight": "model-00027-of-00028.safetensors",
+    "layers.45.mlp.down_proj.weight": "model-00027-of-00028.safetensors",
+    "layers.45.mlp.gate_proj.weight": "model-00027-of-00028.safetensors",
+    "layers.45.mlp.up_proj.weight": "model-00027-of-00028.safetensors",
+    "layers.45.post_attention_layernorm.weight": "model-00027-of-00028.safetensors",
+    "layers.45.self_attn.k_proj.weight": "model-00027-of-00028.safetensors",
+    "layers.45.self_attn.o_proj.weight": "model-00027-of-00028.safetensors",
+    "layers.45.self_attn.q_proj.weight": "model-00027-of-00028.safetensors",
+    "layers.45.self_attn.v_proj.weight": "model-00027-of-00028.safetensors",
+    "layers.46.input_layernorm.weight": "model-00028-of-00028.safetensors",
+    "layers.46.mlp.down_proj.weight": "model-00028-of-00028.safetensors",
+    "layers.46.mlp.gate_proj.weight": "model-00027-of-00028.safetensors",
+    "layers.46.mlp.up_proj.weight": "model-00027-of-00028.safetensors",
+    "layers.46.post_attention_layernorm.weight": "model-00028-of-00028.safetensors",
+    "layers.46.self_attn.k_proj.weight": "model-00027-of-00028.safetensors",
+    "layers.46.self_attn.o_proj.weight": "model-00027-of-00028.safetensors",
+    "layers.46.self_attn.q_proj.weight": "model-00027-of-00028.safetensors",
+    "layers.46.self_attn.v_proj.weight": "model-00027-of-00028.safetensors",
+    "layers.47.input_layernorm.weight": "model-00028-of-00028.safetensors",
+    "layers.47.mlp.down_proj.weight": "model-00028-of-00028.safetensors",
+    "layers.47.mlp.gate_proj.weight": "model-00028-of-00028.safetensors",
+    "layers.47.mlp.up_proj.weight": "model-00028-of-00028.safetensors",
+    "layers.47.post_attention_layernorm.weight": "model-00028-of-00028.safetensors",
+    "layers.47.self_attn.k_proj.weight": "model-00028-of-00028.safetensors",
+    "layers.47.self_attn.o_proj.weight": "model-00028-of-00028.safetensors",
+    "layers.47.self_attn.q_proj.weight": "model-00028-of-00028.safetensors",
+    "layers.47.self_attn.v_proj.weight": "model-00028-of-00028.safetensors",
+    "layers.5.input_layernorm.weight": "model-00004-of-00028.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00004-of-00028.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00004-of-00028.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00004-of-00028.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00004-of-00028.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00004-of-00028.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00004-of-00028.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00004-of-00028.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00004-of-00028.safetensors",
+    "layers.6.input_layernorm.weight": "model-00005-of-00028.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00005-of-00028.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00004-of-00028.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00005-of-00028.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00005-of-00028.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00004-of-00028.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00004-of-00028.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00004-of-00028.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00004-of-00028.safetensors",
+    "layers.7.input_layernorm.weight": "model-00005-of-00028.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00005-of-00028.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00005-of-00028.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00005-of-00028.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00005-of-00028.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00005-of-00028.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00005-of-00028.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00005-of-00028.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00005-of-00028.safetensors",
+    "layers.8.input_layernorm.weight": "model-00006-of-00028.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00006-of-00028.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00006-of-00028.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00006-of-00028.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00006-of-00028.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00005-of-00028.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00005-of-00028.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00005-of-00028.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00005-of-00028.safetensors",
+    "layers.9.input_layernorm.weight": "model-00006-of-00028.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00006-of-00028.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00006-of-00028.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00006-of-00028.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00006-of-00028.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00006-of-00028.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00006-of-00028.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00006-of-00028.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00006-of-00028.safetensors",
+    "norm.weight": "model-00028-of-00028.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}