Initial commit

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/data/cw_llm/models/merged_model",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_steps": "global_step320000",
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 30080
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.34.1"
+}

model-00001-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa7a06eaf64c15154df517854b58dd0a7e6cb7a761a2d134e5f2babe46ae37c4
+size 761398560

model-00002-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ed5c64e7444e6c25ba03875dd10322d8e957a9a60cbef675eda8be6da117ff6
+size 805521024

model-00003-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1c95466bcbf6428bf0c18c408454bfc30008d25920eca6daca09c507f19c878
+size 805521024

model-00004-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3653e5fe9a27cd2456a4cbdbb863b969209d3e77c65a0d08aee2d173e560b6c
+size 805521024

model-00005-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e38c64c484e8365463086e4768e31a1367ecd540131bb78379f77af877cc251
+size 805521024

model-00006-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0469d54a2c6f66be7478caab1e4794d55ba54127fc297593eab0e0e2edd1a0b0
+size 805521024

model-00007-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e8532df9e8fbf270a26b4684a0d31f6f19eabc9104b3d3708e33521c6a53707
+size 805521024

model-00008-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e5bc7cfa93dac89ec6858680d4ff8e3c0ea1361c9f7348aa147906348f4180d
+size 805521024

model-00009-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4232e10a8d7b0686f7c68e73aa3f0fa1d5c527bee1b20d3bca388e9fd563afd5
+size 805521024

model-00010-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7af0343957d9bf83560747136255bdb64693ec759fd9d0bf1af243bae4e2000
+size 805521024

model-00011-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f241fbc4656952e53a7a85898757c532e1459b4653c6721890ee3823d320587
+size 805521024

model-00012-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4f2a07b5cb55be59d54234ad1524cb43bd730561f73fa7a568d1b44bebe4610
+size 805521032

model-00013-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c41e66f55e5835e50c1326943226b9631293e58fde63bd5d3b3394cd06b4a19
+size 805521032

model-00014-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b92908ec8308c0e4c1cfd5fee43cb12d94b7c89a86756ed0537f8bd86245c8fe
+size 805521032

model-00015-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e4cb03ff01bc4b44f84ed43ee430f09a1aace4fd81d726b1bbad08dffa0d8e6
+size 805521032

model-00016-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:059715467a9c8d657a261f962327c2e00a19c3e2bf8748a1315b0b4260936711
+size 805521032

model-00017-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86e7d080acf25b00454298e1a8d7c6fd056d41a8a9877fb58f0c8ea861bf00e0
+size 805521032

model-00018-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:763668341c3e24ea67b7f95d74a4d60ce2ed70b28395dcee0bd95a855a1a1af9
+size 805521032

model-00019-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fe9d3c1d1af80f0fd8d65e09b279055c90c526c9a36c1c01eb9706fff5af77f
+size 805521032

model-00020-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bece06690af563e804ee69f2c8cf0f01a8df142f908472578aec1323f55add4
+size 805521032

model-00021-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2222bd92421e3ca9b10862f45f8250527386b4f66914ba21cd42502ae8b4c4aa
+size 805521032

model-00022-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff5b5f7d6abd77523a9813fbd7a3c018a4b67422d42474999652ea66fd9b957c
+size 805521032

model-00023-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad9c825b176d2597c6af45c41d85c10973de8a055361bea009f05e34a55fadd0
+size 805521032

model-00024-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72db933db41f157ddc74ff17543239329188943e9e003155dd1a115bd2d64a57
+size 805521032

model-00025-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec6672d8680db8136adaaace963fae0593490b0612bbebf17bab80997adfd0a
+size 805521032

model-00026-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aadd521bd8b77a899b61fa44dce414fe8c7c97373d644d7be5a09c2d2cc3f739
+size 805521032

model-00027-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91d1329d94c8a27fd3b3c6f71f94cca4d5f3f644bbd54c587a23e7969e3fef02
+size 805521032

model-00028-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:503d13068661bfda3ef1883a60b23420fd694a30234ff1aaeb4bfb69adf50774
+size 805521032

model-00029-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b14703df0e4a2e1a217b32737e865d3a7d483e2b0254d3d187ff5746e481f8f8
+size 536986280

model-00030-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6ce2d6b0d20ba8a70c0a782efb42a440783139c92ae9fef886f8a0124a2d609
+size 492830848

model.safetensors.index.json

@@ -0,0 +1,375 @@
+{
+  "metadata": {
+    "total_size": 23540239872
+  },
+  "weight_map": {
+    "embed_out.weight": "model-00030-of-00030.safetensors",
+    "gpt_neox.embed_in.weight": "model-00001-of-00030.safetensors",
+    "gpt_neox.final_layer_norm.bias": "model-00029-of-00030.safetensors",
+    "gpt_neox.final_layer_norm.weight": "model-00029-of-00030.safetensors",
+    "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00030.safetensors",
+    "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00030.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00030.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00030.safetensors",
+    "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "model-00001-of-00030.safetensors",
+    "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00030.safetensors",
+    "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00030.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00002-of-00030.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00002-of-00030.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00002-of-00030.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00002-of-00030.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00030.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00030.safetensors",
+    "gpt_neox.layers.1.attention.dense.bias": "model-00002-of-00030.safetensors",
+    "gpt_neox.layers.1.attention.dense.weight": "model-00002-of-00030.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "model-00002-of-00030.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "model-00002-of-00030.safetensors",
+    "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "model-00002-of-00030.safetensors",
+    "gpt_neox.layers.1.input_layernorm.bias": "model-00002-of-00030.safetensors",
+    "gpt_neox.layers.1.input_layernorm.weight": "model-00002-of-00030.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00003-of-00030.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00003-of-00030.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00003-of-00030.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00003-of-00030.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00002-of-00030.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
+    "gpt_neox.layers.10.attention.dense.bias": "model-00011-of-00030.safetensors",
+    "gpt_neox.layers.10.attention.dense.weight": "model-00011-of-00030.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "model-00011-of-00030.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "model-00011-of-00030.safetensors",
+    "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "model-00011-of-00030.safetensors",
+    "gpt_neox.layers.10.input_layernorm.bias": "model-00011-of-00030.safetensors",
+    "gpt_neox.layers.10.input_layernorm.weight": "model-00011-of-00030.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00012-of-00030.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00012-of-00030.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00012-of-00030.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00012-of-00030.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00011-of-00030.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
+    "gpt_neox.layers.11.attention.dense.bias": "model-00012-of-00030.safetensors",
+    "gpt_neox.layers.11.attention.dense.weight": "model-00012-of-00030.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "model-00012-of-00030.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "model-00012-of-00030.safetensors",
+    "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "model-00012-of-00030.safetensors",
+    "gpt_neox.layers.11.input_layernorm.bias": "model-00012-of-00030.safetensors",
+    "gpt_neox.layers.11.input_layernorm.weight": "model-00012-of-00030.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00013-of-00030.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00013-of-00030.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00013-of-00030.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00013-of-00030.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00012-of-00030.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
+    "gpt_neox.layers.12.attention.dense.bias": "model-00013-of-00030.safetensors",
+    "gpt_neox.layers.12.attention.dense.weight": "model-00013-of-00030.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "model-00013-of-00030.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "model-00013-of-00030.safetensors",
+    "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "model-00013-of-00030.safetensors",
+    "gpt_neox.layers.12.input_layernorm.bias": "model-00013-of-00030.safetensors",
+    "gpt_neox.layers.12.input_layernorm.weight": "model-00013-of-00030.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00014-of-00030.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00014-of-00030.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00014-of-00030.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00014-of-00030.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00013-of-00030.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
+    "gpt_neox.layers.13.attention.dense.bias": "model-00014-of-00030.safetensors",
+    "gpt_neox.layers.13.attention.dense.weight": "model-00014-of-00030.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "model-00014-of-00030.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "model-00014-of-00030.safetensors",
+    "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "model-00014-of-00030.safetensors",
+    "gpt_neox.layers.13.input_layernorm.bias": "model-00014-of-00030.safetensors",
+    "gpt_neox.layers.13.input_layernorm.weight": "model-00014-of-00030.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00015-of-00030.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00015-of-00030.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00015-of-00030.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00015-of-00030.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00014-of-00030.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
+    "gpt_neox.layers.14.attention.dense.bias": "model-00015-of-00030.safetensors",
+    "gpt_neox.layers.14.attention.dense.weight": "model-00015-of-00030.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "model-00015-of-00030.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "model-00015-of-00030.safetensors",
+    "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "model-00015-of-00030.safetensors",
+    "gpt_neox.layers.14.input_layernorm.bias": "model-00015-of-00030.safetensors",
+    "gpt_neox.layers.14.input_layernorm.weight": "model-00015-of-00030.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00016-of-00030.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00016-of-00030.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00016-of-00030.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00016-of-00030.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00015-of-00030.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
+    "gpt_neox.layers.15.attention.dense.bias": "model-00016-of-00030.safetensors",
+    "gpt_neox.layers.15.attention.dense.weight": "model-00016-of-00030.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "model-00016-of-00030.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "model-00016-of-00030.safetensors",
+    "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "model-00016-of-00030.safetensors",
+    "gpt_neox.layers.15.input_layernorm.bias": "model-00016-of-00030.safetensors",
+    "gpt_neox.layers.15.input_layernorm.weight": "model-00016-of-00030.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00017-of-00030.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00017-of-00030.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00017-of-00030.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00017-of-00030.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00016-of-00030.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
+    "gpt_neox.layers.16.attention.dense.bias": "model-00017-of-00030.safetensors",
+    "gpt_neox.layers.16.attention.dense.weight": "model-00017-of-00030.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.bias": "model-00017-of-00030.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.weight": "model-00017-of-00030.safetensors",
+    "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "model-00017-of-00030.safetensors",
+    "gpt_neox.layers.16.input_layernorm.bias": "model-00017-of-00030.safetensors",
+    "gpt_neox.layers.16.input_layernorm.weight": "model-00017-of-00030.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00018-of-00030.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00018-of-00030.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00018-of-00030.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00018-of-00030.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00017-of-00030.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
+    "gpt_neox.layers.17.attention.dense.bias": "model-00018-of-00030.safetensors",
+    "gpt_neox.layers.17.attention.dense.weight": "model-00018-of-00030.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.bias": "model-00018-of-00030.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.weight": "model-00018-of-00030.safetensors",
+    "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "model-00018-of-00030.safetensors",
+    "gpt_neox.layers.17.input_layernorm.bias": "model-00018-of-00030.safetensors",
+    "gpt_neox.layers.17.input_layernorm.weight": "model-00018-of-00030.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00019-of-00030.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00019-of-00030.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00019-of-00030.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00019-of-00030.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00018-of-00030.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
+    "gpt_neox.layers.18.attention.dense.bias": "model-00019-of-00030.safetensors",
+    "gpt_neox.layers.18.attention.dense.weight": "model-00019-of-00030.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "model-00019-of-00030.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "model-00019-of-00030.safetensors",
+    "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "model-00019-of-00030.safetensors",
+    "gpt_neox.layers.18.input_layernorm.bias": "model-00019-of-00030.safetensors",
+    "gpt_neox.layers.18.input_layernorm.weight": "model-00019-of-00030.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00020-of-00030.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00020-of-00030.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00020-of-00030.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00020-of-00030.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00019-of-00030.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
+    "gpt_neox.layers.19.attention.dense.bias": "model-00020-of-00030.safetensors",
+    "gpt_neox.layers.19.attention.dense.weight": "model-00020-of-00030.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "model-00020-of-00030.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "model-00020-of-00030.safetensors",
+    "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "model-00020-of-00030.safetensors",
+    "gpt_neox.layers.19.input_layernorm.bias": "model-00020-of-00030.safetensors",
+    "gpt_neox.layers.19.input_layernorm.weight": "model-00020-of-00030.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00021-of-00030.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00021-of-00030.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00021-of-00030.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00021-of-00030.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00020-of-00030.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
+    "gpt_neox.layers.2.attention.dense.bias": "model-00003-of-00030.safetensors",
+    "gpt_neox.layers.2.attention.dense.weight": "model-00003-of-00030.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "model-00003-of-00030.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "model-00003-of-00030.safetensors",
+    "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "model-00003-of-00030.safetensors",
+    "gpt_neox.layers.2.input_layernorm.bias": "model-00003-of-00030.safetensors",
+    "gpt_neox.layers.2.input_layernorm.weight": "model-00003-of-00030.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00004-of-00030.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00004-of-00030.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00004-of-00030.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00004-of-00030.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00003-of-00030.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
+    "gpt_neox.layers.20.attention.dense.bias": "model-00021-of-00030.safetensors",
+    "gpt_neox.layers.20.attention.dense.weight": "model-00021-of-00030.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "model-00021-of-00030.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "model-00021-of-00030.safetensors",
+    "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "model-00021-of-00030.safetensors",
+    "gpt_neox.layers.20.input_layernorm.bias": "model-00021-of-00030.safetensors",
+    "gpt_neox.layers.20.input_layernorm.weight": "model-00021-of-00030.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00022-of-00030.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00022-of-00030.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00022-of-00030.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00022-of-00030.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00021-of-00030.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
+    "gpt_neox.layers.21.attention.dense.bias": "model-00022-of-00030.safetensors",
+    "gpt_neox.layers.21.attention.dense.weight": "model-00022-of-00030.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "model-00022-of-00030.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "model-00022-of-00030.safetensors",
+    "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "model-00022-of-00030.safetensors",
+    "gpt_neox.layers.21.input_layernorm.bias": "model-00022-of-00030.safetensors",
+    "gpt_neox.layers.21.input_layernorm.weight": "model-00022-of-00030.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00023-of-00030.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00023-of-00030.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00023-of-00030.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00023-of-00030.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00022-of-00030.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
+    "gpt_neox.layers.22.attention.dense.bias": "model-00023-of-00030.safetensors",
+    "gpt_neox.layers.22.attention.dense.weight": "model-00023-of-00030.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "model-00023-of-00030.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "model-00023-of-00030.safetensors",
+    "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "model-00023-of-00030.safetensors",
+    "gpt_neox.layers.22.input_layernorm.bias": "model-00023-of-00030.safetensors",
+    "gpt_neox.layers.22.input_layernorm.weight": "model-00023-of-00030.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00024-of-00030.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00024-of-00030.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00024-of-00030.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00024-of-00030.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00023-of-00030.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
+    "gpt_neox.layers.23.attention.dense.bias": "model-00024-of-00030.safetensors",
+    "gpt_neox.layers.23.attention.dense.weight": "model-00024-of-00030.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "model-00024-of-00030.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "model-00024-of-00030.safetensors",
+    "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "model-00024-of-00030.safetensors",
+    "gpt_neox.layers.23.input_layernorm.bias": "model-00024-of-00030.safetensors",
+    "gpt_neox.layers.23.input_layernorm.weight": "model-00024-of-00030.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00025-of-00030.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00025-of-00030.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00025-of-00030.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00025-of-00030.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00024-of-00030.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
+    "gpt_neox.layers.24.attention.dense.bias": "model-00025-of-00030.safetensors",
+    "gpt_neox.layers.24.attention.dense.weight": "model-00025-of-00030.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.bias": "model-00025-of-00030.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.weight": "model-00025-of-00030.safetensors",
+    "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "model-00025-of-00030.safetensors",
+    "gpt_neox.layers.24.input_layernorm.bias": "model-00025-of-00030.safetensors",
+    "gpt_neox.layers.24.input_layernorm.weight": "model-00025-of-00030.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00026-of-00030.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00026-of-00030.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00026-of-00030.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00026-of-00030.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.bias": "model-00025-of-00030.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
+    "gpt_neox.layers.25.attention.dense.bias": "model-00026-of-00030.safetensors",
+    "gpt_neox.layers.25.attention.dense.weight": "model-00026-of-00030.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.bias": "model-00026-of-00030.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.weight": "model-00026-of-00030.safetensors",
+    "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "model-00026-of-00030.safetensors",
+    "gpt_neox.layers.25.input_layernorm.bias": "model-00026-of-00030.safetensors",
+    "gpt_neox.layers.25.input_layernorm.weight": "model-00026-of-00030.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00027-of-00030.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00027-of-00030.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00027-of-00030.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00027-of-00030.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.bias": "model-00026-of-00030.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
+    "gpt_neox.layers.26.attention.dense.bias": "model-00027-of-00030.safetensors",
+    "gpt_neox.layers.26.attention.dense.weight": "model-00027-of-00030.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.bias": "model-00027-of-00030.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.weight": "model-00027-of-00030.safetensors",
+    "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "model-00027-of-00030.safetensors",
+    "gpt_neox.layers.26.input_layernorm.bias": "model-00027-of-00030.safetensors",
+    "gpt_neox.layers.26.input_layernorm.weight": "model-00027-of-00030.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00028-of-00030.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00028-of-00030.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00028-of-00030.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00028-of-00030.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "model-00027-of-00030.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
+    "gpt_neox.layers.27.attention.dense.bias": "model-00028-of-00030.safetensors",
+    "gpt_neox.layers.27.attention.dense.weight": "model-00028-of-00030.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.bias": "model-00028-of-00030.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.weight": "model-00028-of-00030.safetensors",
+    "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "model-00028-of-00030.safetensors",
+    "gpt_neox.layers.27.input_layernorm.bias": "model-00028-of-00030.safetensors",
+    "gpt_neox.layers.27.input_layernorm.weight": "model-00028-of-00030.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00029-of-00030.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00029-of-00030.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00029-of-00030.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00029-of-00030.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "model-00028-of-00030.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
+    "gpt_neox.layers.3.attention.dense.bias": "model-00004-of-00030.safetensors",
+    "gpt_neox.layers.3.attention.dense.weight": "model-00004-of-00030.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "model-00004-of-00030.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "model-00004-of-00030.safetensors",
+    "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "model-00004-of-00030.safetensors",
+    "gpt_neox.layers.3.input_layernorm.bias": "model-00004-of-00030.safetensors",
+    "gpt_neox.layers.3.input_layernorm.weight": "model-00004-of-00030.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00005-of-00030.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00005-of-00030.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00005-of-00030.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00005-of-00030.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00004-of-00030.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
+    "gpt_neox.layers.4.attention.dense.bias": "model-00005-of-00030.safetensors",
+    "gpt_neox.layers.4.attention.dense.weight": "model-00005-of-00030.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "model-00005-of-00030.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "model-00005-of-00030.safetensors",
+    "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "model-00005-of-00030.safetensors",
+    "gpt_neox.layers.4.input_layernorm.bias": "model-00005-of-00030.safetensors",
+    "gpt_neox.layers.4.input_layernorm.weight": "model-00005-of-00030.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00006-of-00030.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00006-of-00030.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00006-of-00030.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00006-of-00030.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00005-of-00030.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
+    "gpt_neox.layers.5.attention.dense.bias": "model-00006-of-00030.safetensors",
+    "gpt_neox.layers.5.attention.dense.weight": "model-00006-of-00030.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "model-00006-of-00030.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "model-00006-of-00030.safetensors",
+    "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "model-00006-of-00030.safetensors",
+    "gpt_neox.layers.5.input_layernorm.bias": "model-00006-of-00030.safetensors",
+    "gpt_neox.layers.5.input_layernorm.weight": "model-00006-of-00030.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00007-of-00030.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00007-of-00030.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00007-of-00030.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00007-of-00030.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00006-of-00030.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
+    "gpt_neox.layers.6.attention.dense.bias": "model-00007-of-00030.safetensors",
+    "gpt_neox.layers.6.attention.dense.weight": "model-00007-of-00030.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "model-00007-of-00030.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "model-00007-of-00030.safetensors",
+    "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "model-00007-of-00030.safetensors",
+    "gpt_neox.layers.6.input_layernorm.bias": "model-00007-of-00030.safetensors",
+    "gpt_neox.layers.6.input_layernorm.weight": "model-00007-of-00030.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00008-of-00030.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00008-of-00030.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00008-of-00030.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00008-of-00030.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00007-of-00030.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
+    "gpt_neox.layers.7.attention.dense.bias": "model-00008-of-00030.safetensors",
+    "gpt_neox.layers.7.attention.dense.weight": "model-00008-of-00030.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "model-00008-of-00030.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "model-00008-of-00030.safetensors",
+    "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "model-00008-of-00030.safetensors",
+    "gpt_neox.layers.7.input_layernorm.bias": "model-00008-of-00030.safetensors",
+    "gpt_neox.layers.7.input_layernorm.weight": "model-00008-of-00030.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00009-of-00030.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00009-of-00030.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00009-of-00030.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00009-of-00030.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00008-of-00030.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
+    "gpt_neox.layers.8.attention.dense.bias": "model-00009-of-00030.safetensors",
+    "gpt_neox.layers.8.attention.dense.weight": "model-00009-of-00030.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "model-00009-of-00030.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "model-00009-of-00030.safetensors",
+    "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "model-00009-of-00030.safetensors",
+    "gpt_neox.layers.8.input_layernorm.bias": "model-00009-of-00030.safetensors",
+    "gpt_neox.layers.8.input_layernorm.weight": "model-00009-of-00030.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00010-of-00030.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00010-of-00030.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00010-of-00030.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00010-of-00030.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00009-of-00030.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
+    "gpt_neox.layers.9.attention.dense.bias": "model-00010-of-00030.safetensors",
+    "gpt_neox.layers.9.attention.dense.weight": "model-00010-of-00030.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "model-00010-of-00030.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "model-00010-of-00030.safetensors",
+    "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "model-00010-of-00030.safetensors",
+    "gpt_neox.layers.9.input_layernorm.bias": "model-00010-of-00030.safetensors",
+    "gpt_neox.layers.9.input_layernorm.weight": "model-00010-of-00030.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00011-of-00030.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00011-of-00030.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00011-of-00030.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00011-of-00030.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00010-of-00030.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00010-of-00030.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|sep|>",
+    "<|acc|>",
+    "<|tel|>",
+    "<|rrn|>"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,73 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|unused0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|unused1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30000": {
+      "content": "<|acc|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30001": {
+      "content": "<|tel|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30002": {
+      "content": "<|rrn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|sep|>",
+    "<|acc|>",
+    "<|tel|>",
+    "<|rrn|>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "max_length": 2048,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}