Upload 7 files

config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "ScalarModel"
+  ],
+  "base_config": {
+    "_name_or_path": "./models/sft_model_2.9",
+    "architectures": [
+      "GPTNeoXForCausalLM"
+    ],
+    "eos_token_id": 0,
+    "hidden_size": 2560,
+    "intermediate_size": 10240,
+    "model_type": "gpt_neox",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 32,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 50304
+  },
+  "base_model": "./models/sft_model_2.9",
+  "bias": 2.53739437142289,
+  "hidden_size": 2560,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.0"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44f7821ec09a809fc8d3d210e0bdd447871ec3f6919d1f2210927b6d3ce54aac
+size 4978292117

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:697cc79336f669f0129be9353e63683b1cd75ac7acf343507ce607f853414d7b
+size 314709466

pytorch_model.bin.index.json

@@ -0,0 +1,396 @@
+{
+  "metadata": {
+    "total_size": 5292866562
+  },
+  "weight_map": {
+    "lm_backbone.embed_in.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.0.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.0.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.22.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.22.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.22.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.22.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.22.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.22.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.23.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.23.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.23.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.23.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.23.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.23.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.24.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.24.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.24.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.24.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.24.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.24.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.24.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.24.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.25.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.25.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.25.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.25.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.25.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.25.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.25.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.25.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.26.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.26.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.26.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.26.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.26.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.26.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.26.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.26.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.27.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.27.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.27.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.27.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.27.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.27.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.27.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.27.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.28.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.28.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.28.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.28.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.28.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.28.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.28.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.28.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.29.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.29.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.29.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.29.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.29.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.29.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.29.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.29.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.3.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.3.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.30.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.30.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.30.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.30.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.30.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.30.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.30.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.30.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.31.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.31.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.31.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.31.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.31.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.31.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.4.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.4.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "scalar_head.bias": "pytorch_model-00002-of-00002.bin",
+    "scalar_head.weight": "pytorch_model-00002-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,221 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}