Upload model

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "/content/models/StableLM-3B",
+  "architectures": [
+    "StableLMEpochForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_stablelm_epoch.StableLMEpochConfig",
+    "AutoModelForCausalLM": "modeling_stablelm_epoch.StableLMEpochForCausalLM"
+  },
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 6912,
+  "max_position_embeddings": 4096,
+  "model_type": "stablelm_epoch",
+  "norm_eps": 1e-05,
+  "num_attention_heads": 32,
+  "num_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "rope_pct": 0.25,
+  "rope_theta": 10000,
+  "rotary_scaling_factor": 1.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 50304
+}

configuration_stablelm_epoch.py

@@ -0,0 +1,110 @@
+# coding=utf-8
+# Copyright 2023 Stability and The HuggingFace Inc. team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+""" StableLM Epoch model configuration"""
+from transformers import PretrainedConfig
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+
+class StableLMEpochConfig(PretrainedConfig):
+    r"""
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 50_304):
+            Vocabulary size of the StableLM model. Defines the number of different tokens that
+            can be represented by the `inputs_ids` passed when calling [`StableLMEpochModel`].
+        intermediate_size (`int`, *optional*, defaults to 6912):
+            Dimension of the MLP representations.
+        hidden_size (`int`, *optional*, defaults to 2560):
+            Dimension of the decoder layers and the pooler layer.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer decoder.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer encoder.
+        num_key_value_heads (`int`, *optional*):
+            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
+            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
+            `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
+            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
+            by meanpooling all the original heads within that group. For more details checkout [this
+            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
+            `num_attention_heads`.
+        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
+            The non-linear activation function (function or string).
+        rope_pct (`float`, *optional*, defaults to 1.0):
+            Percentage of hidden dimensions to allocate to rotary embeddings.
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        max_position_embeddings (`int`, *optional*, defaults to 2048):
+            The maximum sequence length that this model might ever be used with.
+            Typically set this to something large just in case (e.g., 512 or 1024 or 2048).
+        initializer_range (`float`, *optional*, defaults to 1e-5):
+            The standard deviation of the truncated_normal_initializer for initializing
+             all weight matrices.
+        norm_eps (`float`, *optional*, defaults to 1e-8):
+            The epsilon used by the normalization layers.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions
+            (not used by all models). Only relevant if `config.is_decoder=True`.
+        tie_word_embeddings(`bool`, *optional*, defaults to `False`):
+            Whether to tie weight embeddings
+    """
+    model_type = "stablelm_epoch"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=50_304,
+        intermediate_size=6912,
+        hidden_size=2560,
+        num_hidden_layers=32,
+        num_attention_heads=32,
+        num_key_value_heads=32,
+        hidden_act="silu",
+        rope_pct=0.25,
+        rope_theta=10_000,
+        max_position_embeddings=4096,
+        initializer_range=0.02,
+        norm_eps=1.0e-5,
+        use_cache=True,
+        bos_token_id=0,
+        eos_token_id=2,
+        tie_word_embeddings=False,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.intermediate_size = intermediate_size
+        self.hidden_size = hidden_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.rope_pct = rope_pct
+        self.rope_theta = rope_theta
+        self.initializer_range = initializer_range
+        self.norm_eps = norm_eps
+        self.use_cache = use_cache
+        self.tie_word_embeddings = tie_word_embeddings
+        super().__init__(
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )

model-00001-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad99b98ee94c59329f71a6064de5afe5b3e89b438e01a2785cee826ef2f6821
+size 257556616

model-00002-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:415b0487b436334ff32cee993becb8e0c1a9b612ffa653f3f920a32ba9b1b745
+size 158629304

model-00003-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4e478acda93bc1365dea58f5670c2054f670012df9653df2182a334b83cd1fc
+size 158618864

model-00004-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20a98c35d3f06d2727382d630fb622ed86602f05201d4e36530ba2a3f3243819
+size 158618864

model-00005-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f909ee2c7281b56f8e130c85a78af6e5c7a0726fe90a6c40785bdf8085a87580
+size 158608408

model-00006-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f48cb7244b2bd50167e895ad07edeed752e0b5f5cb0f2162d36604f08c1b7ae
+size 158597944

model-00007-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9fc3126a4e4a2ff2c0344c7282d4fb139075cbbeb835e17fd81eb50b23d0864
+size 158629312

model-00008-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0467d41b07675242263dd27ba2d5e04fd82175eda449805d81cf6318ff183b1e
+size 158618856

model-00009-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48630e77a2557430311a56ef2f3311e1d5e15c2d6d89ac6e9726013660a637d8
+size 158618856

model-00010-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfb2b2860e5df49e2b1ca3a96e601181a49f635ab37d5936eb9a13d962d273e6
+size 158618856

model-00011-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38e8f32367ca903db2c44534dd2a876675c76d546aa29a4628f83ac360a7defa
+size 158618856

model-00012-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a21231d1c360231bdd9b8e83227be229e2e3763be9eb3ec3d6c12ead4dfb5f2e
+size 158639768

model-00013-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e70e7ad9d803a0aae4d156b54a56cda418cfa7fdfa0307c18fc73699ac314d1
+size 158618872

model-00014-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db54223efab9dcf6c0905c57d784ba4e7ad91e0368e1dcd3886e02e1ca3b53fe
+size 158618872

model-00015-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9805cde33ba747cc1fceb29f4aca182e6ec8ddc7224f4fdec523840853dad223
+size 158618872

model-00016-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70e30d8748be612f871b3014e2ed08c88303de3634978651d851f05e5aff6ea0
+size 158618872

model-00017-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a475eeff76bb6d2e9ce102f65263cd4bfbea74ef91eddd00084bf40b3aa2eb8c
+size 158618872

model-00018-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07292e3c7c4630e05582696e9e67785a4eb52705c7f55c2cea0272ada48ed3a7
+size 158618872

model-00019-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34aabdcbc2eaed2175cd54ab6f833e75aa734c4c83be6a4bfa99610ad170a3d2
+size 158618872

model-00020-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:781310f005f0f78ff4ab3d663200b60244c240f137cda13021d82103ce5355a1
+size 158618872

model-00021-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1c0a6b4769049a0559ace8796b57b0dc4cf79389f251d1538898d57dfb45844
+size 158618872

model-00022-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40879e45708d09a2219ef9cc665be6e93f17b80cc01a12668655b1f38ffaf92e
+size 158618872

model-00023-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88451a83603276e2fbc37fb8e5b956c21883013be8ef9843db44be04364a1ba3
+size 158618872

model-00024-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b2b4b32bd934cd727117bde8f83d8c5c094a935db3129e1b75e90f1468ba5a9
+size 158608416

model-00025-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:827d1f09f71e7d2ef3bcfe05cef1819aa0bc5d9152d549b032c726877832e1c3
+size 158629312

model-00026-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb4dced55865fb7ef2e38305a5fa06cfadcd705896341f5bebf00c30bfe7283b
+size 158618872

model-00027-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2449d7f0062f5bf2092f4a3ef2668792a675c1e3087ed2ae3087f10ccabff3de
+size 158618872

model-00028-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b65a426db112aa56a79d5cf1ec31367fc348bb2b21a687621f648931d50e9f73
+size 158618872

model-00029-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feb10ba5b2d82aa0e5d3929c51e996d4d849e321b6a8a3d3bf454be2e26739ba
+size 158618872

model-00030-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f75f71022765cdbc73e09210820886d35542c5e13639967f4afa266848fe0739
+size 158608416

model-00031-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:479f8718971f6f1d9a9bce40db49669dbd5fbbef4b0bf51aa759193146fae847
+size 52429288

model-00032-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:854c6c4652d86ec6645ec93af1fb1d75af7ed688a46ca3fcd2c910145578d355
+size 257556608

model-00033-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48e751952dbb37ed9a70195d2d7fe8b34dd6fb6276a433ad4b676b286de9e725
+size 141589608

model-00034-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4326f5523d19e65390253c47a95ca0c8797f8ddda70027b55e4ad404cd1882ee
+size 158618864

model-00035-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4766d49a6acbf654b83815293c9bb850f2fde2bad4888ad45d49ca5cc1c23801
+size 123229272

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.3"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00035.safetensors", "model.layers.0.input_layernorm.bias": "model-00002-of-00035.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00035.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00035.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00035.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00035.safetensors", "model.layers.0.post_attention_layernorm.bias": "model-00002-of-00035.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00035.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00035.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00035.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00035.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00035.safetensors", "model.layers.1.input_layernorm.bias": "model-00002-of-00035.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00035.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00035.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00035.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00035.safetensors", "model.layers.1.post_attention_layernorm.bias": "model-00003-of-00035.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00035.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00035.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00035.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00035.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00035.safetensors", "model.layers.2.input_layernorm.bias": "model-00003-of-00035.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00035.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00035.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00035.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00035.safetensors", "model.layers.2.post_attention_layernorm.bias": "model-00004-of-00035.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00035.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00035.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00035.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00035.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00035.safetensors", "model.layers.3.input_layernorm.bias": "model-00004-of-00035.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00035.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00005-of-00035.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00035.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00005-of-00035.safetensors", "model.layers.3.post_attention_layernorm.bias": "model-00005-of-00035.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00035.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00035.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00035.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00035.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00035.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00006-of-00035.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00006-of-00035.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00006-of-00035.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00006-of-00035.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00006-of-00035.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00035.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00006-of-00035.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00007-of-00035.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00007-of-00035.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00035.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00007-of-00035.safetensors", "model.layers.4.input_layernorm.bias": "model-00007-of-00035.safetensors", "model.layers.4.input_layernorm.weight": "model-00007-of-00035.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00007-of-00035.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00007-of-00035.safetensors", "model.layers.4.post_attention_layernorm.bias": "model-00007-of-00035.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00007-of-00035.safetensors", "model.layers.5.input_layernorm.bias": "model-00007-of-00035.safetensors", "model.layers.5.input_layernorm.weight": "model-00007-of-00035.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00007-of-00035.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00008-of-00035.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00008-of-00035.safetensors", "model.layers.5.post_attention_layernorm.bias": "model-00008-of-00035.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00008-of-00035.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00008-of-00035.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00008-of-00035.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00008-of-00035.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00008-of-00035.safetensors", "model.layers.6.input_layernorm.bias": "model-00008-of-00035.safetensors", "model.layers.6.input_layernorm.weight": "model-00008-of-00035.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00008-of-00035.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00009-of-00035.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00009-of-00035.safetensors", "model.layers.6.post_attention_layernorm.bias": "model-00009-of-00035.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00009-of-00035.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00009-of-00035.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00009-of-00035.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00009-of-00035.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00009-of-00035.safetensors", "model.layers.7.input_layernorm.bias": "model-00009-of-00035.safetensors", "model.layers.7.input_layernorm.weight": "model-00009-of-00035.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00009-of-00035.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00010-of-00035.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00010-of-00035.safetensors", "model.layers.7.post_attention_layernorm.bias": "model-00010-of-00035.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00010-of-00035.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00035.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00010-of-00035.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00035.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00010-of-00035.safetensors", "model.layers.8.input_layernorm.bias": "model-00010-of-00035.safetensors", "model.layers.8.input_layernorm.weight": "model-00010-of-00035.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00010-of-00035.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00011-of-00035.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00011-of-00035.safetensors", "model.layers.8.post_attention_layernorm.bias": "model-00011-of-00035.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00011-of-00035.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00011-of-00035.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00011-of-00035.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00011-of-00035.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00011-of-00035.safetensors", "model.layers.9.input_layernorm.bias": "model-00011-of-00035.safetensors", "model.layers.9.input_layernorm.weight": "model-00011-of-00035.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00011-of-00035.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00012-of-00035.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00012-of-00035.safetensors", "model.layers.9.post_attention_layernorm.bias": "model-00012-of-00035.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00012-of-00035.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00012-of-00035.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00012-of-00035.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00012-of-00035.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00012-of-00035.safetensors", "model.layers.10.input_layernorm.bias": "model-00012-of-00035.safetensors", "model.layers.10.input_layernorm.weight": "model-00012-of-00035.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00012-of-00035.safetensors", "model.layers.10.post_attention_layernorm.bias": "model-00012-of-00035.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00012-of-00035.safetensors", "model.layers.11.input_layernorm.bias": "model-00012-of-00035.safetensors", "model.layers.11.input_layernorm.weight": "model-00012-of-00035.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00013-of-00035.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00013-of-00035.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00013-of-00035.safetensors", "model.layers.11.post_attention_layernorm.bias": "model-00013-of-00035.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00013-of-00035.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00013-of-00035.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00013-of-00035.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00013-of-00035.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00013-of-00035.safetensors", "model.layers.12.input_layernorm.bias": "model-00013-of-00035.safetensors", "model.layers.12.input_layernorm.weight": "model-00013-of-00035.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00014-of-00035.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00014-of-00035.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00014-of-00035.safetensors", "model.layers.12.post_attention_layernorm.bias": "model-00014-of-00035.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00014-of-00035.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00014-of-00035.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00014-of-00035.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00014-of-00035.safetensors", "model.layers.13.input_layernorm.bias": "model-00014-of-00035.safetensors", "model.layers.13.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00015-of-00035.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00015-of-00035.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00015-of-00035.safetensors", "model.layers.13.post_attention_layernorm.bias": "model-00015-of-00035.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00015-of-00035.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00015-of-00035.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00015-of-00035.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00015-of-00035.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00015-of-00035.safetensors", "model.layers.14.input_layernorm.bias": "model-00015-of-00035.safetensors", "model.layers.14.input_layernorm.weight": "model-00015-of-00035.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00016-of-00035.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00016-of-00035.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00016-of-00035.safetensors", "model.layers.14.post_attention_layernorm.bias": "model-00016-of-00035.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00016-of-00035.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00016-of-00035.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00016-of-00035.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00016-of-00035.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00016-of-00035.safetensors", "model.layers.15.input_layernorm.bias": "model-00016-of-00035.safetensors", "model.layers.15.input_layernorm.weight": "model-00016-of-00035.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00017-of-00035.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00017-of-00035.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00017-of-00035.safetensors", "model.layers.15.post_attention_layernorm.bias": "model-00017-of-00035.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00017-of-00035.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00017-of-00035.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00017-of-00035.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00017-of-00035.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00017-of-00035.safetensors", "model.layers.16.input_layernorm.bias": "model-00017-of-00035.safetensors", "model.layers.16.input_layernorm.weight": "model-00017-of-00035.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00018-of-00035.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00018-of-00035.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00018-of-00035.safetensors", "model.layers.16.post_attention_layernorm.bias": "model-00018-of-00035.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00018-of-00035.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00018-of-00035.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00018-of-00035.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00018-of-00035.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00018-of-00035.safetensors", "model.layers.17.input_layernorm.bias": "model-00018-of-00035.safetensors", "model.layers.17.input_layernorm.weight": "model-00018-of-00035.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00019-of-00035.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00019-of-00035.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00019-of-00035.safetensors", "model.layers.17.post_attention_layernorm.bias": "model-00019-of-00035.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00019-of-00035.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00019-of-00035.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00019-of-00035.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00019-of-00035.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00019-of-00035.safetensors", "model.layers.18.input_layernorm.bias": "model-00019-of-00035.safetensors", "model.layers.18.input_layernorm.weight": "model-00019-of-00035.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00020-of-00035.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00020-of-00035.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00020-of-00035.safetensors", "model.layers.18.post_attention_layernorm.bias": "model-00020-of-00035.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00020-of-00035.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00020-of-00035.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00020-of-00035.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00020-of-00035.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00020-of-00035.safetensors", "model.layers.19.input_layernorm.bias": "model-00020-of-00035.safetensors", "model.layers.19.input_layernorm.weight": "model-00020-of-00035.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00021-of-00035.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00021-of-00035.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00021-of-00035.safetensors", "model.layers.19.post_attention_layernorm.bias": "model-00021-of-00035.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00021-of-00035.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00021-of-00035.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00021-of-00035.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00021-of-00035.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00021-of-00035.safetensors", "model.layers.20.input_layernorm.bias": "model-00021-of-00035.safetensors", "model.layers.20.input_layernorm.weight": "model-00021-of-00035.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00022-of-00035.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00022-of-00035.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00022-of-00035.safetensors", "model.layers.20.post_attention_layernorm.bias": "model-00022-of-00035.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00022-of-00035.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00022-of-00035.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00022-of-00035.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00022-of-00035.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00022-of-00035.safetensors", "model.layers.21.input_layernorm.bias": "model-00022-of-00035.safetensors", "model.layers.21.input_layernorm.weight": "model-00022-of-00035.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00023-of-00035.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00023-of-00035.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00023-of-00035.safetensors", "model.layers.21.post_attention_layernorm.bias": "model-00023-of-00035.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00023-of-00035.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00023-of-00035.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00023-of-00035.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00023-of-00035.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00023-of-00035.safetensors", "model.layers.22.input_layernorm.bias": "model-00023-of-00035.safetensors", "model.layers.22.input_layernorm.weight": "model-00023-of-00035.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00024-of-00035.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00024-of-00035.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00024-of-00035.safetensors", "model.layers.22.post_attention_layernorm.bias": "model-00024-of-00035.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00024-of-00035.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00024-of-00035.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00024-of-00035.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00024-of-00035.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00024-of-00035.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00025-of-00035.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00025-of-00035.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00025-of-00035.safetensors", "model.layers.23.input_layernorm.bias": "model-00025-of-00035.safetensors", "model.layers.23.input_layernorm.weight": "model-00025-of-00035.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00025-of-00035.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00025-of-00035.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00025-of-00035.safetensors", "model.layers.23.post_attention_layernorm.bias": "model-00025-of-00035.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00025-of-00035.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00025-of-00035.safetensors", "model.layers.24.input_layernorm.bias": "model-00025-of-00035.safetensors", "model.layers.24.input_layernorm.weight": "model-00025-of-00035.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00026-of-00035.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00026-of-00035.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00026-of-00035.safetensors", "model.layers.24.post_attention_layernorm.bias": "model-00026-of-00035.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00026-of-00035.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00026-of-00035.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00026-of-00035.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00026-of-00035.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00026-of-00035.safetensors", "model.layers.25.input_layernorm.bias": "model-00026-of-00035.safetensors", "model.layers.25.input_layernorm.weight": "model-00026-of-00035.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00027-of-00035.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00027-of-00035.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00027-of-00035.safetensors", "model.layers.25.post_attention_layernorm.bias": "model-00027-of-00035.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00027-of-00035.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00027-of-00035.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00027-of-00035.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00027-of-00035.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00027-of-00035.safetensors", "model.layers.26.input_layernorm.bias": "model-00027-of-00035.safetensors", "model.layers.26.input_layernorm.weight": "model-00027-of-00035.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00028-of-00035.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00028-of-00035.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00028-of-00035.safetensors", "model.layers.26.post_attention_layernorm.bias": "model-00028-of-00035.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00028-of-00035.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00028-of-00035.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00028-of-00035.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00028-of-00035.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00028-of-00035.safetensors", "model.layers.27.input_layernorm.bias": "model-00028-of-00035.safetensors", "model.layers.27.input_layernorm.weight": "model-00028-of-00035.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00029-of-00035.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00029-of-00035.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00029-of-00035.safetensors", "model.layers.27.post_attention_layernorm.bias": "model-00029-of-00035.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00029-of-00035.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00029-of-00035.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00029-of-00035.safetensors", "model.layers.28.input_layernorm.bias": "model-00029-of-00035.safetensors", "model.layers.28.input_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00030-of-00035.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00030-of-00035.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00030-of-00035.safetensors", "model.layers.28.post_attention_layernorm.bias": "model-00030-of-00035.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00030-of-00035.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00030-of-00035.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00030-of-00035.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00030-of-00035.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00031-of-00035.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00031-of-00035.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00031-of-00035.safetensors", "lm_head.weight": "model-00032-of-00035.safetensors", "model.layers.29.input_layernorm.bias": "model-00033-of-00035.safetensors", "model.layers.29.input_layernorm.weight": "model-00033-of-00035.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00033-of-00035.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00033-of-00035.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00033-of-00035.safetensors", "model.layers.29.post_attention_layernorm.bias": "model-00033-of-00035.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00033-of-00035.safetensors", "model.layers.30.input_layernorm.bias": "model-00033-of-00035.safetensors", "model.layers.30.input_layernorm.weight": "model-00033-of-00035.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00033-of-00035.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00034-of-00035.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00034-of-00035.safetensors", "model.layers.30.post_attention_layernorm.bias": "model-00034-of-00035.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00034-of-00035.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00034-of-00035.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00034-of-00035.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00034-of-00035.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00034-of-00035.safetensors", "model.layers.31.input_layernorm.bias": "model-00034-of-00035.safetensors", "model.layers.31.input_layernorm.weight": "model-00034-of-00035.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00034-of-00035.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00035-of-00035.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00035-of-00035.safetensors", "model.layers.31.post_attention_layernorm.bias": "model-00035-of-00035.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00035-of-00035.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00035-of-00035.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00035-of-00035.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00035-of-00035.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00035-of-00035.safetensors", "model.norm.bias": "model-00035-of-00035.safetensors", "model.norm.weight": "model-00035-of-00035.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,211 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}