failspy commited on
Commit
b13d7ec
1 Parent(s): a3836ba

Upload ortho'd Phi

Browse files
added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 32000,
3
+ "<|assistant|>": 32001,
4
+ "<|placeholder1|>": 32002,
5
+ "<|placeholder2|>": 32003,
6
+ "<|placeholder3|>": 32004,
7
+ "<|placeholder4|>": 32005,
8
+ "<|system|>": 32006,
9
+ "<|end|>": 32007,
10
+ "<|placeholder5|>": 32008,
11
+ "<|placeholder6|>": 32009,
12
+ "<|user|>": 32010
13
+ }
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
3
+ "architectures": [
4
+ "Phi3ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
9
+ "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "embd_pdrop": 0.0,
13
+ "eos_token_id": 32000,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 3072,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 8192,
18
+ "max_position_embeddings": 4096,
19
+ "model_type": "phi3",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "num_key_value_heads": 32,
23
+ "original_max_position_embeddings": 4096,
24
+ "pad_token_id": 32000,
25
+ "resid_pdrop": 0.0,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": null,
28
+ "rope_theta": 10000.0,
29
+ "sliding_window": 2047,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.41.0.dev0",
33
+ "use_cache": true,
34
+ "vocab_size": 32064
35
+ }
configuration_phi3.py ADDED
@@ -0,0 +1,213 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # coding=utf-8
2
+ # Copyright 2024 Microsoft and the HuggingFace Inc. team. All rights reserved.
3
+ #
4
+ # Licensed under the Apache License, Version 2.0 (the "License");
5
+ # you may not use this file except in compliance with the License.
6
+ # You may obtain a copy of the License at
7
+ #
8
+ # http://www.apache.org/licenses/LICENSE-2.0
9
+ #
10
+ # Unless required by applicable law or agreed to in writing, software
11
+ # distributed under the License is distributed on an "AS IS" BASIS,
12
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13
+ # See the License for the specific language governing permissions and
14
+ # limitations under the License.
15
+
16
+ """ Phi-3 model configuration"""
17
+
18
+
19
+ from transformers.configuration_utils import PretrainedConfig
20
+ from transformers.utils import logging
21
+
22
+
23
+ logger = logging.get_logger(__name__)
24
+
25
+ PHI3_PRETRAINED_CONFIG_ARCHIVE_MAP = {
26
+ "microsoft/Phi-3-mini-4k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/resolve/main/config.json",
27
+ "microsoft/Phi-3-mini-128k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/config.json",
28
+ }
29
+
30
+
31
+ class Phi3Config(PretrainedConfig):
32
+ r"""
33
+ This is the configuration class to store the configuration of a [`Phi3Model`]. It is used to instantiate a Phi-3
34
+ model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
35
+ defaults will yield a similar configuration to that of the
36
+ [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
37
+
38
+ Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
39
+ documentation from [`PretrainedConfig`] for more information.
40
+
41
+ Args:
42
+ vocab_size (`int`, *optional*, defaults to 32064):
43
+ Vocabulary size of the Phi-3 model. Defines the number of different tokens that can be represented by the
44
+ `inputs_ids` passed when calling [`Phi3Model`].
45
+ hidden_size (`int`, *optional*, defaults to 3072):
46
+ Dimension of the hidden representations.
47
+ intermediate_size (`int`, *optional*, defaults to 8192):
48
+ Dimension of the MLP representations.
49
+ num_hidden_layers (`int`, *optional*, defaults to 32):
50
+ Number of hidden layers in the Transformer decoder.
51
+ num_attention_heads (`int`, *optional*, defaults to 32):
52
+ Number of attention heads for each attention layer in the Transformer decoder.
53
+ num_key_value_heads (`int`, *optional*):
54
+ This is the number of key_value heads that should be used to implement Grouped Query Attention. If
55
+ `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
56
+ `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
57
+ converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
58
+ by meanpooling all the original heads within that group. For more details checkout [this
59
+ paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
60
+ `num_attention_heads`.
61
+ resid_pdrop (`float`, *optional*, defaults to 0.0):
62
+ Dropout probability for mlp outputs.
63
+ embd_pdrop (`int`, *optional*, defaults to 0.0):
64
+ The dropout ratio for the embeddings.
65
+ attention_dropout (`float`, *optional*, defaults to 0.0):
66
+ The dropout ratio after computing the attention scores.
67
+ hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
68
+ The non-linear activation function (function or string) in the decoder.
69
+ max_position_embeddings (`int`, *optional*, defaults to 4096):
70
+ The maximum sequence length that this model might ever be used with.
71
+ original_max_position_embeddings (`int`, *optional*, defaults to 4096):
72
+ The maximum sequence length that this model was trained with. This is used to determine the size of the
73
+ original RoPE embeddings when using long scaling.
74
+ initializer_range (`float`, *optional*, defaults to 0.02):
75
+ The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
76
+ rms_norm_eps (`float`, *optional*, defaults to 1e-05):
77
+ The epsilon value used for the RMSNorm.
78
+ use_cache (`bool`, *optional*, defaults to `True`):
79
+ Whether or not the model should return the last key/values attentions (not used by all models). Only
80
+ relevant if `config.is_decoder=True`. Whether to tie weight embeddings or not.
81
+ tie_word_embeddings (`bool`, *optional*, defaults to `False`):
82
+ Whether to tie weight embeddings
83
+ rope_theta (`float`, *optional*, defaults to 10000.0):
84
+ The base period of the RoPE embeddings.
85
+ rope_scaling (`dict`, *optional*):
86
+ The scaling strategy for the RoPE embeddings. If `None`, no scaling is applied. If a dictionary, it must
87
+ contain the following keys: `type`, `short_factor` and `long_factor`. The `type` must be either `su` or `yarn` and
88
+ the `short_factor` and `long_factor` must be lists of numbers with the same length as the hidden size
89
+ divided by the number of attention heads divided by 2.
90
+ bos_token_id (`int`, *optional*, defaults to 1):
91
+ The id of the "beginning-of-sequence" token.
92
+ eos_token_id (`int`, *optional*, defaults to 32000):
93
+ The id of the "end-of-sequence" token.
94
+ pad_token_id (`int`, *optional*, defaults to 32000):
95
+ The id of the padding token.
96
+ sliding_window (`int`, *optional*):
97
+ Sliding window attention window size. If `None`, no sliding window is applied.
98
+
99
+ Example:
100
+
101
+ ```python
102
+ >>> from transformers import Phi3Model, Phi3Config
103
+
104
+ >>> # Initializing a Phi-3 style configuration
105
+ >>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
106
+
107
+ >>> # Initializing a model from the configuration
108
+ >>> model = Phi3Model(configuration)
109
+
110
+ >>> # Accessing the model configuration
111
+ >>> configuration = model.config
112
+ ```"""
113
+
114
+ model_type = "phi3"
115
+ keys_to_ignore_at_inference = ["past_key_values"]
116
+
117
+ def __init__(
118
+ self,
119
+ vocab_size=32064,
120
+ hidden_size=3072,
121
+ intermediate_size=8192,
122
+ num_hidden_layers=32,
123
+ num_attention_heads=32,
124
+ num_key_value_heads=None,
125
+ resid_pdrop=0.0,
126
+ embd_pdrop=0.0,
127
+ attention_dropout=0.0,
128
+ hidden_act="silu",
129
+ max_position_embeddings=4096,
130
+ original_max_position_embeddings=4096,
131
+ initializer_range=0.02,
132
+ rms_norm_eps=1e-5,
133
+ use_cache=True,
134
+ tie_word_embeddings=False,
135
+ rope_theta=10000.0,
136
+ rope_scaling=None,
137
+ bos_token_id=1,
138
+ eos_token_id=32000,
139
+ pad_token_id=32000,
140
+ sliding_window=None,
141
+ **kwargs,
142
+ ):
143
+ self.vocab_size = vocab_size
144
+ self.hidden_size = hidden_size
145
+ self.intermediate_size = intermediate_size
146
+ self.num_hidden_layers = num_hidden_layers
147
+ self.num_attention_heads = num_attention_heads
148
+
149
+ if num_key_value_heads is None:
150
+ num_key_value_heads = num_attention_heads
151
+
152
+ self.num_key_value_heads = num_key_value_heads
153
+ self.resid_pdrop = resid_pdrop
154
+ self.embd_pdrop = embd_pdrop
155
+ self.attention_dropout = attention_dropout
156
+ self.hidden_act = hidden_act
157
+ self.max_position_embeddings = max_position_embeddings
158
+ self.original_max_position_embeddings = original_max_position_embeddings
159
+ self.initializer_range = initializer_range
160
+ self.rms_norm_eps = rms_norm_eps
161
+ self.use_cache = use_cache
162
+ self.rope_theta = rope_theta
163
+ self.rope_scaling = rope_scaling
164
+ self._rope_scaling_validation()
165
+ self.sliding_window = sliding_window
166
+
167
+ super().__init__(
168
+ bos_token_id=bos_token_id,
169
+ eos_token_id=eos_token_id,
170
+ pad_token_id=pad_token_id,
171
+ tie_word_embeddings=tie_word_embeddings,
172
+ **kwargs,
173
+ )
174
+
175
+ def _rope_scaling_validation(self):
176
+ """
177
+ Validate the `rope_scaling` configuration.
178
+ """
179
+ if self.rope_scaling is None:
180
+ return
181
+
182
+ if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 3:
183
+ raise ValueError(
184
+ "`rope_scaling` must be a dictionary with three fields, `type`, `short_factor` and `long_factor`, "
185
+ f"got {self.rope_scaling}"
186
+ )
187
+ rope_scaling_type = self.rope_scaling.get("type", None)
188
+ rope_scaling_short_factor = self.rope_scaling.get("short_factor", None)
189
+ rope_scaling_long_factor = self.rope_scaling.get("long_factor", None)
190
+ if rope_scaling_type is None or rope_scaling_type not in ["su", "yarn"]:
191
+ raise ValueError(f"`rope_scaling`'s type field must be one of ['su', 'yarn'], got {rope_scaling_type}")
192
+ if not (
193
+ isinstance(rope_scaling_short_factor, list)
194
+ and all(isinstance(x, (int, float)) for x in rope_scaling_short_factor)
195
+ ):
196
+ raise ValueError(
197
+ f"`rope_scaling`'s short_factor field must be a list of numbers, got {rope_scaling_short_factor}"
198
+ )
199
+ if not len(rope_scaling_short_factor) == self.hidden_size // self.num_attention_heads // 2:
200
+ raise ValueError(
201
+ f"`rope_scaling`'s short_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_short_factor)}"
202
+ )
203
+ if not (
204
+ isinstance(rope_scaling_long_factor, list)
205
+ and all(isinstance(x, (int, float)) for x in rope_scaling_long_factor)
206
+ ):
207
+ raise ValueError(
208
+ f"`rope_scaling`'s long_factor field must be a list of numbers, got {rope_scaling_long_factor}"
209
+ )
210
+ if not len(rope_scaling_long_factor) == self.hidden_size // self.num_attention_heads // 2:
211
+ raise ValueError(
212
+ f"`rope_scaling`'s long_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_long_factor)}"
213
+ )
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 32000,
6
+ 32001,
7
+ 32007
8
+ ],
9
+ "pad_token_id": 32000,
10
+ "transformers_version": "4.41.0.dev0"
11
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86c52da420f73169fb6d974a23ef0f4b9d489fbc85d22dc4f9204cb2d17e8834
3
+ size 4961852416
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25878acd2850f35e6839227796f13793689aa923b8ef17a9ad3f4de301ab7f43
3
+ size 4983111176
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2421baf321eaeb2f709525b318ef5e03cdb71c959e2d3f9c328c4225471090e6
3
+ size 4945374704
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2412b079b73f0641c7a315e7a558be3affcb81a936d5cd251f81ebfa110d7a44
3
+ size 394002560
model.safetensors.index.json ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15284318208
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
21
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
22
+ "model.layers.10.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
23
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
24
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.10.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
26
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.11.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.12.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.13.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.14.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.14.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.15.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.15.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.16.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.16.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.17.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.17.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.18.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.18.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.19.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.19.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
81
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
82
+ "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
83
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
84
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
85
+ "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
86
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.20.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
93
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
94
+ "model.layers.21.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
95
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
96
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.21.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
98
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
99
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
100
+ "model.layers.22.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
101
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
102
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
103
+ "model.layers.22.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
104
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
105
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
106
+ "model.layers.23.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
107
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
109
+ "model.layers.23.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
110
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
111
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
112
+ "model.layers.24.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
113
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
114
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
115
+ "model.layers.24.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
116
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
117
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
118
+ "model.layers.25.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
119
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
120
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
121
+ "model.layers.25.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
122
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
123
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
124
+ "model.layers.26.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
125
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.26.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.27.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.27.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.28.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.28.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.29.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.29.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
147
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
148
+ "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
149
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
150
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
151
+ "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
152
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.30.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.30.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.31.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.31.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
165
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
166
+ "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
167
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
168
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
169
+ "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
170
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
171
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
172
+ "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
173
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
174
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
175
+ "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
176
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
177
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
178
+ "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
179
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
180
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
181
+ "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
182
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
183
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
184
+ "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
185
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
186
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
187
+ "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
188
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
189
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
190
+ "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
191
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
192
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
193
+ "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
194
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
195
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
196
+ "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
197
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
198
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
199
+ "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
200
+ "model.norm.weight": "model-00003-of-00004.safetensors"
201
+ }
202
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": true,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "32000": {
30
+ "content": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|assistant|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": true,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<|placeholder1|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": true,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<|placeholder2|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": true,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<|placeholder3|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": true,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "32005": {
70
+ "content": "<|placeholder4|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": true,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "32006": {
78
+ "content": "<|system|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": true,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "32007": {
86
+ "content": "<|end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": true,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "32008": {
94
+ "content": "<|placeholder5|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": true,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "32009": {
102
+ "content": "<|placeholder6|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": true,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "32010": {
110
+ "content": "<|user|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": true,
114
+ "single_word": false,
115
+ "special": true
116
+ }
117
+ },
118
+ "bos_token": "<s>",
119
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
120
+ "clean_up_tokenization_spaces": false,
121
+ "eos_token": "<|endoftext|>",
122
+ "legacy": false,
123
+ "model_max_length": 4096,
124
+ "pad_token": "<|endoftext|>",
125
+ "padding_side": "left",
126
+ "sp_model_kwargs": {},
127
+ "tokenizer_class": "LlamaTokenizer",
128
+ "unk_token": "<unk>",
129
+ "use_default_system_prompt": false
130
+ }