Upload folder using huggingface_hub
Browse files- added_tokens.json +13 -0
- config.json +171 -0
- configuration_phi3.py +213 -0
- generation_config.json +11 -0
- openvino_config.json +22 -0
- openvino_model.bin +3 -0
- openvino_model.xml +0 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +130 -0
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 +1,171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/media/data8/hf_models/microsoft_Phi-3-medium-128k-instruct/",
|
3 |
+
"architectures": [
|
4 |
+
"Phi3ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoConfig": "configuration_phi3.Phi3Config",
|
10 |
+
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
11 |
+
},
|
12 |
+
"bos_token_id": 1,
|
13 |
+
"embd_pdrop": 0.0,
|
14 |
+
"eos_token_id": 32000,
|
15 |
+
"hidden_act": "silu",
|
16 |
+
"hidden_size": 5120,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 17920,
|
19 |
+
"is_decoder": true,
|
20 |
+
"max_position_embeddings": 131072,
|
21 |
+
"model_type": "phi3",
|
22 |
+
"num_attention_heads": 40,
|
23 |
+
"num_hidden_layers": 40,
|
24 |
+
"num_key_value_heads": 10,
|
25 |
+
"original_max_position_embeddings": 4096,
|
26 |
+
"pad_token_id": null,
|
27 |
+
"resid_pdrop": 0.0,
|
28 |
+
"rms_norm_eps": 1e-05,
|
29 |
+
"rope_scaling": {
|
30 |
+
"long_factor": [
|
31 |
+
1.0,
|
32 |
+
1.0,
|
33 |
+
1.0,
|
34 |
+
1.0,
|
35 |
+
1.0,
|
36 |
+
1.0,
|
37 |
+
1.0,
|
38 |
+
1.0,
|
39 |
+
1.0,
|
40 |
+
1.0,
|
41 |
+
1.0,
|
42 |
+
1.0,
|
43 |
+
1.0,
|
44 |
+
1.25,
|
45 |
+
1.25,
|
46 |
+
1.5,
|
47 |
+
2.0,
|
48 |
+
2.75,
|
49 |
+
5.75,
|
50 |
+
5.75,
|
51 |
+
6.5,
|
52 |
+
9.25,
|
53 |
+
11.0,
|
54 |
+
13.25,
|
55 |
+
19.25,
|
56 |
+
19.75,
|
57 |
+
19.75,
|
58 |
+
21.25,
|
59 |
+
21.5,
|
60 |
+
26.5,
|
61 |
+
30.0,
|
62 |
+
33.75,
|
63 |
+
35.25,
|
64 |
+
38.5,
|
65 |
+
42.0,
|
66 |
+
42.25,
|
67 |
+
46.0,
|
68 |
+
47.0,
|
69 |
+
50.0,
|
70 |
+
50.5,
|
71 |
+
51.0,
|
72 |
+
52.0,
|
73 |
+
52.75,
|
74 |
+
53.75,
|
75 |
+
54.75,
|
76 |
+
57.0,
|
77 |
+
57.25,
|
78 |
+
58.5,
|
79 |
+
59.25,
|
80 |
+
59.5,
|
81 |
+
62.0,
|
82 |
+
62.5,
|
83 |
+
62.75,
|
84 |
+
63.25,
|
85 |
+
63.25,
|
86 |
+
63.25,
|
87 |
+
63.75,
|
88 |
+
64.0,
|
89 |
+
64.0,
|
90 |
+
64.25,
|
91 |
+
64.5,
|
92 |
+
64.5,
|
93 |
+
65.0,
|
94 |
+
65.0
|
95 |
+
],
|
96 |
+
"short_factor": [
|
97 |
+
1.0,
|
98 |
+
1.0,
|
99 |
+
1.0,
|
100 |
+
1.0,
|
101 |
+
1.0,
|
102 |
+
1.0,
|
103 |
+
1.01,
|
104 |
+
1.02,
|
105 |
+
1.02,
|
106 |
+
1.04,
|
107 |
+
1.04,
|
108 |
+
1.07,
|
109 |
+
1.07,
|
110 |
+
1.1,
|
111 |
+
1.3000000000000003,
|
112 |
+
1.3000000000000003,
|
113 |
+
1.5000000000000004,
|
114 |
+
1.5700000000000005,
|
115 |
+
1.9000000000000008,
|
116 |
+
2.3100000000000014,
|
117 |
+
2.759999999999992,
|
118 |
+
3.3899999999999784,
|
119 |
+
3.9399999999999666,
|
120 |
+
4.009999999999965,
|
121 |
+
4.289999999999959,
|
122 |
+
4.349999999999958,
|
123 |
+
5.349999999999937,
|
124 |
+
6.659999999999909,
|
125 |
+
7.029999999999901,
|
126 |
+
7.51999999999989,
|
127 |
+
8.00999999999988,
|
128 |
+
8.249999999999876,
|
129 |
+
8.279999999999875,
|
130 |
+
9.629999999999846,
|
131 |
+
9.89999999999984,
|
132 |
+
10.589999999999826,
|
133 |
+
11.049999999999816,
|
134 |
+
11.7899999999998,
|
135 |
+
12.189999999999792,
|
136 |
+
12.889999999999777,
|
137 |
+
13.129999999999772,
|
138 |
+
13.16999999999977,
|
139 |
+
13.20999999999977,
|
140 |
+
13.479999999999764,
|
141 |
+
13.539999999999763,
|
142 |
+
13.779999999999758,
|
143 |
+
13.929999999999755,
|
144 |
+
14.429999999999744,
|
145 |
+
14.759999999999737,
|
146 |
+
15.149999999999729,
|
147 |
+
15.419999999999723,
|
148 |
+
15.53999999999972,
|
149 |
+
15.659999999999718,
|
150 |
+
15.749999999999716,
|
151 |
+
15.759999999999716,
|
152 |
+
15.799999999999715,
|
153 |
+
16.05999999999971,
|
154 |
+
16.079999999999714,
|
155 |
+
16.11999999999972,
|
156 |
+
16.11999999999972,
|
157 |
+
16.18999999999973,
|
158 |
+
16.31999999999975,
|
159 |
+
16.539999999999786,
|
160 |
+
16.799999999999827
|
161 |
+
],
|
162 |
+
"type": "su"
|
163 |
+
},
|
164 |
+
"rope_theta": 10000.0,
|
165 |
+
"sliding_window": 131072,
|
166 |
+
"tie_word_embeddings": false,
|
167 |
+
"torch_dtype": "bfloat16",
|
168 |
+
"transformers_version": "4.43.4",
|
169 |
+
"use_cache": true,
|
170 |
+
"vocab_size": 32064
|
171 |
+
}
|
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": "4.43.4"
|
11 |
+
}
|
openvino_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"compression": null,
|
3 |
+
"dtype": "int4",
|
4 |
+
"input_info": null,
|
5 |
+
"optimum_version": "1.21.3",
|
6 |
+
"quantization_config": {
|
7 |
+
"all_layers": null,
|
8 |
+
"bits": 4,
|
9 |
+
"dataset": null,
|
10 |
+
"group_size": 128,
|
11 |
+
"ignored_scope": null,
|
12 |
+
"num_samples": null,
|
13 |
+
"quant_method": "default",
|
14 |
+
"ratio": 1.0,
|
15 |
+
"scale_estimation": null,
|
16 |
+
"sensitivity_metric": null,
|
17 |
+
"sym": true,
|
18 |
+
"tokenizer": null
|
19 |
+
},
|
20 |
+
"save_onnx_model": false,
|
21 |
+
"transformers_version": "4.43.4"
|
22 |
+
}
|
openvino_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd289e4b4b1a1d1fcd23a22cc11bc166794ef3e8d86bc55b834cfb8bfe0d7653
|
3 |
+
size 7358923276
|
openvino_model.xml
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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": false,
|
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": "{% 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": 131072,
|
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 |
+
}
|