Hugging Face's logo

Spaces:
abhisheksan
/
poetica
Running

App Files Community
poetica
File size: 40,787 Bytes 
09d9560
a96ed1b
 
 
 
2442c76
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f4f946e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
 
2024-11-16 23:21:31,464 - main - INFO - Loading tokenizer...
2024-11-16 23:21:32,228 - main - WARNING - Could not load custom vocabulary: property 'vocab' of 'GPT2TokenizerFast' object has no setter
2024-11-16 23:21:32,229 - main - INFO - Loading model...
2024-11-16 23:21:32,229 - main - ERROR - Model file not found at ./models\poeticagpt-quantized-new.pth
2024-11-16 23:21:32,231 - main - ERROR - Failed to initialize model manager
2024-11-16 23:30:46,037 - main - INFO - Loading tokenizer...
2024-11-16 23:30:46,798 - main - WARNING - Could not load custom vocabulary: property 'vocab' of 'GPT2TokenizerFast' object has no setter
2024-11-16 23:30:46,799 - main - INFO - Loading model...
2024-11-16 23:30:46,799 - main - ERROR - Error initializing model: Incorrect path_or_model_id: './models/poeticagpt.pth'. Please provide either the path to a local folder or the repo_id of a model on the Hub.
2024-11-16 23:30:46,800 - main - ERROR - Detailed traceback:
Traceback (most recent call last):
  File "e:\Self Work\My Projects\Poetica HuggingFace Server\.venv\Lib\site-packages\transformers\utils\hub.py", line 402, in cached_file
    resolved_file = hf_hub_download(
                    ^^^^^^^^^^^^^^^^
  File "e:\Self Work\My Projects\Poetica HuggingFace Server\.venv\Lib\site-packages\huggingface_hub\utils\_validators.py", line 106, in _inner_fn
    validate_repo_id(arg_value)
  File "e:\Self Work\My Projects\Poetica HuggingFace Server\.venv\Lib\site-packages\huggingface_hub\utils\_validators.py", line 154, in validate_repo_id
    raise HFValidationError(
huggingface_hub.errors.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': './models/poeticagpt.pth'. Use `repo_type` argument if needed.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "E:\Self Work\My Projects\Poetica HuggingFace Server\poetica\main.py", line 88, in initialize
    self.model = AutoModelForCausalLM.from_pretrained(model_path, local_files_only=True)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "e:\Self Work\My Projects\Poetica HuggingFace Server\.venv\Lib\site-packages\transformers\models\auto\auto_factory.py", line 485, in from_pretrained
    resolved_config_file = cached_file(
                           ^^^^^^^^^^^^
  File "e:\Self Work\My Projects\Poetica HuggingFace Server\.venv\Lib\site-packages\transformers\utils\hub.py", line 466, in cached_file
    raise EnvironmentError(
OSError: Incorrect path_or_model_id: './models/poeticagpt.pth'. Please provide either the path to a local folder or the repo_id of a model on the Hub.
2024-11-16 23:30:46,803 - main - ERROR - Failed to initialize model manager
2024-11-16 23:33:40,483 - main - INFO - Loading tokenizer...
2024-11-16 23:33:41,621 - main - WARNING - Could not load custom vocabulary: property 'vocab' of 'GPT2TokenizerFast' object has no setter
2024-11-16 23:33:41,622 - main - INFO - Loading model...
2024-11-16 23:33:43,332 - main - ERROR - Error initializing model: Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory ./models/.
2024-11-16 23:33:43,333 - main - ERROR - Detailed traceback:
Traceback (most recent call last):
  File "E:\Self Work\My Projects\Poetica HuggingFace Server\poetica\main.py", line 88, in initialize
    self.model = AutoModelForCausalLM.from_pretrained(model_path, local_files_only=True)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "e:\Self Work\My Projects\Poetica HuggingFace Server\.venv\Lib\site-packages\transformers\models\auto\auto_factory.py", line 564, in from_pretrained
    return model_class.from_pretrained(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "e:\Self Work\My Projects\Poetica HuggingFace Server\.venv\Lib\site-packages\transformers\modeling_utils.py", line 3447, in from_pretrained
    raise EnvironmentError(
OSError: Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory ./models/.
2024-11-16 23:33:43,335 - main - ERROR - Failed to initialize model manager
2024-11-16 23:34:18,283 - main - INFO - Loading tokenizer...
2024-11-16 23:34:18,966 - main - WARNING - Could not load custom vocabulary: property 'vocab' of 'GPT2TokenizerFast' object has no setter
2024-11-16 23:34:18,966 - main - INFO - Loading model...
2024-11-16 23:34:20,499 - main - ERROR - Error initializing model: Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory ./models/.
2024-11-16 23:34:20,500 - main - ERROR - Detailed traceback:
Traceback (most recent call last):
  File "E:\Self Work\My Projects\Poetica HuggingFace Server\poetica\main.py", line 88, in initialize
    self.model = AutoModelForCausalLM.from_pretrained(model_path, local_files_only=True)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "e:\Self Work\My Projects\Poetica HuggingFace Server\.venv\Lib\site-packages\transformers\models\auto\auto_factory.py", line 564, in from_pretrained
    return model_class.from_pretrained(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "e:\Self Work\My Projects\Poetica HuggingFace Server\.venv\Lib\site-packages\transformers\modeling_utils.py", line 3447, in from_pretrained
    raise EnvironmentError(
OSError: Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory ./models/.
2024-11-16 23:34:20,502 - main - ERROR - Failed to initialize model manager
2024-11-16 23:35:15,983 - main - INFO - Loading tokenizer...
2024-11-16 23:35:17,111 - main - WARNING - Could not load custom vocabulary: property 'vocab' of 'GPT2TokenizerFast' object has no setter
2024-11-16 23:35:17,111 - main - INFO - Loading model...
2024-11-16 23:35:18,795 - main - ERROR - Error initializing model: Unable to load weights from pytorch checkpoint file for './models/pytorch_model.bin' at './models/pytorch_model.bin'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.
2024-11-16 23:35:18,796 - main - ERROR - Detailed traceback:
Traceback (most recent call last):
  File "e:\Self Work\My Projects\Poetica HuggingFace Server\.venv\Lib\site-packages\transformers\modeling_utils.py", line 575, in load_state_dict
    return torch.load(
           ^^^^^^^^^^^
  File "e:\Self Work\My Projects\Poetica HuggingFace Server\.venv\Lib\site-packages\torch\serialization.py", line 1024, in load
    raise pickle.UnpicklingError(UNSAFE_MESSAGE + str(e)) from None
_pickle.UnpicklingError: Weights only load failed. Re-running `torch.load` with `weights_only` set to `False` will likely succeed, but it can result in arbitrary code execution.Do it only if you get the file from a trusted source. WeightsUnpickler error: Unsupported class torch.qint8

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "e:\Self Work\My Projects\Poetica HuggingFace Server\.venv\Lib\site-packages\transformers\modeling_utils.py", line 584, in load_state_dict
    if f.read(7) == "version":
       ^^^^^^^^^
  File "D:\Program Files\Python\Lib\encodings\cp1252.py", line 23, in decode
    return codecs.charmap_decode(input,self.errors,decoding_table)[0]
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
UnicodeDecodeError: 'charmap' codec can't decode byte 0x81 in position 1651: character maps to <undefined>

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "E:\Self Work\My Projects\Poetica HuggingFace Server\poetica\main.py", line 88, in initialize
    self.model = AutoModelForCausalLM.from_pretrained(model_path, local_files_only=True)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "e:\Self Work\My Projects\Poetica HuggingFace Server\.venv\Lib\site-packages\transformers\models\auto\auto_factory.py", line 564, in from_pretrained
    return model_class.from_pretrained(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "e:\Self Work\My Projects\Poetica HuggingFace Server\.venv\Lib\site-packages\transformers\modeling_utils.py", line 3703, in from_pretrained
    state_dict = load_state_dict(resolved_archive_file)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "e:\Self Work\My Projects\Poetica HuggingFace Server\.venv\Lib\site-packages\transformers\modeling_utils.py", line 596, in load_state_dict
    raise OSError(
OSError: Unable to load weights from pytorch checkpoint file for './models/pytorch_model.bin' at './models/pytorch_model.bin'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.
2024-11-16 23:35:18,815 - main - ERROR - Failed to initialize model manager
2024-11-16 23:37:05,649 - main - INFO - Loading tokenizer...
2024-11-16 23:37:06,372 - main - INFO - Loading model...
2024-11-16 23:40:15,280 - main - ERROR - Error initializing model: Error(s) in loading state_dict for GPT2LMHeadModel:
	Missing key(s) in state_dict: "transformer.h.6.ln_1.weight", "transformer.h.6.ln_1.bias", "transformer.h.6.attn.c_attn.weight", "transformer.h.6.attn.c_attn.bias", "transformer.h.6.attn.c_proj.weight", "transformer.h.6.attn.c_proj.bias", "transformer.h.6.ln_2.weight", "transformer.h.6.ln_2.bias", "transformer.h.6.mlp.c_fc.weight", "transformer.h.6.mlp.c_fc.bias", "transformer.h.6.mlp.c_proj.weight", "transformer.h.6.mlp.c_proj.bias", "transformer.h.7.ln_1.weight", "transformer.h.7.ln_1.bias", "transformer.h.7.attn.c_attn.weight", "transformer.h.7.attn.c_attn.bias", "transformer.h.7.attn.c_proj.weight", "transformer.h.7.attn.c_proj.bias", "transformer.h.7.ln_2.weight", "transformer.h.7.ln_2.bias", "transformer.h.7.mlp.c_fc.weight", "transformer.h.7.mlp.c_fc.bias", "transformer.h.7.mlp.c_proj.weight", "transformer.h.7.mlp.c_proj.bias", "transformer.h.8.ln_1.weight", "transformer.h.8.ln_1.bias", "transformer.h.8.attn.c_attn.weight", "transformer.h.8.attn.c_attn.bias", "transformer.h.8.attn.c_proj.weight", "transformer.h.8.attn.c_proj.bias", "transformer.h.8.ln_2.weight", "transformer.h.8.ln_2.bias", "transformer.h.8.mlp.c_fc.weight", "transformer.h.8.mlp.c_fc.bias", "transformer.h.8.mlp.c_proj.weight", "transformer.h.8.mlp.c_proj.bias", "transformer.h.9.ln_1.weight", "transformer.h.9.ln_1.bias", "transformer.h.9.attn.c_attn.weight", "transformer.h.9.attn.c_attn.bias", "transformer.h.9.attn.c_proj.weight", "transformer.h.9.attn.c_proj.bias", "transformer.h.9.ln_2.weight", "transformer.h.9.ln_2.bias", "transformer.h.9.mlp.c_fc.weight", "transformer.h.9.mlp.c_fc.bias", "transformer.h.9.mlp.c_proj.weight", "transformer.h.9.mlp.c_proj.bias", "transformer.h.10.ln_1.weight", "transformer.h.10.ln_1.bias", "transformer.h.10.attn.c_attn.weight", "transformer.h.10.attn.c_attn.bias", "transformer.h.10.attn.c_proj.weight", "transformer.h.10.attn.c_proj.bias", "transformer.h.10.ln_2.weight", "transformer.h.10.ln_2.bias", "transformer.h.10.mlp.c_fc.weight", "transformer.h.10.mlp.c_fc.bias", "transformer.h.10.mlp.c_proj.weight", "transformer.h.10.mlp.c_proj.bias", "transformer.h.11.ln_1.weight", "transformer.h.11.ln_1.bias", "transformer.h.11.attn.c_attn.weight", "transformer.h.11.attn.c_attn.bias", "transformer.h.11.attn.c_proj.weight", "transformer.h.11.attn.c_proj.bias", "transformer.h.11.ln_2.weight", "transformer.h.11.ln_2.bias", "transformer.h.11.mlp.c_fc.weight", "transformer.h.11.mlp.c_fc.bias", "transformer.h.11.mlp.c_proj.weight", "transformer.h.11.mlp.c_proj.bias", "lm_head.weight". 
	Unexpected key(s) in state_dict: "lm_head.scale", "lm_head.zero_point", "lm_head._packed_params.dtype", "lm_head._packed_params._packed_params". 
	size mismatch for transformer.wte.weight: copying a param with shape torch.Size([50257, 384]) from checkpoint, the shape in current model is torch.Size([50257, 768]).
	size mismatch for transformer.wpe.weight: copying a param with shape torch.Size([128, 384]) from checkpoint, the shape in current model is torch.Size([1024, 768]).
	size mismatch for transformer.h.0.ln_1.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.0.ln_1.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.0.attn.c_attn.weight: copying a param with shape torch.Size([384, 1152]) from checkpoint, the shape in current model is torch.Size([768, 2304]).
	size mismatch for transformer.h.0.attn.c_attn.bias: copying a param with shape torch.Size([1152]) from checkpoint, the shape in current model is torch.Size([2304]).
	size mismatch for transformer.h.0.attn.c_proj.weight: copying a param with shape torch.Size([384, 384]) from checkpoint, the shape in current model is torch.Size([768, 768]).
	size mismatch for transformer.h.0.attn.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.0.ln_2.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.0.ln_2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.0.mlp.c_fc.weight: copying a param with shape torch.Size([384, 1536]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
	size mismatch for transformer.h.0.mlp.c_fc.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([3072]).
	size mismatch for transformer.h.0.mlp.c_proj.weight: copying a param with shape torch.Size([1536, 384]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
	size mismatch for transformer.h.0.mlp.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.1.ln_1.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.1.ln_1.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.1.attn.c_attn.weight: copying a param with shape torch.Size([384, 1152]) from checkpoint, the shape in current model is torch.Size([768, 2304]).
	size mismatch for transformer.h.1.attn.c_attn.bias: copying a param with shape torch.Size([1152]) from checkpoint, the shape in current model is torch.Size([2304]).
	size mismatch for transformer.h.1.attn.c_proj.weight: copying a param with shape torch.Size([384, 384]) from checkpoint, the shape in current model is torch.Size([768, 768]).
	size mismatch for transformer.h.1.attn.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.1.ln_2.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.1.ln_2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.1.mlp.c_fc.weight: copying a param with shape torch.Size([384, 1536]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
	size mismatch for transformer.h.1.mlp.c_fc.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([3072]).
	size mismatch for transformer.h.1.mlp.c_proj.weight: copying a param with shape torch.Size([1536, 384]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
	size mismatch for transformer.h.1.mlp.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.2.ln_1.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.2.ln_1.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.2.attn.c_attn.weight: copying a param with shape torch.Size([384, 1152]) from checkpoint, the shape in current model is torch.Size([768, 2304]).
	size mismatch for transformer.h.2.attn.c_attn.bias: copying a param with shape torch.Size([1152]) from checkpoint, the shape in current model is torch.Size([2304]).
	size mismatch for transformer.h.2.attn.c_proj.weight: copying a param with shape torch.Size([384, 384]) from checkpoint, the shape in current model is torch.Size([768, 768]).
	size mismatch for transformer.h.2.attn.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.2.ln_2.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.2.ln_2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.2.mlp.c_fc.weight: copying a param with shape torch.Size([384, 1536]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
	size mismatch for transformer.h.2.mlp.c_fc.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([3072]).
	size mismatch for transformer.h.2.mlp.c_proj.weight: copying a param with shape torch.Size([1536, 384]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
	size mismatch for transformer.h.2.mlp.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.3.ln_1.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.3.ln_1.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.3.attn.c_attn.weight: copying a param with shape torch.Size([384, 1152]) from checkpoint, the shape in current model is torch.Size([768, 2304]).
	size mismatch for transformer.h.3.attn.c_attn.bias: copying a param with shape torch.Size([1152]) from checkpoint, the shape in current model is torch.Size([2304]).
	size mismatch for transformer.h.3.attn.c_proj.weight: copying a param with shape torch.Size([384, 384]) from checkpoint, the shape in current model is torch.Size([768, 768]).
	size mismatch for transformer.h.3.attn.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.3.ln_2.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.3.ln_2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.3.mlp.c_fc.weight: copying a param with shape torch.Size([384, 1536]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
	size mismatch for transformer.h.3.mlp.c_fc.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([3072]).
	size mismatch for transformer.h.3.mlp.c_proj.weight: copying a param with shape torch.Size([1536, 384]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
	size mismatch for transformer.h.3.mlp.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.4.ln_1.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.4.ln_1.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.4.attn.c_attn.weight: copying a param with shape torch.Size([384, 1152]) from checkpoint, the shape in current model is torch.Size([768, 2304]).
	size mismatch for transformer.h.4.attn.c_attn.bias: copying a param with shape torch.Size([1152]) from checkpoint, the shape in current model is torch.Size([2304]).
	size mismatch for transformer.h.4.attn.c_proj.weight: copying a param with shape torch.Size([384, 384]) from checkpoint, the shape in current model is torch.Size([768, 768]).
	size mismatch for transformer.h.4.attn.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.4.ln_2.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.4.ln_2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.4.mlp.c_fc.weight: copying a param with shape torch.Size([384, 1536]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
	size mismatch for transformer.h.4.mlp.c_fc.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([3072]).
	size mismatch for transformer.h.4.mlp.c_proj.weight: copying a param with shape torch.Size([1536, 384]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
	size mismatch for transformer.h.4.mlp.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.5.ln_1.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.5.ln_1.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.5.attn.c_attn.weight: copying a param with shape torch.Size([384, 1152]) from checkpoint, the shape in current model is torch.Size([768, 2304]).
	size mismatch for transformer.h.5.attn.c_attn.bias: copying a param with shape torch.Size([1152]) from checkpoint, the shape in current model is torch.Size([2304]).
	size mismatch for transformer.h.5.attn.c_proj.weight: copying a param with shape torch.Size([384, 384]) from checkpoint, the shape in current model is torch.Size([768, 768]).
	size mismatch for transformer.h.5.attn.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.5.ln_2.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.5.ln_2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.5.mlp.c_fc.weight: copying a param with shape torch.Size([384, 1536]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
	size mismatch for transformer.h.5.mlp.c_fc.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([3072]).
	size mismatch for transformer.h.5.mlp.c_proj.weight: copying a param with shape torch.Size([1536, 384]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
	size mismatch for transformer.h.5.mlp.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.ln_f.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.ln_f.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
2024-11-16 23:40:15,283 - main - ERROR - Detailed traceback:
Traceback (most recent call last):
  File "E:\Self Work\My Projects\Poetica HuggingFace Server\poetica\main.py", line 74, in initialize
    self.model.load_state_dict(state_dict)
  File "e:\Self Work\My Projects\Poetica HuggingFace Server\.venv\Lib\site-packages\torch\nn\modules\module.py", line 2189, in load_state_dict
    raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for GPT2LMHeadModel:
	Missing key(s) in state_dict: "transformer.h.6.ln_1.weight", "transformer.h.6.ln_1.bias", "transformer.h.6.attn.c_attn.weight", "transformer.h.6.attn.c_attn.bias", "transformer.h.6.attn.c_proj.weight", "transformer.h.6.attn.c_proj.bias", "transformer.h.6.ln_2.weight", "transformer.h.6.ln_2.bias", "transformer.h.6.mlp.c_fc.weight", "transformer.h.6.mlp.c_fc.bias", "transformer.h.6.mlp.c_proj.weight", "transformer.h.6.mlp.c_proj.bias", "transformer.h.7.ln_1.weight", "transformer.h.7.ln_1.bias", "transformer.h.7.attn.c_attn.weight", "transformer.h.7.attn.c_attn.bias", "transformer.h.7.attn.c_proj.weight", "transformer.h.7.attn.c_proj.bias", "transformer.h.7.ln_2.weight", "transformer.h.7.ln_2.bias", "transformer.h.7.mlp.c_fc.weight", "transformer.h.7.mlp.c_fc.bias", "transformer.h.7.mlp.c_proj.weight", "transformer.h.7.mlp.c_proj.bias", "transformer.h.8.ln_1.weight", "transformer.h.8.ln_1.bias", "transformer.h.8.attn.c_attn.weight", "transformer.h.8.attn.c_attn.bias", "transformer.h.8.attn.c_proj.weight", "transformer.h.8.attn.c_proj.bias", "transformer.h.8.ln_2.weight", "transformer.h.8.ln_2.bias", "transformer.h.8.mlp.c_fc.weight", "transformer.h.8.mlp.c_fc.bias", "transformer.h.8.mlp.c_proj.weight", "transformer.h.8.mlp.c_proj.bias", "transformer.h.9.ln_1.weight", "transformer.h.9.ln_1.bias", "transformer.h.9.attn.c_attn.weight", "transformer.h.9.attn.c_attn.bias", "transformer.h.9.attn.c_proj.weight", "transformer.h.9.attn.c_proj.bias", "transformer.h.9.ln_2.weight", "transformer.h.9.ln_2.bias", "transformer.h.9.mlp.c_fc.weight", "transformer.h.9.mlp.c_fc.bias", "transformer.h.9.mlp.c_proj.weight", "transformer.h.9.mlp.c_proj.bias", "transformer.h.10.ln_1.weight", "transformer.h.10.ln_1.bias", "transformer.h.10.attn.c_attn.weight", "transformer.h.10.attn.c_attn.bias", "transformer.h.10.attn.c_proj.weight", "transformer.h.10.attn.c_proj.bias", "transformer.h.10.ln_2.weight", "transformer.h.10.ln_2.bias", "transformer.h.10.mlp.c_fc.weight", "transformer.h.10.mlp.c_fc.bias", "transformer.h.10.mlp.c_proj.weight", "transformer.h.10.mlp.c_proj.bias", "transformer.h.11.ln_1.weight", "transformer.h.11.ln_1.bias", "transformer.h.11.attn.c_attn.weight", "transformer.h.11.attn.c_attn.bias", "transformer.h.11.attn.c_proj.weight", "transformer.h.11.attn.c_proj.bias", "transformer.h.11.ln_2.weight", "transformer.h.11.ln_2.bias", "transformer.h.11.mlp.c_fc.weight", "transformer.h.11.mlp.c_fc.bias", "transformer.h.11.mlp.c_proj.weight", "transformer.h.11.mlp.c_proj.bias", "lm_head.weight". 
	Unexpected key(s) in state_dict: "lm_head.scale", "lm_head.zero_point", "lm_head._packed_params.dtype", "lm_head._packed_params._packed_params". 
	size mismatch for transformer.wte.weight: copying a param with shape torch.Size([50257, 384]) from checkpoint, the shape in current model is torch.Size([50257, 768]).
	size mismatch for transformer.wpe.weight: copying a param with shape torch.Size([128, 384]) from checkpoint, the shape in current model is torch.Size([1024, 768]).
	size mismatch for transformer.h.0.ln_1.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.0.ln_1.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.0.attn.c_attn.weight: copying a param with shape torch.Size([384, 1152]) from checkpoint, the shape in current model is torch.Size([768, 2304]).
	size mismatch for transformer.h.0.attn.c_attn.bias: copying a param with shape torch.Size([1152]) from checkpoint, the shape in current model is torch.Size([2304]).
	size mismatch for transformer.h.0.attn.c_proj.weight: copying a param with shape torch.Size([384, 384]) from checkpoint, the shape in current model is torch.Size([768, 768]).
	size mismatch for transformer.h.0.attn.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.0.ln_2.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.0.ln_2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.0.mlp.c_fc.weight: copying a param with shape torch.Size([384, 1536]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
	size mismatch for transformer.h.0.mlp.c_fc.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([3072]).
	size mismatch for transformer.h.0.mlp.c_proj.weight: copying a param with shape torch.Size([1536, 384]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
	size mismatch for transformer.h.0.mlp.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.1.ln_1.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.1.ln_1.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.1.attn.c_attn.weight: copying a param with shape torch.Size([384, 1152]) from checkpoint, the shape in current model is torch.Size([768, 2304]).
	size mismatch for transformer.h.1.attn.c_attn.bias: copying a param with shape torch.Size([1152]) from checkpoint, the shape in current model is torch.Size([2304]).
	size mismatch for transformer.h.1.attn.c_proj.weight: copying a param with shape torch.Size([384, 384]) from checkpoint, the shape in current model is torch.Size([768, 768]).
	size mismatch for transformer.h.1.attn.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.1.ln_2.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.1.ln_2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.1.mlp.c_fc.weight: copying a param with shape torch.Size([384, 1536]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
	size mismatch for transformer.h.1.mlp.c_fc.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([3072]).
	size mismatch for transformer.h.1.mlp.c_proj.weight: copying a param with shape torch.Size([1536, 384]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
	size mismatch for transformer.h.1.mlp.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.2.ln_1.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.2.ln_1.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.2.attn.c_attn.weight: copying a param with shape torch.Size([384, 1152]) from checkpoint, the shape in current model is torch.Size([768, 2304]).
	size mismatch for transformer.h.2.attn.c_attn.bias: copying a param with shape torch.Size([1152]) from checkpoint, the shape in current model is torch.Size([2304]).
	size mismatch for transformer.h.2.attn.c_proj.weight: copying a param with shape torch.Size([384, 384]) from checkpoint, the shape in current model is torch.Size([768, 768]).
	size mismatch for transformer.h.2.attn.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.2.ln_2.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.2.ln_2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.2.mlp.c_fc.weight: copying a param with shape torch.Size([384, 1536]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
	size mismatch for transformer.h.2.mlp.c_fc.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([3072]).
	size mismatch for transformer.h.2.mlp.c_proj.weight: copying a param with shape torch.Size([1536, 384]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
	size mismatch for transformer.h.2.mlp.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.3.ln_1.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.3.ln_1.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.3.attn.c_attn.weight: copying a param with shape torch.Size([384, 1152]) from checkpoint, the shape in current model is torch.Size([768, 2304]).
	size mismatch for transformer.h.3.attn.c_attn.bias: copying a param with shape torch.Size([1152]) from checkpoint, the shape in current model is torch.Size([2304]).
	size mismatch for transformer.h.3.attn.c_proj.weight: copying a param with shape torch.Size([384, 384]) from checkpoint, the shape in current model is torch.Size([768, 768]).
	size mismatch for transformer.h.3.attn.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.3.ln_2.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.3.ln_2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.3.mlp.c_fc.weight: copying a param with shape torch.Size([384, 1536]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
	size mismatch for transformer.h.3.mlp.c_fc.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([3072]).
	size mismatch for transformer.h.3.mlp.c_proj.weight: copying a param with shape torch.Size([1536, 384]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
	size mismatch for transformer.h.3.mlp.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.4.ln_1.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.4.ln_1.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.4.attn.c_attn.weight: copying a param with shape torch.Size([384, 1152]) from checkpoint, the shape in current model is torch.Size([768, 2304]).
	size mismatch for transformer.h.4.attn.c_attn.bias: copying a param with shape torch.Size([1152]) from checkpoint, the shape in current model is torch.Size([2304]).
	size mismatch for transformer.h.4.attn.c_proj.weight: copying a param with shape torch.Size([384, 384]) from checkpoint, the shape in current model is torch.Size([768, 768]).
	size mismatch for transformer.h.4.attn.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.4.ln_2.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.4.ln_2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.4.mlp.c_fc.weight: copying a param with shape torch.Size([384, 1536]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
	size mismatch for transformer.h.4.mlp.c_fc.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([3072]).
	size mismatch for transformer.h.4.mlp.c_proj.weight: copying a param with shape torch.Size([1536, 384]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
	size mismatch for transformer.h.4.mlp.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.5.ln_1.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.5.ln_1.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.5.attn.c_attn.weight: copying a param with shape torch.Size([384, 1152]) from checkpoint, the shape in current model is torch.Size([768, 2304]).
	size mismatch for transformer.h.5.attn.c_attn.bias: copying a param with shape torch.Size([1152]) from checkpoint, the shape in current model is torch.Size([2304]).
	size mismatch for transformer.h.5.attn.c_proj.weight: copying a param with shape torch.Size([384, 384]) from checkpoint, the shape in current model is torch.Size([768, 768]).
	size mismatch for transformer.h.5.attn.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.5.ln_2.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.5.ln_2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.h.5.mlp.c_fc.weight: copying a param with shape torch.Size([384, 1536]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
	size mismatch for transformer.h.5.mlp.c_fc.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([3072]).
	size mismatch for transformer.h.5.mlp.c_proj.weight: copying a param with shape torch.Size([1536, 384]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
	size mismatch for transformer.h.5.mlp.c_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.ln_f.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
	size mismatch for transformer.ln_f.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([768]).
2024-11-16 23:40:15,287 - main - ERROR - Failed to initialize model manager
2024-11-16 23:45:40,456 - main - INFO - Loading tokenizer...
2024-11-16 23:45:41,738 - main - INFO - Loading model...
2024-11-16 23:45:42,454 - main - WARNING - Missing keys: ['lm_head.weight']
2024-11-16 23:45:42,455 - main - WARNING - Unexpected keys: ['lm_head.scale', 'lm_head.zero_point', 'lm_head._packed_params.dtype', 'lm_head._packed_params._packed_params']
2024-11-16 23:45:42,459 - main - INFO - Model and tokenizer loaded successfully