Commit
•
4335708
1
Parent(s):
1c6bcd4
Upload 13 files
Browse files- audio_processing_mllama.py +85 -0
- chat_template.json +3 -0
- config.json +243 -0
- configuration_llama3.py +112 -0
- generation_config.json +13 -0
- mllama_audio_model.py +51 -0
- model.safetensors.index.json +913 -0
- modeling_llama3.py +287 -0
- preprocessor_config.json +25 -0
- processing_mllama.py +365 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2079 -0
audio_processing_mllama.py
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import math
|
| 2 |
+
from typing import Dict, List, Optional, Union
|
| 3 |
+
import numpy as np
|
| 4 |
+
import torch
|
| 5 |
+
from transformers.tokenization_utils_base import AudioInput
|
| 6 |
+
from transformers.models.seamless_m4t.feature_extraction_seamless_m4t import SeamlessM4TFeatureExtractor
|
| 7 |
+
from transformers.utils import TensorType
|
| 8 |
+
from transformers.feature_extraction_utils import BatchFeature
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
def make_list_of_audio_clips(audio: AudioInput) -> List[List[Optional[np.ndarray]]]:
|
| 13 |
+
"""
|
| 14 |
+
Convert a single audio clip or a list of audio clips to a list of numpy arrays.
|
| 15 |
+
|
| 16 |
+
Args:
|
| 17 |
+
audio (`AudioInput`):
|
| 18 |
+
A single audio or a list of audio clips.
|
| 19 |
+
|
| 20 |
+
Returns:
|
| 21 |
+
A list of numpy arrays.
|
| 22 |
+
"""
|
| 23 |
+
# If it's a single audil clip, convert it to a list of lists
|
| 24 |
+
if not isinstance(audio, (list, tuple)):
|
| 25 |
+
output = [[audio]]
|
| 26 |
+
|
| 27 |
+
else:
|
| 28 |
+
if all(isinstance(audio_i, (list, tuple)) for audio_i in audio):
|
| 29 |
+
# If it's a list of batches, it's already in the right format
|
| 30 |
+
output = audio
|
| 31 |
+
else:
|
| 32 |
+
# If it's a list of audio clips, it's a single batch, so convert it to a list of lists
|
| 33 |
+
output = [audio]
|
| 34 |
+
|
| 35 |
+
return output
|
| 36 |
+
|
| 37 |
+
def build_audio_tokens(encoding: Dict, audio_features: List[List[np.ndarray]], audio_token_id: int) -> Dict:
|
| 38 |
+
bs = len(audio_features)
|
| 39 |
+
for i in range(bs):
|
| 40 |
+
for j in range(len(audio_features[i])):
|
| 41 |
+
token_id = -1 - j
|
| 42 |
+
pos = encoding['input_ids'][i].index(audio_token_id)
|
| 43 |
+
encoding['input_ids'][i] = encoding['input_ids'][i][:pos] \
|
| 44 |
+
+ [token_id] * get_num_embeddings(audio_features[i][j].size(0)) \
|
| 45 |
+
+ encoding['input_ids'][i][pos+1:]
|
| 46 |
+
encoding['attention_mask'][i] = [1] * len(encoding['input_ids'][i])
|
| 47 |
+
return encoding
|
| 48 |
+
|
| 49 |
+
def get_num_embeddings(num_framses, adapter_kernel_size=7, adapter_stride=4) -> int:
|
| 50 |
+
return math.ceil((num_framses - adapter_kernel_size) / adapter_stride) + 1 + 2 # 2 = <|begin_of_audio|>, <|end_of_audio|>
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
class MllamaAudioFeatureExtractor(SeamlessM4TFeatureExtractor):
|
| 54 |
+
|
| 55 |
+
def __call__(
|
| 56 |
+
self,
|
| 57 |
+
batch_audio_clips: List[List[AudioInput]],
|
| 58 |
+
return_tensors: Optional[Union[str, TensorType]] = None,
|
| 59 |
+
) -> BatchFeature:
|
| 60 |
+
audio_features = [[ super().__call__(audio_j, return_attention_mask=False)['input_features'][0] for audio_j in audio_i ] for audio_i in batch_audio_clips ]
|
| 61 |
+
packed_audio_features = self.pack_audio_clips(audio_features)
|
| 62 |
+
|
| 63 |
+
encoded_audio_inputs = BatchFeature(
|
| 64 |
+
data={
|
| 65 |
+
"audio_features": packed_audio_features,
|
| 66 |
+
},
|
| 67 |
+
tensor_type=return_tensors,
|
| 68 |
+
)
|
| 69 |
+
|
| 70 |
+
return encoded_audio_inputs
|
| 71 |
+
|
| 72 |
+
def pack_audio_clips(batch_audio_clips: List[List[np.ndarray]]) -> np.ndarray:
|
| 73 |
+
assert batch_audio_clips[0][0].ndim == 2 # sequence length x feature dimension
|
| 74 |
+
# Determine output shape: (batch_size, max_num_clips, max_frames, feature_dim)
|
| 75 |
+
batch_size = len(batch_audio_clips)
|
| 76 |
+
max_num_clips = max([len(clips) for clips in batch_audio_clips])
|
| 77 |
+
max_frames = max([clip.size(0) for clips in batch_audio_clips for clip in clips])
|
| 78 |
+
feature_dim = batch_audio_clips[0][0].size(1)
|
| 79 |
+
|
| 80 |
+
stacked_audio_clips = np.zeros((batch_size, max_num_clips, max_frames, feature_dim), dtype=np.float32)
|
| 81 |
+
for i, clips in enumerate(batch_audio_clips):
|
| 82 |
+
for j, clip in enumerate(clips):
|
| 83 |
+
stacked_audio_clips[i, j, :clip.shape[0], :] = clip
|
| 84 |
+
|
| 85 |
+
return stacked_audio_clips
|
chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- Find out if there are any images #}\n{% set image_ns = namespace(has_images=false) %} \n{%- for message in messages %}\n {%- for content in message['content'] %}\n {%- if content['type'] == 'image' %}\n {%- set image_ns.has_images = true %}\n {%- endif %}\n {%- endfor %}\n{%- endfor %}\n\n{#- Error out if there are images and system message #}\n{%- if image_ns.has_images and not system_message == \"\" %}\n {{- raise_exception(\"Prompting with images is incompatible with system messages.\") }}\n{%- endif %}\n\n{#- System message if there are no images #}\n{%- if not image_ns.has_images %}\n {{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n {%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n {%- endif %}\n {{- \"Cutting Knowledge Date: December 2023\\n\" }}\n {{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n {%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {%- endif %}\n {{- system_message }}\n {{- \"<|eot_id|>\" }}\n{%- endif %}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n' }}\n {%- if message['content'] is string %}\n {{- message['content'] }}\n {%- else %}\n {%- for content in message['content'] %}\n {%- if content['type'] == 'image' %}\n {{- '<|image|>' }}\n {%- elif content['type'] == 'text' %}\n {{- content['text'] }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n"
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,243 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": ["Llama3ForConditionalGeneration"],
|
| 3 |
+
"audio_config": {
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"adapter_act": "relu",
|
| 6 |
+
"adapter_kernel_size": 7,
|
| 7 |
+
"adapter_stride": 4,
|
| 8 |
+
"add_adapter": true,
|
| 9 |
+
"apply_spec_augment": false,
|
| 10 |
+
"architectures": ["Wav2Vec2BertModel"],
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"bos_token_id": 1,
|
| 13 |
+
"classifier_proj_size": 768,
|
| 14 |
+
"codevector_dim": 768,
|
| 15 |
+
"conformer_conv_dropout": 0.1,
|
| 16 |
+
"contrastive_logits_temperature": 0.1,
|
| 17 |
+
"conv_depthwise_kernel_size": 31,
|
| 18 |
+
"ctc_loss_reduction": "sum",
|
| 19 |
+
"ctc_zero_infinity": false,
|
| 20 |
+
"diversity_loss_weight": 0.1,
|
| 21 |
+
"eos_token_id": 2,
|
| 22 |
+
"feat_proj_dropout": 0.0,
|
| 23 |
+
"feat_quantizer_dropout": 0.0,
|
| 24 |
+
"feature_projection_input_dim": 160,
|
| 25 |
+
"final_dropout": 0.1,
|
| 26 |
+
"hidden_act": "swish",
|
| 27 |
+
"hidden_dropout": 0.0,
|
| 28 |
+
"hidden_size": 1024,
|
| 29 |
+
"initializer_range": 0.02,
|
| 30 |
+
"intermediate_size": 4096,
|
| 31 |
+
"layer_norm_eps": 1e-5,
|
| 32 |
+
"layerdrop": 0.1,
|
| 33 |
+
"left_max_position_embeddings": 64,
|
| 34 |
+
"mask_feature_length": 10,
|
| 35 |
+
"mask_feature_min_masks": 0,
|
| 36 |
+
"mask_feature_prob": 0.0,
|
| 37 |
+
"mask_time_length": 10,
|
| 38 |
+
"mask_time_min_masks": 2,
|
| 39 |
+
"mask_time_prob": 0.05,
|
| 40 |
+
"max_source_positions": 5000,
|
| 41 |
+
"model_type": "wav2vec2-bert",
|
| 42 |
+
"num_adapter_layers": 1,
|
| 43 |
+
"num_attention_heads": 16,
|
| 44 |
+
"num_codevector_groups": 2,
|
| 45 |
+
"num_codevectors_per_group": 320,
|
| 46 |
+
"num_hidden_layers": 24,
|
| 47 |
+
"num_negatives": 100,
|
| 48 |
+
"output_hidden_size": 4096,
|
| 49 |
+
"pad_token_id": 0,
|
| 50 |
+
"position_embeddings_type": "relative_key",
|
| 51 |
+
"proj_codevector_dim": 768,
|
| 52 |
+
"right_max_position_embeddings": 8,
|
| 53 |
+
"rotary_embedding_base": 10000,
|
| 54 |
+
"tdnn_dilation": [1, 2, 3, 1, 1],
|
| 55 |
+
"tdnn_dim": [512, 512, 512, 512, 1500],
|
| 56 |
+
"tdnn_kernel": [5, 3, 3, 1, 1],
|
| 57 |
+
"torch_dtype": "float16",
|
| 58 |
+
"transformers_version": "4.37.0.dev0",
|
| 59 |
+
"use_intermediate_ffn_before_adapter": false,
|
| 60 |
+
"use_weighted_layer_sum": false,
|
| 61 |
+
"vocab_size": null,
|
| 62 |
+
"xvector_output_dim": 512,
|
| 63 |
+
"attn_implementation": "eager"
|
| 64 |
+
},
|
| 65 |
+
"auto_map": {
|
| 66 |
+
"AutoConfig": "configuration_llama3.Llama3Config",
|
| 67 |
+
"AutoModel": "modeling_llama3.Llama3ForConditionalGeneration"
|
| 68 |
+
},
|
| 69 |
+
"image_token_index": 128256,
|
| 70 |
+
"model_type": "llama3",
|
| 71 |
+
"text_config": {
|
| 72 |
+
"_name_or_path": "",
|
| 73 |
+
"add_cross_attention": false,
|
| 74 |
+
"architectures": null,
|
| 75 |
+
"bad_words_ids": null,
|
| 76 |
+
"begin_suppress_tokens": null,
|
| 77 |
+
"bos_token_id": 128000,
|
| 78 |
+
"chunk_size_feed_forward": 0,
|
| 79 |
+
"cross_attention_hidden_size": null,
|
| 80 |
+
"cross_attention_layers": [3, 8, 13, 18, 23, 28, 33, 38],
|
| 81 |
+
"decoder_start_token_id": null,
|
| 82 |
+
"diversity_penalty": 0.0,
|
| 83 |
+
"do_sample": false,
|
| 84 |
+
"dropout": 0,
|
| 85 |
+
"early_stopping": false,
|
| 86 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 87 |
+
"eos_token_id": [128001, 128008, 128009],
|
| 88 |
+
"exponential_decay_length_penalty": null,
|
| 89 |
+
"finetuning_task": null,
|
| 90 |
+
"forced_bos_token_id": null,
|
| 91 |
+
"forced_eos_token_id": null,
|
| 92 |
+
"hidden_act": "silu",
|
| 93 |
+
"hidden_size": 4096,
|
| 94 |
+
"id2label": {
|
| 95 |
+
"0": "LABEL_0",
|
| 96 |
+
"1": "LABEL_1"
|
| 97 |
+
},
|
| 98 |
+
"initializer_range": 0.02,
|
| 99 |
+
"intermediate_size": 14336,
|
| 100 |
+
"is_decoder": false,
|
| 101 |
+
"is_encoder_decoder": false,
|
| 102 |
+
"label2id": {
|
| 103 |
+
"LABEL_0": 0,
|
| 104 |
+
"LABEL_1": 1
|
| 105 |
+
},
|
| 106 |
+
"length_penalty": 1.0,
|
| 107 |
+
"max_length": 20,
|
| 108 |
+
"max_position_embeddings": 131072,
|
| 109 |
+
"min_length": 0,
|
| 110 |
+
"model_type": "mllama_text_model",
|
| 111 |
+
"no_repeat_ngram_size": 0,
|
| 112 |
+
"num_attention_heads": 32,
|
| 113 |
+
"num_beam_groups": 1,
|
| 114 |
+
"num_beams": 1,
|
| 115 |
+
"num_hidden_layers": 40,
|
| 116 |
+
"num_key_value_heads": 8,
|
| 117 |
+
"num_return_sequences": 1,
|
| 118 |
+
"output_attentions": false,
|
| 119 |
+
"output_hidden_states": false,
|
| 120 |
+
"output_scores": false,
|
| 121 |
+
"pad_token_id": 128004,
|
| 122 |
+
"prefix": null,
|
| 123 |
+
"problem_type": null,
|
| 124 |
+
"pruned_heads": {},
|
| 125 |
+
"remove_invalid_values": false,
|
| 126 |
+
"repetition_penalty": 1.0,
|
| 127 |
+
"return_dict": true,
|
| 128 |
+
"return_dict_in_generate": false,
|
| 129 |
+
"rms_norm_eps": 1e-5,
|
| 130 |
+
"rope_scaling": {
|
| 131 |
+
"factor": 8.0,
|
| 132 |
+
"high_freq_factor": 4.0,
|
| 133 |
+
"low_freq_factor": 1.0,
|
| 134 |
+
"original_max_position_embeddings": 8192,
|
| 135 |
+
"rope_type": "llama3"
|
| 136 |
+
},
|
| 137 |
+
"rope_theta": 500000.0,
|
| 138 |
+
"sep_token_id": null,
|
| 139 |
+
"suppress_tokens": null,
|
| 140 |
+
"task_specific_params": null,
|
| 141 |
+
"temperature": 1.0,
|
| 142 |
+
"tf_legacy_loss": false,
|
| 143 |
+
"tie_encoder_decoder": false,
|
| 144 |
+
"tie_word_embeddings": false,
|
| 145 |
+
"tokenizer_class": null,
|
| 146 |
+
"top_k": 50,
|
| 147 |
+
"top_p": 1.0,
|
| 148 |
+
"torch_dtype": "float16",
|
| 149 |
+
"torchscript": false,
|
| 150 |
+
"typical_p": 1.0,
|
| 151 |
+
"use_bfloat16": false,
|
| 152 |
+
"use_cache": true,
|
| 153 |
+
"vocab_size": 128256
|
| 154 |
+
},
|
| 155 |
+
"torch_dtype": "float16",
|
| 156 |
+
"transformers_version": "4.45.0.dev0",
|
| 157 |
+
"vision_config": {
|
| 158 |
+
"_name_or_path": "",
|
| 159 |
+
"add_cross_attention": false,
|
| 160 |
+
"architectures": null,
|
| 161 |
+
"attention_heads": 16,
|
| 162 |
+
"bad_words_ids": null,
|
| 163 |
+
"begin_suppress_tokens": null,
|
| 164 |
+
"bos_token_id": null,
|
| 165 |
+
"chunk_size_feed_forward": 0,
|
| 166 |
+
"cross_attention_hidden_size": null,
|
| 167 |
+
"decoder_start_token_id": null,
|
| 168 |
+
"diversity_penalty": 0.0,
|
| 169 |
+
"do_sample": false,
|
| 170 |
+
"early_stopping": false,
|
| 171 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 172 |
+
"eos_token_id": null,
|
| 173 |
+
"exponential_decay_length_penalty": null,
|
| 174 |
+
"finetuning_task": null,
|
| 175 |
+
"forced_bos_token_id": null,
|
| 176 |
+
"forced_eos_token_id": null,
|
| 177 |
+
"hidden_act": "gelu",
|
| 178 |
+
"hidden_size": 1280,
|
| 179 |
+
"id2label": {
|
| 180 |
+
"0": "LABEL_0",
|
| 181 |
+
"1": "LABEL_1"
|
| 182 |
+
},
|
| 183 |
+
"image_size": 560,
|
| 184 |
+
"intermediate_layers_indices": [3, 7, 15, 23, 30],
|
| 185 |
+
"intermediate_size": 5120,
|
| 186 |
+
"is_decoder": false,
|
| 187 |
+
"is_encoder_decoder": false,
|
| 188 |
+
"label2id": {
|
| 189 |
+
"LABEL_0": 0,
|
| 190 |
+
"LABEL_1": 1
|
| 191 |
+
},
|
| 192 |
+
"length_penalty": 1.0,
|
| 193 |
+
"max_length": 20,
|
| 194 |
+
"max_num_tiles": 4,
|
| 195 |
+
"min_length": 0,
|
| 196 |
+
"model_type": "mllama_vision_model",
|
| 197 |
+
"no_repeat_ngram_size": 0,
|
| 198 |
+
"norm_eps": 1e-5,
|
| 199 |
+
"num_beam_groups": 1,
|
| 200 |
+
"num_beams": 1,
|
| 201 |
+
"num_channels": 3,
|
| 202 |
+
"num_global_layers": 8,
|
| 203 |
+
"num_hidden_layers": 32,
|
| 204 |
+
"num_return_sequences": 1,
|
| 205 |
+
"output_attentions": false,
|
| 206 |
+
"output_hidden_states": false,
|
| 207 |
+
"output_scores": false,
|
| 208 |
+
"pad_token_id": null,
|
| 209 |
+
"patch_size": 14,
|
| 210 |
+
"prefix": null,
|
| 211 |
+
"problem_type": null,
|
| 212 |
+
"pruned_heads": {},
|
| 213 |
+
"remove_invalid_values": false,
|
| 214 |
+
"repetition_penalty": 1.0,
|
| 215 |
+
"return_dict": true,
|
| 216 |
+
"return_dict_in_generate": false,
|
| 217 |
+
"sep_token_id": null,
|
| 218 |
+
"supported_aspect_ratios": [
|
| 219 |
+
[1, 1],
|
| 220 |
+
[1, 2],
|
| 221 |
+
[1, 3],
|
| 222 |
+
[1, 4],
|
| 223 |
+
[2, 1],
|
| 224 |
+
[2, 2],
|
| 225 |
+
[3, 1],
|
| 226 |
+
[4, 1]
|
| 227 |
+
],
|
| 228 |
+
"suppress_tokens": null,
|
| 229 |
+
"task_specific_params": null,
|
| 230 |
+
"temperature": 1.0,
|
| 231 |
+
"tf_legacy_loss": false,
|
| 232 |
+
"tie_encoder_decoder": false,
|
| 233 |
+
"tie_word_embeddings": true,
|
| 234 |
+
"tokenizer_class": null,
|
| 235 |
+
"top_k": 50,
|
| 236 |
+
"top_p": 1.0,
|
| 237 |
+
"torch_dtype": "float16",
|
| 238 |
+
"torchscript": false,
|
| 239 |
+
"typical_p": 1.0,
|
| 240 |
+
"use_bfloat16": false,
|
| 241 |
+
"vision_output_dim": 7680
|
| 242 |
+
}
|
| 243 |
+
}
|
configuration_llama3.py
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# coding=utf-8
|
| 2 |
+
# Copyright 2024 HuggingFace Inc. team. All rights reserved.
|
| 3 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
| 4 |
+
# you may not use this file except in compliance with the License.
|
| 5 |
+
# You may obtain a copy of the License at
|
| 6 |
+
#
|
| 7 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
| 8 |
+
#
|
| 9 |
+
# Unless required by applicable law or agreed to in writing, software
|
| 10 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
| 11 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 12 |
+
# See the License for the specific language governing permissions and
|
| 13 |
+
# limitations under the License.
|
| 14 |
+
"""Mllama model configuration"""
|
| 15 |
+
|
| 16 |
+
import os
|
| 17 |
+
from typing import Dict, List, Optional, Union
|
| 18 |
+
|
| 19 |
+
from transformers.configuration_utils import PretrainedConfig
|
| 20 |
+
from transformers.modeling_rope_utils import rope_config_validation
|
| 21 |
+
from transformers.utils import logging
|
| 22 |
+
from transformers import Wav2Vec2BertConfig
|
| 23 |
+
from transformers.models.mllama.configuration_mllama import MllamaVisionConfig, MllamaTextConfig
|
| 24 |
+
|
| 25 |
+
logger = logging.get_logger(__name__)
|
| 26 |
+
|
| 27 |
+
class MllamaAudioConfig(Wav2Vec2BertConfig):
|
| 28 |
+
def __init__(self, filler_token_id: int = 128004, **kwargs):
|
| 29 |
+
super().__init__(**kwargs)
|
| 30 |
+
self.filler_token_id = filler_token_id
|
| 31 |
+
|
| 32 |
+
class Llama3Config(PretrainedConfig):
|
| 33 |
+
r"""
|
| 34 |
+
This is the configuration class to store the configuration of a [`MllamaForConditionalGeneration`]. It is used to instantiate an
|
| 35 |
+
Mllama model according to the specified arguments, defining the model architecture. Instantiating a configuration
|
| 36 |
+
with the defaults will yield a similar configuration to that of the Mllama-9B.
|
| 37 |
+
|
| 38 |
+
e.g. [meta-llama/Llama-3.2-11B-Vision](https://huggingface.co/meta-llama/Llama-3.2-11B-Vision)
|
| 39 |
+
|
| 40 |
+
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
| 41 |
+
documentation from [`PretrainedConfig`] for more information.
|
| 42 |
+
|
| 43 |
+
Args:
|
| 44 |
+
vision_config (`Union[AutoConfig, dict]`, *optional*, defaults to `MllamaVisionConfig`):
|
| 45 |
+
The config object or dictionary of the vision backbone.
|
| 46 |
+
text_config (`Union[AutoConfig, dict]`, *optional*, defaults to `MllamaTextConfig`):
|
| 47 |
+
The config object or dictionary of the text backbone.
|
| 48 |
+
image_token_index (`int`, *optional*, defaults to 128256):
|
| 49 |
+
The image token index to encode the image prompt.
|
| 50 |
+
|
| 51 |
+
Example:
|
| 52 |
+
|
| 53 |
+
```python
|
| 54 |
+
>>> from transformers import MllamaForConditionalGeneration, MllamaConfig, MllamaVisionConfig, MllamaTextConfig
|
| 55 |
+
|
| 56 |
+
>>> # Initializing a CLIP-vision config
|
| 57 |
+
>>> vision_config = MllamaVisionConfig()
|
| 58 |
+
|
| 59 |
+
>>> # Initializing a Llama config
|
| 60 |
+
>>> text_config = MllamaTextConfig()
|
| 61 |
+
|
| 62 |
+
>>> # Initializing a mllama-11b style configuration
|
| 63 |
+
>>> configuration = MllamaConfig(vision_config, text_config)
|
| 64 |
+
|
| 65 |
+
>>> # Initializing a model from the mllama-11b style configuration
|
| 66 |
+
>>> model = MllamaForConditionalGeneration(configuration)
|
| 67 |
+
|
| 68 |
+
>>> # Accessing the model configuration
|
| 69 |
+
>>> configuration = model.config
|
| 70 |
+
```"""
|
| 71 |
+
|
| 72 |
+
model_type = "llama3"
|
| 73 |
+
is_composition = True
|
| 74 |
+
|
| 75 |
+
def __init__(
|
| 76 |
+
self,
|
| 77 |
+
vision_config=None,
|
| 78 |
+
text_config=None,
|
| 79 |
+
audio_config=None,
|
| 80 |
+
image_token_index=128256,
|
| 81 |
+
audio_token_index=128257,
|
| 82 |
+
**kwargs,
|
| 83 |
+
):
|
| 84 |
+
if vision_config is None:
|
| 85 |
+
self.vision_config = MllamaVisionConfig()
|
| 86 |
+
logger.info("vision_config is None, using default mllama vision config")
|
| 87 |
+
elif isinstance(vision_config, dict):
|
| 88 |
+
self.vision_config = MllamaVisionConfig(**vision_config)
|
| 89 |
+
elif isinstance(vision_config, MllamaVisionConfig):
|
| 90 |
+
self.vision_config = vision_config
|
| 91 |
+
|
| 92 |
+
self.image_token_index = image_token_index
|
| 93 |
+
|
| 94 |
+
if audio_config is None:
|
| 95 |
+
self.audio_config = MllamaAudioConfig()
|
| 96 |
+
logger.info("audio_config is None, using default mllama audio config")
|
| 97 |
+
elif isinstance(audio_config, dict):
|
| 98 |
+
self.audio_config = MllamaAudioConfig(**audio_config)
|
| 99 |
+
elif isinstance(audio_config, MllamaAudioConfig):
|
| 100 |
+
self.audio_config = audio_config
|
| 101 |
+
|
| 102 |
+
self.audio_token_index = audio_token_index
|
| 103 |
+
|
| 104 |
+
if text_config is None:
|
| 105 |
+
self.text_config = MllamaTextConfig()
|
| 106 |
+
logger.info("text_config is None, using default mllama text config")
|
| 107 |
+
elif isinstance(text_config, dict):
|
| 108 |
+
self.text_config = MllamaTextConfig(**text_config)
|
| 109 |
+
elif isinstance(text_config, MllamaTextConfig):
|
| 110 |
+
self.text_config = text_config
|
| 111 |
+
|
| 112 |
+
super().__init__(**kwargs)
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 128000,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
128001,
|
| 6 |
+
128008,
|
| 7 |
+
128009
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 128004,
|
| 10 |
+
"temperature": 0.6,
|
| 11 |
+
"top_p": 0.9,
|
| 12 |
+
"transformers_version": "4.45.0.dev0"
|
| 13 |
+
}
|
mllama_audio_model.py
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import itertools
|
| 2 |
+
|
| 3 |
+
from typing import List, Optional, Tuple, Union
|
| 4 |
+
import torch
|
| 5 |
+
from torch import nn
|
| 6 |
+
from transformers.modeling_outputs import BaseModelOutput
|
| 7 |
+
from transformers import Wav2Vec2BertModel
|
| 8 |
+
from configuration_llama3 import MllamaAudioConfig
|
| 9 |
+
from modeling_llama3 import MllamaPreTrainedModel
|
| 10 |
+
|
| 11 |
+
def split_list(lst, val):
|
| 12 |
+
return [list(group) for k,
|
| 13 |
+
group in
|
| 14 |
+
itertools.groupby(lst, lambda x: x==val) if not k]
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
class MllamaAudioModel(MllamaPreTrainedModel):
|
| 18 |
+
config_class = MllamaAudioConfig
|
| 19 |
+
base_model_prefix = "audio_model"
|
| 20 |
+
def __init__(self, config: MllamaAudioConfig, text_embedding: nn.Embedding):
|
| 21 |
+
super().__init__(config)
|
| 22 |
+
assert config.add_adapter is True, f'{type(self).__name__} requires add adapter to be true.'
|
| 23 |
+
assert config.output_hidden_size == text_embedding.weight.shape[1], f'Output hidden size({config.output_hidden_size}) of audio model and text embedding({text_embedding.weight.shape[1]}) must match!'
|
| 24 |
+
self.text_embedding = text_embedding
|
| 25 |
+
self.audio_embedding = Wav2Vec2BertModel(config)
|
| 26 |
+
self.start_of_audio = nn.Parameter(data=torch.mean(text_embedding.weight, dim=0).unsqueeze(0), requires_grad=True)
|
| 27 |
+
self.end_of_audio = nn.Parameter(data=torch.mean(text_embedding.weight, dim=0).unsqueeze(0), requires_grad=True)
|
| 28 |
+
self.filler_token_id = config.filler_token_id
|
| 29 |
+
|
| 30 |
+
def forward(
|
| 31 |
+
self,
|
| 32 |
+
audio_features: torch.Tensor = None,
|
| 33 |
+
input_ids: torch.LongTensor = None,
|
| 34 |
+
return_dict: Optional[bool] = None,
|
| 35 |
+
) -> Union[BaseModelOutput, Tuple[torch.Tensor, ...]]:
|
| 36 |
+
input_embeddings = self.text_embedding(torch.clamp(input_ids, min=0))
|
| 37 |
+
bs, max_num_img, _, _ = audio_features.shape
|
| 38 |
+
|
| 39 |
+
for i in range(bs):
|
| 40 |
+
for j in range(max_num_img):
|
| 41 |
+
audio_id = -1 - j
|
| 42 |
+
idx = torch.where(input_ids[i] == audio_id)
|
| 43 |
+
if idx.numel() > 0:
|
| 44 |
+
input_embeddings[i][idx] = torch.concat([self.start_of_audio, audio_features[i, j][idx], self.end_of_audio])
|
| 45 |
+
|
| 46 |
+
idx = torch.where(input_ids < 0 and input_ids >= -max_num_img)
|
| 47 |
+
input_ids[idx].fill_(self.filler_token_id)
|
| 48 |
+
|
| 49 |
+
if return_dict:
|
| 50 |
+
return dict(input_embeddings=input_embeddings)
|
| 51 |
+
return input_embeddings
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,913 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 21340441670
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"language_model.lm_head.weight": "model-00005-of-00005.safetensors",
|
| 7 |
+
"language_model.model.embed_tokens.weight": "model-00001-of-00005.safetensors",
|
| 8 |
+
"language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 9 |
+
"language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 10 |
+
"language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 11 |
+
"language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 12 |
+
"language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 13 |
+
"language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 14 |
+
"language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 15 |
+
"language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 16 |
+
"language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 17 |
+
"language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 18 |
+
"language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 19 |
+
"language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 20 |
+
"language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 21 |
+
"language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 22 |
+
"language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 23 |
+
"language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 24 |
+
"language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 25 |
+
"language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 26 |
+
"language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 27 |
+
"language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 28 |
+
"language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 29 |
+
"language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 30 |
+
"language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 31 |
+
"language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 32 |
+
"language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 33 |
+
"language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 34 |
+
"language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 35 |
+
"language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 36 |
+
"language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 37 |
+
"language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 38 |
+
"language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 39 |
+
"language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 40 |
+
"language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 41 |
+
"language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 42 |
+
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 43 |
+
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 44 |
+
"language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 45 |
+
"language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 46 |
+
"language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 47 |
+
"language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 48 |
+
"language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 49 |
+
"language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 50 |
+
"language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 51 |
+
"language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 52 |
+
"language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 53 |
+
"language_model.model.layers.13.cross_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 54 |
+
"language_model.model.layers.13.cross_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 55 |
+
"language_model.model.layers.13.cross_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 56 |
+
"language_model.model.layers.13.cross_attn.q_norm.weight": "model-00002-of-00005.safetensors",
|
| 57 |
+
"language_model.model.layers.13.cross_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 58 |
+
"language_model.model.layers.13.cross_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 59 |
+
"language_model.model.layers.13.cross_attn_attn_gate": "model-00002-of-00005.safetensors",
|
| 60 |
+
"language_model.model.layers.13.cross_attn_mlp_gate": "model-00002-of-00005.safetensors",
|
| 61 |
+
"language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 62 |
+
"language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 63 |
+
"language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 64 |
+
"language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 65 |
+
"language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 66 |
+
"language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 67 |
+
"language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 68 |
+
"language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 69 |
+
"language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 70 |
+
"language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 71 |
+
"language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 72 |
+
"language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 73 |
+
"language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 74 |
+
"language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 75 |
+
"language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 76 |
+
"language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 77 |
+
"language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 78 |
+
"language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 79 |
+
"language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 80 |
+
"language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 81 |
+
"language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 82 |
+
"language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 83 |
+
"language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 84 |
+
"language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 85 |
+
"language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 86 |
+
"language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 87 |
+
"language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 88 |
+
"language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 89 |
+
"language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 90 |
+
"language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 91 |
+
"language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 92 |
+
"language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 93 |
+
"language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 94 |
+
"language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 95 |
+
"language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 96 |
+
"language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 97 |
+
"language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 98 |
+
"language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 99 |
+
"language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 100 |
+
"language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 101 |
+
"language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 102 |
+
"language_model.model.layers.18.cross_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 103 |
+
"language_model.model.layers.18.cross_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 104 |
+
"language_model.model.layers.18.cross_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 105 |
+
"language_model.model.layers.18.cross_attn.q_norm.weight": "model-00003-of-00005.safetensors",
|
| 106 |
+
"language_model.model.layers.18.cross_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 107 |
+
"language_model.model.layers.18.cross_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 108 |
+
"language_model.model.layers.18.cross_attn_attn_gate": "model-00003-of-00005.safetensors",
|
| 109 |
+
"language_model.model.layers.18.cross_attn_mlp_gate": "model-00003-of-00005.safetensors",
|
| 110 |
+
"language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 111 |
+
"language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 112 |
+
"language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 113 |
+
"language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 114 |
+
"language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 115 |
+
"language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 116 |
+
"language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 117 |
+
"language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 118 |
+
"language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 119 |
+
"language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 120 |
+
"language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 121 |
+
"language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 122 |
+
"language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 123 |
+
"language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 124 |
+
"language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 125 |
+
"language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 126 |
+
"language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 127 |
+
"language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 128 |
+
"language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 129 |
+
"language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 130 |
+
"language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 131 |
+
"language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 132 |
+
"language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 133 |
+
"language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 134 |
+
"language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 135 |
+
"language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 136 |
+
"language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 137 |
+
"language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 138 |
+
"language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 139 |
+
"language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 140 |
+
"language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 141 |
+
"language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 142 |
+
"language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 143 |
+
"language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 144 |
+
"language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 145 |
+
"language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 146 |
+
"language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 147 |
+
"language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 148 |
+
"language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 149 |
+
"language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 150 |
+
"language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 151 |
+
"language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 152 |
+
"language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 153 |
+
"language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 154 |
+
"language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 155 |
+
"language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 156 |
+
"language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 157 |
+
"language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 158 |
+
"language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 159 |
+
"language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 160 |
+
"language_model.model.layers.23.cross_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 161 |
+
"language_model.model.layers.23.cross_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 162 |
+
"language_model.model.layers.23.cross_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 163 |
+
"language_model.model.layers.23.cross_attn.q_norm.weight": "model-00003-of-00005.safetensors",
|
| 164 |
+
"language_model.model.layers.23.cross_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 165 |
+
"language_model.model.layers.23.cross_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 166 |
+
"language_model.model.layers.23.cross_attn_attn_gate": "model-00003-of-00005.safetensors",
|
| 167 |
+
"language_model.model.layers.23.cross_attn_mlp_gate": "model-00003-of-00005.safetensors",
|
| 168 |
+
"language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 169 |
+
"language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 170 |
+
"language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 171 |
+
"language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 172 |
+
"language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 173 |
+
"language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 174 |
+
"language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 175 |
+
"language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 176 |
+
"language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 177 |
+
"language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 178 |
+
"language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 179 |
+
"language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 180 |
+
"language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 181 |
+
"language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 182 |
+
"language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 183 |
+
"language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 184 |
+
"language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 185 |
+
"language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 186 |
+
"language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 187 |
+
"language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 188 |
+
"language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 189 |
+
"language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 190 |
+
"language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 191 |
+
"language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 192 |
+
"language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 193 |
+
"language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 194 |
+
"language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 195 |
+
"language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 196 |
+
"language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 197 |
+
"language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 198 |
+
"language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 199 |
+
"language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 200 |
+
"language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 201 |
+
"language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 202 |
+
"language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 203 |
+
"language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 204 |
+
"language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 205 |
+
"language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 206 |
+
"language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 207 |
+
"language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 208 |
+
"language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 209 |
+
"language_model.model.layers.28.cross_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 210 |
+
"language_model.model.layers.28.cross_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 211 |
+
"language_model.model.layers.28.cross_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 212 |
+
"language_model.model.layers.28.cross_attn.q_norm.weight": "model-00004-of-00005.safetensors",
|
| 213 |
+
"language_model.model.layers.28.cross_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 214 |
+
"language_model.model.layers.28.cross_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 215 |
+
"language_model.model.layers.28.cross_attn_attn_gate": "model-00004-of-00005.safetensors",
|
| 216 |
+
"language_model.model.layers.28.cross_attn_mlp_gate": "model-00004-of-00005.safetensors",
|
| 217 |
+
"language_model.model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 218 |
+
"language_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 219 |
+
"language_model.model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 220 |
+
"language_model.model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 221 |
+
"language_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 222 |
+
"language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 223 |
+
"language_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 224 |
+
"language_model.model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 225 |
+
"language_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 226 |
+
"language_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 227 |
+
"language_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 228 |
+
"language_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 229 |
+
"language_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 230 |
+
"language_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 231 |
+
"language_model.model.layers.3.cross_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 232 |
+
"language_model.model.layers.3.cross_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 233 |
+
"language_model.model.layers.3.cross_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 234 |
+
"language_model.model.layers.3.cross_attn.q_norm.weight": "model-00001-of-00005.safetensors",
|
| 235 |
+
"language_model.model.layers.3.cross_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 236 |
+
"language_model.model.layers.3.cross_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 237 |
+
"language_model.model.layers.3.cross_attn_attn_gate": "model-00001-of-00005.safetensors",
|
| 238 |
+
"language_model.model.layers.3.cross_attn_mlp_gate": "model-00001-of-00005.safetensors",
|
| 239 |
+
"language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 240 |
+
"language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 241 |
+
"language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 242 |
+
"language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 243 |
+
"language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 244 |
+
"language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 245 |
+
"language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 246 |
+
"language_model.model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 247 |
+
"language_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 248 |
+
"language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 249 |
+
"language_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 250 |
+
"language_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 251 |
+
"language_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 252 |
+
"language_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 253 |
+
"language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 254 |
+
"language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 255 |
+
"language_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 256 |
+
"language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 257 |
+
"language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 258 |
+
"language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 259 |
+
"language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 260 |
+
"language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 261 |
+
"language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 262 |
+
"language_model.model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 263 |
+
"language_model.model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 264 |
+
"language_model.model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 265 |
+
"language_model.model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 266 |
+
"language_model.model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 267 |
+
"language_model.model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 268 |
+
"language_model.model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 269 |
+
"language_model.model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 270 |
+
"language_model.model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 271 |
+
"language_model.model.layers.33.cross_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 272 |
+
"language_model.model.layers.33.cross_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 273 |
+
"language_model.model.layers.33.cross_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 274 |
+
"language_model.model.layers.33.cross_attn.q_norm.weight": "model-00004-of-00005.safetensors",
|
| 275 |
+
"language_model.model.layers.33.cross_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 276 |
+
"language_model.model.layers.33.cross_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 277 |
+
"language_model.model.layers.33.cross_attn_attn_gate": "model-00004-of-00005.safetensors",
|
| 278 |
+
"language_model.model.layers.33.cross_attn_mlp_gate": "model-00004-of-00005.safetensors",
|
| 279 |
+
"language_model.model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 280 |
+
"language_model.model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 281 |
+
"language_model.model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 282 |
+
"language_model.model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 283 |
+
"language_model.model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 284 |
+
"language_model.model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 285 |
+
"language_model.model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 286 |
+
"language_model.model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 287 |
+
"language_model.model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 288 |
+
"language_model.model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 289 |
+
"language_model.model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 290 |
+
"language_model.model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 291 |
+
"language_model.model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 292 |
+
"language_model.model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 293 |
+
"language_model.model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 294 |
+
"language_model.model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 295 |
+
"language_model.model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 296 |
+
"language_model.model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 297 |
+
"language_model.model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 298 |
+
"language_model.model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 299 |
+
"language_model.model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 300 |
+
"language_model.model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 301 |
+
"language_model.model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 302 |
+
"language_model.model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 303 |
+
"language_model.model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 304 |
+
"language_model.model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 305 |
+
"language_model.model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 306 |
+
"language_model.model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 307 |
+
"language_model.model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 308 |
+
"language_model.model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 309 |
+
"language_model.model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 310 |
+
"language_model.model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 311 |
+
"language_model.model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 312 |
+
"language_model.model.layers.37.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 313 |
+
"language_model.model.layers.37.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 314 |
+
"language_model.model.layers.37.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 315 |
+
"language_model.model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 316 |
+
"language_model.model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 317 |
+
"language_model.model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 318 |
+
"language_model.model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 319 |
+
"language_model.model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 320 |
+
"language_model.model.layers.38.cross_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 321 |
+
"language_model.model.layers.38.cross_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 322 |
+
"language_model.model.layers.38.cross_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 323 |
+
"language_model.model.layers.38.cross_attn.q_norm.weight": "model-00004-of-00005.safetensors",
|
| 324 |
+
"language_model.model.layers.38.cross_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 325 |
+
"language_model.model.layers.38.cross_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 326 |
+
"language_model.model.layers.38.cross_attn_attn_gate": "model-00004-of-00005.safetensors",
|
| 327 |
+
"language_model.model.layers.38.cross_attn_mlp_gate": "model-00004-of-00005.safetensors",
|
| 328 |
+
"language_model.model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 329 |
+
"language_model.model.layers.38.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 330 |
+
"language_model.model.layers.38.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 331 |
+
"language_model.model.layers.38.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 332 |
+
"language_model.model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 333 |
+
"language_model.model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 334 |
+
"language_model.model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 335 |
+
"language_model.model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 336 |
+
"language_model.model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 337 |
+
"language_model.model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 338 |
+
"language_model.model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 339 |
+
"language_model.model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 340 |
+
"language_model.model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 341 |
+
"language_model.model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 342 |
+
"language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 343 |
+
"language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 344 |
+
"language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 345 |
+
"language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 346 |
+
"language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 347 |
+
"language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 348 |
+
"language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 349 |
+
"language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 350 |
+
"language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 351 |
+
"language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 352 |
+
"language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 353 |
+
"language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 354 |
+
"language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 355 |
+
"language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 356 |
+
"language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 357 |
+
"language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 358 |
+
"language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 359 |
+
"language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 360 |
+
"language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 361 |
+
"language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 362 |
+
"language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 363 |
+
"language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 364 |
+
"language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 365 |
+
"language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 366 |
+
"language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 367 |
+
"language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 368 |
+
"language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 369 |
+
"language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 370 |
+
"language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 371 |
+
"language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 372 |
+
"language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 373 |
+
"language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 374 |
+
"language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 375 |
+
"language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 376 |
+
"language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 377 |
+
"language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 378 |
+
"language_model.model.layers.8.cross_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 379 |
+
"language_model.model.layers.8.cross_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 380 |
+
"language_model.model.layers.8.cross_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 381 |
+
"language_model.model.layers.8.cross_attn.q_norm.weight": "model-00002-of-00005.safetensors",
|
| 382 |
+
"language_model.model.layers.8.cross_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 383 |
+
"language_model.model.layers.8.cross_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 384 |
+
"language_model.model.layers.8.cross_attn_attn_gate": "model-00002-of-00005.safetensors",
|
| 385 |
+
"language_model.model.layers.8.cross_attn_mlp_gate": "model-00002-of-00005.safetensors",
|
| 386 |
+
"language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 387 |
+
"language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 388 |
+
"language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 389 |
+
"language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 390 |
+
"language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 391 |
+
"language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 392 |
+
"language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 393 |
+
"language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 394 |
+
"language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 395 |
+
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 396 |
+
"language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 397 |
+
"language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 398 |
+
"language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 399 |
+
"language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 400 |
+
"language_model.model.norm.weight": "model-00005-of-00005.safetensors",
|
| 401 |
+
"multi_modal_projector.bias": "model-00005-of-00005.safetensors",
|
| 402 |
+
"multi_modal_projector.weight": "model-00005-of-00005.safetensors",
|
| 403 |
+
"vision_model.class_embedding": "model-00001-of-00005.safetensors",
|
| 404 |
+
"vision_model.gated_positional_embedding.embedding": "model-00001-of-00005.safetensors",
|
| 405 |
+
"vision_model.gated_positional_embedding.gate": "model-00001-of-00005.safetensors",
|
| 406 |
+
"vision_model.gated_positional_embedding.tile_embedding.weight": "model-00001-of-00005.safetensors",
|
| 407 |
+
"vision_model.global_transformer.layers.0.gate_attn": "model-00001-of-00005.safetensors",
|
| 408 |
+
"vision_model.global_transformer.layers.0.gate_ffn": "model-00001-of-00005.safetensors",
|
| 409 |
+
"vision_model.global_transformer.layers.0.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 410 |
+
"vision_model.global_transformer.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 411 |
+
"vision_model.global_transformer.layers.0.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 412 |
+
"vision_model.global_transformer.layers.0.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 413 |
+
"vision_model.global_transformer.layers.0.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 414 |
+
"vision_model.global_transformer.layers.0.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 415 |
+
"vision_model.global_transformer.layers.0.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 416 |
+
"vision_model.global_transformer.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 417 |
+
"vision_model.global_transformer.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 418 |
+
"vision_model.global_transformer.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 419 |
+
"vision_model.global_transformer.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 420 |
+
"vision_model.global_transformer.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 421 |
+
"vision_model.global_transformer.layers.1.gate_attn": "model-00001-of-00005.safetensors",
|
| 422 |
+
"vision_model.global_transformer.layers.1.gate_ffn": "model-00001-of-00005.safetensors",
|
| 423 |
+
"vision_model.global_transformer.layers.1.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 424 |
+
"vision_model.global_transformer.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 425 |
+
"vision_model.global_transformer.layers.1.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 426 |
+
"vision_model.global_transformer.layers.1.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 427 |
+
"vision_model.global_transformer.layers.1.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 428 |
+
"vision_model.global_transformer.layers.1.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 429 |
+
"vision_model.global_transformer.layers.1.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 430 |
+
"vision_model.global_transformer.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 431 |
+
"vision_model.global_transformer.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 432 |
+
"vision_model.global_transformer.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 433 |
+
"vision_model.global_transformer.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 434 |
+
"vision_model.global_transformer.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 435 |
+
"vision_model.global_transformer.layers.2.gate_attn": "model-00001-of-00005.safetensors",
|
| 436 |
+
"vision_model.global_transformer.layers.2.gate_ffn": "model-00001-of-00005.safetensors",
|
| 437 |
+
"vision_model.global_transformer.layers.2.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 438 |
+
"vision_model.global_transformer.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 439 |
+
"vision_model.global_transformer.layers.2.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 440 |
+
"vision_model.global_transformer.layers.2.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 441 |
+
"vision_model.global_transformer.layers.2.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 442 |
+
"vision_model.global_transformer.layers.2.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 443 |
+
"vision_model.global_transformer.layers.2.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 444 |
+
"vision_model.global_transformer.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 445 |
+
"vision_model.global_transformer.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 446 |
+
"vision_model.global_transformer.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 447 |
+
"vision_model.global_transformer.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 448 |
+
"vision_model.global_transformer.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 449 |
+
"vision_model.global_transformer.layers.3.gate_attn": "model-00001-of-00005.safetensors",
|
| 450 |
+
"vision_model.global_transformer.layers.3.gate_ffn": "model-00001-of-00005.safetensors",
|
| 451 |
+
"vision_model.global_transformer.layers.3.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 452 |
+
"vision_model.global_transformer.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 453 |
+
"vision_model.global_transformer.layers.3.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 454 |
+
"vision_model.global_transformer.layers.3.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 455 |
+
"vision_model.global_transformer.layers.3.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 456 |
+
"vision_model.global_transformer.layers.3.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 457 |
+
"vision_model.global_transformer.layers.3.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 458 |
+
"vision_model.global_transformer.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 459 |
+
"vision_model.global_transformer.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 460 |
+
"vision_model.global_transformer.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 461 |
+
"vision_model.global_transformer.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 462 |
+
"vision_model.global_transformer.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 463 |
+
"vision_model.global_transformer.layers.4.gate_attn": "model-00001-of-00005.safetensors",
|
| 464 |
+
"vision_model.global_transformer.layers.4.gate_ffn": "model-00001-of-00005.safetensors",
|
| 465 |
+
"vision_model.global_transformer.layers.4.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 466 |
+
"vision_model.global_transformer.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 467 |
+
"vision_model.global_transformer.layers.4.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 468 |
+
"vision_model.global_transformer.layers.4.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 469 |
+
"vision_model.global_transformer.layers.4.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 470 |
+
"vision_model.global_transformer.layers.4.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 471 |
+
"vision_model.global_transformer.layers.4.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 472 |
+
"vision_model.global_transformer.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 473 |
+
"vision_model.global_transformer.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 474 |
+
"vision_model.global_transformer.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 475 |
+
"vision_model.global_transformer.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 476 |
+
"vision_model.global_transformer.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 477 |
+
"vision_model.global_transformer.layers.5.gate_attn": "model-00001-of-00005.safetensors",
|
| 478 |
+
"vision_model.global_transformer.layers.5.gate_ffn": "model-00001-of-00005.safetensors",
|
| 479 |
+
"vision_model.global_transformer.layers.5.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 480 |
+
"vision_model.global_transformer.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 481 |
+
"vision_model.global_transformer.layers.5.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 482 |
+
"vision_model.global_transformer.layers.5.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 483 |
+
"vision_model.global_transformer.layers.5.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 484 |
+
"vision_model.global_transformer.layers.5.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 485 |
+
"vision_model.global_transformer.layers.5.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 486 |
+
"vision_model.global_transformer.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 487 |
+
"vision_model.global_transformer.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 488 |
+
"vision_model.global_transformer.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 489 |
+
"vision_model.global_transformer.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 490 |
+
"vision_model.global_transformer.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 491 |
+
"vision_model.global_transformer.layers.6.gate_attn": "model-00001-of-00005.safetensors",
|
| 492 |
+
"vision_model.global_transformer.layers.6.gate_ffn": "model-00001-of-00005.safetensors",
|
| 493 |
+
"vision_model.global_transformer.layers.6.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 494 |
+
"vision_model.global_transformer.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 495 |
+
"vision_model.global_transformer.layers.6.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 496 |
+
"vision_model.global_transformer.layers.6.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 497 |
+
"vision_model.global_transformer.layers.6.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 498 |
+
"vision_model.global_transformer.layers.6.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 499 |
+
"vision_model.global_transformer.layers.6.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 500 |
+
"vision_model.global_transformer.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 501 |
+
"vision_model.global_transformer.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 502 |
+
"vision_model.global_transformer.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 503 |
+
"vision_model.global_transformer.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 504 |
+
"vision_model.global_transformer.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 505 |
+
"vision_model.global_transformer.layers.7.gate_attn": "model-00001-of-00005.safetensors",
|
| 506 |
+
"vision_model.global_transformer.layers.7.gate_ffn": "model-00001-of-00005.safetensors",
|
| 507 |
+
"vision_model.global_transformer.layers.7.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 508 |
+
"vision_model.global_transformer.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 509 |
+
"vision_model.global_transformer.layers.7.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 510 |
+
"vision_model.global_transformer.layers.7.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 511 |
+
"vision_model.global_transformer.layers.7.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 512 |
+
"vision_model.global_transformer.layers.7.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 513 |
+
"vision_model.global_transformer.layers.7.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 514 |
+
"vision_model.global_transformer.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 515 |
+
"vision_model.global_transformer.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 516 |
+
"vision_model.global_transformer.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 517 |
+
"vision_model.global_transformer.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 518 |
+
"vision_model.global_transformer.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 519 |
+
"vision_model.layernorm_post.bias": "model-00001-of-00005.safetensors",
|
| 520 |
+
"vision_model.layernorm_post.weight": "model-00001-of-00005.safetensors",
|
| 521 |
+
"vision_model.layernorm_pre.bias": "model-00001-of-00005.safetensors",
|
| 522 |
+
"vision_model.layernorm_pre.weight": "model-00001-of-00005.safetensors",
|
| 523 |
+
"vision_model.patch_embedding.weight": "model-00001-of-00005.safetensors",
|
| 524 |
+
"vision_model.post_tile_positional_embedding.embedding.weight": "model-00001-of-00005.safetensors",
|
| 525 |
+
"vision_model.post_tile_positional_embedding.gate": "model-00001-of-00005.safetensors",
|
| 526 |
+
"vision_model.pre_tile_positional_embedding.embedding.weight": "model-00001-of-00005.safetensors",
|
| 527 |
+
"vision_model.pre_tile_positional_embedding.gate": "model-00001-of-00005.safetensors",
|
| 528 |
+
"vision_model.transformer.layers.0.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 529 |
+
"vision_model.transformer.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 530 |
+
"vision_model.transformer.layers.0.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 531 |
+
"vision_model.transformer.layers.0.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 532 |
+
"vision_model.transformer.layers.0.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 533 |
+
"vision_model.transformer.layers.0.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 534 |
+
"vision_model.transformer.layers.0.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 535 |
+
"vision_model.transformer.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 536 |
+
"vision_model.transformer.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 537 |
+
"vision_model.transformer.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 538 |
+
"vision_model.transformer.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 539 |
+
"vision_model.transformer.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 540 |
+
"vision_model.transformer.layers.1.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 541 |
+
"vision_model.transformer.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 542 |
+
"vision_model.transformer.layers.1.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 543 |
+
"vision_model.transformer.layers.1.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 544 |
+
"vision_model.transformer.layers.1.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 545 |
+
"vision_model.transformer.layers.1.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 546 |
+
"vision_model.transformer.layers.1.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 547 |
+
"vision_model.transformer.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 548 |
+
"vision_model.transformer.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 549 |
+
"vision_model.transformer.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 550 |
+
"vision_model.transformer.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 551 |
+
"vision_model.transformer.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 552 |
+
"vision_model.transformer.layers.10.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 553 |
+
"vision_model.transformer.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 554 |
+
"vision_model.transformer.layers.10.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 555 |
+
"vision_model.transformer.layers.10.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 556 |
+
"vision_model.transformer.layers.10.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 557 |
+
"vision_model.transformer.layers.10.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 558 |
+
"vision_model.transformer.layers.10.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 559 |
+
"vision_model.transformer.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 560 |
+
"vision_model.transformer.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 561 |
+
"vision_model.transformer.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 562 |
+
"vision_model.transformer.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 563 |
+
"vision_model.transformer.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 564 |
+
"vision_model.transformer.layers.11.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 565 |
+
"vision_model.transformer.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 566 |
+
"vision_model.transformer.layers.11.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 567 |
+
"vision_model.transformer.layers.11.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 568 |
+
"vision_model.transformer.layers.11.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 569 |
+
"vision_model.transformer.layers.11.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 570 |
+
"vision_model.transformer.layers.11.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 571 |
+
"vision_model.transformer.layers.11.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 572 |
+
"vision_model.transformer.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 573 |
+
"vision_model.transformer.layers.11.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 574 |
+
"vision_model.transformer.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 575 |
+
"vision_model.transformer.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 576 |
+
"vision_model.transformer.layers.12.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 577 |
+
"vision_model.transformer.layers.12.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 578 |
+
"vision_model.transformer.layers.12.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 579 |
+
"vision_model.transformer.layers.12.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 580 |
+
"vision_model.transformer.layers.12.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 581 |
+
"vision_model.transformer.layers.12.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 582 |
+
"vision_model.transformer.layers.12.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 583 |
+
"vision_model.transformer.layers.12.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 584 |
+
"vision_model.transformer.layers.12.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 585 |
+
"vision_model.transformer.layers.12.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 586 |
+
"vision_model.transformer.layers.12.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 587 |
+
"vision_model.transformer.layers.12.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 588 |
+
"vision_model.transformer.layers.13.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 589 |
+
"vision_model.transformer.layers.13.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 590 |
+
"vision_model.transformer.layers.13.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 591 |
+
"vision_model.transformer.layers.13.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 592 |
+
"vision_model.transformer.layers.13.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 593 |
+
"vision_model.transformer.layers.13.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 594 |
+
"vision_model.transformer.layers.13.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 595 |
+
"vision_model.transformer.layers.13.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 596 |
+
"vision_model.transformer.layers.13.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 597 |
+
"vision_model.transformer.layers.13.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 598 |
+
"vision_model.transformer.layers.13.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 599 |
+
"vision_model.transformer.layers.13.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 600 |
+
"vision_model.transformer.layers.14.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 601 |
+
"vision_model.transformer.layers.14.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 602 |
+
"vision_model.transformer.layers.14.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 603 |
+
"vision_model.transformer.layers.14.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 604 |
+
"vision_model.transformer.layers.14.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 605 |
+
"vision_model.transformer.layers.14.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 606 |
+
"vision_model.transformer.layers.14.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 607 |
+
"vision_model.transformer.layers.14.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 608 |
+
"vision_model.transformer.layers.14.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 609 |
+
"vision_model.transformer.layers.14.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 610 |
+
"vision_model.transformer.layers.14.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 611 |
+
"vision_model.transformer.layers.14.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 612 |
+
"vision_model.transformer.layers.15.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 613 |
+
"vision_model.transformer.layers.15.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 614 |
+
"vision_model.transformer.layers.15.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 615 |
+
"vision_model.transformer.layers.15.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 616 |
+
"vision_model.transformer.layers.15.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 617 |
+
"vision_model.transformer.layers.15.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 618 |
+
"vision_model.transformer.layers.15.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 619 |
+
"vision_model.transformer.layers.15.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 620 |
+
"vision_model.transformer.layers.15.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 621 |
+
"vision_model.transformer.layers.15.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 622 |
+
"vision_model.transformer.layers.15.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 623 |
+
"vision_model.transformer.layers.15.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 624 |
+
"vision_model.transformer.layers.16.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 625 |
+
"vision_model.transformer.layers.16.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 626 |
+
"vision_model.transformer.layers.16.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 627 |
+
"vision_model.transformer.layers.16.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 628 |
+
"vision_model.transformer.layers.16.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 629 |
+
"vision_model.transformer.layers.16.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 630 |
+
"vision_model.transformer.layers.16.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 631 |
+
"vision_model.transformer.layers.16.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 632 |
+
"vision_model.transformer.layers.16.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 633 |
+
"vision_model.transformer.layers.16.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 634 |
+
"vision_model.transformer.layers.16.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 635 |
+
"vision_model.transformer.layers.16.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 636 |
+
"vision_model.transformer.layers.17.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 637 |
+
"vision_model.transformer.layers.17.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 638 |
+
"vision_model.transformer.layers.17.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 639 |
+
"vision_model.transformer.layers.17.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 640 |
+
"vision_model.transformer.layers.17.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 641 |
+
"vision_model.transformer.layers.17.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 642 |
+
"vision_model.transformer.layers.17.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 643 |
+
"vision_model.transformer.layers.17.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 644 |
+
"vision_model.transformer.layers.17.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 645 |
+
"vision_model.transformer.layers.17.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 646 |
+
"vision_model.transformer.layers.17.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 647 |
+
"vision_model.transformer.layers.17.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 648 |
+
"vision_model.transformer.layers.18.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 649 |
+
"vision_model.transformer.layers.18.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 650 |
+
"vision_model.transformer.layers.18.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 651 |
+
"vision_model.transformer.layers.18.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 652 |
+
"vision_model.transformer.layers.18.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 653 |
+
"vision_model.transformer.layers.18.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 654 |
+
"vision_model.transformer.layers.18.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 655 |
+
"vision_model.transformer.layers.18.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 656 |
+
"vision_model.transformer.layers.18.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 657 |
+
"vision_model.transformer.layers.18.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 658 |
+
"vision_model.transformer.layers.18.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 659 |
+
"vision_model.transformer.layers.18.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 660 |
+
"vision_model.transformer.layers.19.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 661 |
+
"vision_model.transformer.layers.19.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 662 |
+
"vision_model.transformer.layers.19.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 663 |
+
"vision_model.transformer.layers.19.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 664 |
+
"vision_model.transformer.layers.19.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 665 |
+
"vision_model.transformer.layers.19.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 666 |
+
"vision_model.transformer.layers.19.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 667 |
+
"vision_model.transformer.layers.19.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 668 |
+
"vision_model.transformer.layers.19.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 669 |
+
"vision_model.transformer.layers.19.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 670 |
+
"vision_model.transformer.layers.19.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 671 |
+
"vision_model.transformer.layers.19.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 672 |
+
"vision_model.transformer.layers.2.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 673 |
+
"vision_model.transformer.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 674 |
+
"vision_model.transformer.layers.2.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 675 |
+
"vision_model.transformer.layers.2.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 676 |
+
"vision_model.transformer.layers.2.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 677 |
+
"vision_model.transformer.layers.2.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 678 |
+
"vision_model.transformer.layers.2.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 679 |
+
"vision_model.transformer.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 680 |
+
"vision_model.transformer.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 681 |
+
"vision_model.transformer.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 682 |
+
"vision_model.transformer.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 683 |
+
"vision_model.transformer.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 684 |
+
"vision_model.transformer.layers.20.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 685 |
+
"vision_model.transformer.layers.20.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 686 |
+
"vision_model.transformer.layers.20.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 687 |
+
"vision_model.transformer.layers.20.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 688 |
+
"vision_model.transformer.layers.20.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 689 |
+
"vision_model.transformer.layers.20.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 690 |
+
"vision_model.transformer.layers.20.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 691 |
+
"vision_model.transformer.layers.20.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 692 |
+
"vision_model.transformer.layers.20.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 693 |
+
"vision_model.transformer.layers.20.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 694 |
+
"vision_model.transformer.layers.20.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 695 |
+
"vision_model.transformer.layers.20.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 696 |
+
"vision_model.transformer.layers.21.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 697 |
+
"vision_model.transformer.layers.21.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 698 |
+
"vision_model.transformer.layers.21.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 699 |
+
"vision_model.transformer.layers.21.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 700 |
+
"vision_model.transformer.layers.21.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 701 |
+
"vision_model.transformer.layers.21.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 702 |
+
"vision_model.transformer.layers.21.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 703 |
+
"vision_model.transformer.layers.21.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 704 |
+
"vision_model.transformer.layers.21.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 705 |
+
"vision_model.transformer.layers.21.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 706 |
+
"vision_model.transformer.layers.21.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 707 |
+
"vision_model.transformer.layers.21.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 708 |
+
"vision_model.transformer.layers.22.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 709 |
+
"vision_model.transformer.layers.22.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 710 |
+
"vision_model.transformer.layers.22.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 711 |
+
"vision_model.transformer.layers.22.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 712 |
+
"vision_model.transformer.layers.22.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 713 |
+
"vision_model.transformer.layers.22.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 714 |
+
"vision_model.transformer.layers.22.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 715 |
+
"vision_model.transformer.layers.22.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 716 |
+
"vision_model.transformer.layers.22.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 717 |
+
"vision_model.transformer.layers.22.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 718 |
+
"vision_model.transformer.layers.22.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 719 |
+
"vision_model.transformer.layers.22.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 720 |
+
"vision_model.transformer.layers.23.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 721 |
+
"vision_model.transformer.layers.23.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 722 |
+
"vision_model.transformer.layers.23.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 723 |
+
"vision_model.transformer.layers.23.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 724 |
+
"vision_model.transformer.layers.23.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 725 |
+
"vision_model.transformer.layers.23.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 726 |
+
"vision_model.transformer.layers.23.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 727 |
+
"vision_model.transformer.layers.23.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 728 |
+
"vision_model.transformer.layers.23.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 729 |
+
"vision_model.transformer.layers.23.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 730 |
+
"vision_model.transformer.layers.23.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 731 |
+
"vision_model.transformer.layers.23.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 732 |
+
"vision_model.transformer.layers.24.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 733 |
+
"vision_model.transformer.layers.24.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 734 |
+
"vision_model.transformer.layers.24.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 735 |
+
"vision_model.transformer.layers.24.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 736 |
+
"vision_model.transformer.layers.24.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 737 |
+
"vision_model.transformer.layers.24.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 738 |
+
"vision_model.transformer.layers.24.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 739 |
+
"vision_model.transformer.layers.24.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 740 |
+
"vision_model.transformer.layers.24.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 741 |
+
"vision_model.transformer.layers.24.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 742 |
+
"vision_model.transformer.layers.24.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 743 |
+
"vision_model.transformer.layers.24.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 744 |
+
"vision_model.transformer.layers.25.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 745 |
+
"vision_model.transformer.layers.25.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 746 |
+
"vision_model.transformer.layers.25.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 747 |
+
"vision_model.transformer.layers.25.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 748 |
+
"vision_model.transformer.layers.25.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 749 |
+
"vision_model.transformer.layers.25.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 750 |
+
"vision_model.transformer.layers.25.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 751 |
+
"vision_model.transformer.layers.25.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 752 |
+
"vision_model.transformer.layers.25.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 753 |
+
"vision_model.transformer.layers.25.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 754 |
+
"vision_model.transformer.layers.25.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 755 |
+
"vision_model.transformer.layers.25.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 756 |
+
"vision_model.transformer.layers.26.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 757 |
+
"vision_model.transformer.layers.26.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 758 |
+
"vision_model.transformer.layers.26.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 759 |
+
"vision_model.transformer.layers.26.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 760 |
+
"vision_model.transformer.layers.26.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 761 |
+
"vision_model.transformer.layers.26.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 762 |
+
"vision_model.transformer.layers.26.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 763 |
+
"vision_model.transformer.layers.26.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 764 |
+
"vision_model.transformer.layers.26.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 765 |
+
"vision_model.transformer.layers.26.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 766 |
+
"vision_model.transformer.layers.26.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 767 |
+
"vision_model.transformer.layers.26.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 768 |
+
"vision_model.transformer.layers.27.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 769 |
+
"vision_model.transformer.layers.27.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 770 |
+
"vision_model.transformer.layers.27.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 771 |
+
"vision_model.transformer.layers.27.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 772 |
+
"vision_model.transformer.layers.27.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 773 |
+
"vision_model.transformer.layers.27.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 774 |
+
"vision_model.transformer.layers.27.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 775 |
+
"vision_model.transformer.layers.27.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 776 |
+
"vision_model.transformer.layers.27.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 777 |
+
"vision_model.transformer.layers.27.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 778 |
+
"vision_model.transformer.layers.27.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 779 |
+
"vision_model.transformer.layers.27.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 780 |
+
"vision_model.transformer.layers.28.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 781 |
+
"vision_model.transformer.layers.28.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 782 |
+
"vision_model.transformer.layers.28.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 783 |
+
"vision_model.transformer.layers.28.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 784 |
+
"vision_model.transformer.layers.28.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 785 |
+
"vision_model.transformer.layers.28.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 786 |
+
"vision_model.transformer.layers.28.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 787 |
+
"vision_model.transformer.layers.28.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 788 |
+
"vision_model.transformer.layers.28.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 789 |
+
"vision_model.transformer.layers.28.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 790 |
+
"vision_model.transformer.layers.28.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 791 |
+
"vision_model.transformer.layers.28.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 792 |
+
"vision_model.transformer.layers.29.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 793 |
+
"vision_model.transformer.layers.29.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 794 |
+
"vision_model.transformer.layers.29.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 795 |
+
"vision_model.transformer.layers.29.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 796 |
+
"vision_model.transformer.layers.29.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 797 |
+
"vision_model.transformer.layers.29.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 798 |
+
"vision_model.transformer.layers.29.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 799 |
+
"vision_model.transformer.layers.29.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 800 |
+
"vision_model.transformer.layers.29.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 801 |
+
"vision_model.transformer.layers.29.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 802 |
+
"vision_model.transformer.layers.29.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 803 |
+
"vision_model.transformer.layers.29.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 804 |
+
"vision_model.transformer.layers.3.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 805 |
+
"vision_model.transformer.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 806 |
+
"vision_model.transformer.layers.3.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 807 |
+
"vision_model.transformer.layers.3.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 808 |
+
"vision_model.transformer.layers.3.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 809 |
+
"vision_model.transformer.layers.3.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 810 |
+
"vision_model.transformer.layers.3.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 811 |
+
"vision_model.transformer.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 812 |
+
"vision_model.transformer.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 813 |
+
"vision_model.transformer.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 814 |
+
"vision_model.transformer.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 815 |
+
"vision_model.transformer.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 816 |
+
"vision_model.transformer.layers.30.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 817 |
+
"vision_model.transformer.layers.30.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 818 |
+
"vision_model.transformer.layers.30.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 819 |
+
"vision_model.transformer.layers.30.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 820 |
+
"vision_model.transformer.layers.30.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 821 |
+
"vision_model.transformer.layers.30.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 822 |
+
"vision_model.transformer.layers.30.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 823 |
+
"vision_model.transformer.layers.30.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 824 |
+
"vision_model.transformer.layers.30.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 825 |
+
"vision_model.transformer.layers.30.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 826 |
+
"vision_model.transformer.layers.30.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 827 |
+
"vision_model.transformer.layers.30.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 828 |
+
"vision_model.transformer.layers.31.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 829 |
+
"vision_model.transformer.layers.31.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 830 |
+
"vision_model.transformer.layers.31.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 831 |
+
"vision_model.transformer.layers.31.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 832 |
+
"vision_model.transformer.layers.31.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 833 |
+
"vision_model.transformer.layers.31.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 834 |
+
"vision_model.transformer.layers.31.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 835 |
+
"vision_model.transformer.layers.31.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 836 |
+
"vision_model.transformer.layers.31.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 837 |
+
"vision_model.transformer.layers.31.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 838 |
+
"vision_model.transformer.layers.31.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 839 |
+
"vision_model.transformer.layers.31.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 840 |
+
"vision_model.transformer.layers.4.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 841 |
+
"vision_model.transformer.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 842 |
+
"vision_model.transformer.layers.4.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 843 |
+
"vision_model.transformer.layers.4.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 844 |
+
"vision_model.transformer.layers.4.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 845 |
+
"vision_model.transformer.layers.4.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 846 |
+
"vision_model.transformer.layers.4.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 847 |
+
"vision_model.transformer.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 848 |
+
"vision_model.transformer.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 849 |
+
"vision_model.transformer.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 850 |
+
"vision_model.transformer.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 851 |
+
"vision_model.transformer.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 852 |
+
"vision_model.transformer.layers.5.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 853 |
+
"vision_model.transformer.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 854 |
+
"vision_model.transformer.layers.5.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 855 |
+
"vision_model.transformer.layers.5.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 856 |
+
"vision_model.transformer.layers.5.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 857 |
+
"vision_model.transformer.layers.5.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 858 |
+
"vision_model.transformer.layers.5.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 859 |
+
"vision_model.transformer.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 860 |
+
"vision_model.transformer.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 861 |
+
"vision_model.transformer.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 862 |
+
"vision_model.transformer.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 863 |
+
"vision_model.transformer.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 864 |
+
"vision_model.transformer.layers.6.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 865 |
+
"vision_model.transformer.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 866 |
+
"vision_model.transformer.layers.6.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 867 |
+
"vision_model.transformer.layers.6.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 868 |
+
"vision_model.transformer.layers.6.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 869 |
+
"vision_model.transformer.layers.6.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 870 |
+
"vision_model.transformer.layers.6.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 871 |
+
"vision_model.transformer.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 872 |
+
"vision_model.transformer.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 873 |
+
"vision_model.transformer.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 874 |
+
"vision_model.transformer.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 875 |
+
"vision_model.transformer.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 876 |
+
"vision_model.transformer.layers.7.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 877 |
+
"vision_model.transformer.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 878 |
+
"vision_model.transformer.layers.7.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 879 |
+
"vision_model.transformer.layers.7.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 880 |
+
"vision_model.transformer.layers.7.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 881 |
+
"vision_model.transformer.layers.7.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 882 |
+
"vision_model.transformer.layers.7.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 883 |
+
"vision_model.transformer.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 884 |
+
"vision_model.transformer.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 885 |
+
"vision_model.transformer.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 886 |
+
"vision_model.transformer.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 887 |
+
"vision_model.transformer.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 888 |
+
"vision_model.transformer.layers.8.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 889 |
+
"vision_model.transformer.layers.8.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 890 |
+
"vision_model.transformer.layers.8.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 891 |
+
"vision_model.transformer.layers.8.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 892 |
+
"vision_model.transformer.layers.8.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 893 |
+
"vision_model.transformer.layers.8.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 894 |
+
"vision_model.transformer.layers.8.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 895 |
+
"vision_model.transformer.layers.8.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 896 |
+
"vision_model.transformer.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 897 |
+
"vision_model.transformer.layers.8.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 898 |
+
"vision_model.transformer.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 899 |
+
"vision_model.transformer.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 900 |
+
"vision_model.transformer.layers.9.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 901 |
+
"vision_model.transformer.layers.9.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 902 |
+
"vision_model.transformer.layers.9.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
| 903 |
+
"vision_model.transformer.layers.9.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
| 904 |
+
"vision_model.transformer.layers.9.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
| 905 |
+
"vision_model.transformer.layers.9.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
| 906 |
+
"vision_model.transformer.layers.9.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
| 907 |
+
"vision_model.transformer.layers.9.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 908 |
+
"vision_model.transformer.layers.9.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 909 |
+
"vision_model.transformer.layers.9.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 910 |
+
"vision_model.transformer.layers.9.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 911 |
+
"vision_model.transformer.layers.9.self_attn.v_proj.weight": "model-00001-of-00005.safetensors"
|
| 912 |
+
}
|
| 913 |
+
}
|
modeling_llama3.py
ADDED
|
@@ -0,0 +1,287 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# coding=utf-8
|
| 2 |
+
from typing import List, Optional, Tuple, Union
|
| 3 |
+
|
| 4 |
+
import torch
|
| 5 |
+
import torch.utils.checkpoint
|
| 6 |
+
from torch import nn
|
| 7 |
+
|
| 8 |
+
from transformers import MllamaPreTrainedModel, MllamaVisionModel, MllamaForCausalLM
|
| 9 |
+
from transformers.generation import GenerationMixin
|
| 10 |
+
from transformers.modeling_outputs import CausalLMOutputWithPast
|
| 11 |
+
from transformers.utils import logging
|
| 12 |
+
from transformers.models.mllama.modeling_mllama import _prepare_cross_attention_mask
|
| 13 |
+
from configuration_llama3 import Llama3Config
|
| 14 |
+
from mllama_audio_model import MllamaAudioModel
|
| 15 |
+
|
| 16 |
+
logger = logging.get_logger(__name__)
|
| 17 |
+
|
| 18 |
+
class Llama3PreTrainedModel(MllamaPreTrainedModel):
|
| 19 |
+
config_class = Llama3Config
|
| 20 |
+
base_model_prefix = "model"
|
| 21 |
+
|
| 22 |
+
class Llama3ForConditionalGeneration(Llama3PreTrainedModel, GenerationMixin):
|
| 23 |
+
_supports_quantized_cache = False # quant cache not supported in encoder-decoder setting
|
| 24 |
+
|
| 25 |
+
def __init__(self, config: Llama3Config):
|
| 26 |
+
super().__init__(config)
|
| 27 |
+
self.vocab_size = config.text_config.vocab_size
|
| 28 |
+
self.hidden_size = config.text_config.hidden_size
|
| 29 |
+
self.max_num_tiles = config.vision_config.max_num_tiles
|
| 30 |
+
self.vision_output_dim = config.vision_config.vision_output_dim
|
| 31 |
+
self.pad_token_id = self.config.pad_token_id if self.config.pad_token_id is not None else -1
|
| 32 |
+
|
| 33 |
+
self.vision_model = MllamaVisionModel._from_config(config.vision_config)
|
| 34 |
+
self.language_model = MllamaForCausalLM._from_config(config.text_config)
|
| 35 |
+
self.audio_model = MllamaAudioModel(config.audio_config, self.language_model.get_input_embeddings())
|
| 36 |
+
self.multi_modal_projector = nn.Linear(
|
| 37 |
+
config.vision_config.vision_output_dim,
|
| 38 |
+
config.text_config.hidden_size,
|
| 39 |
+
bias=True,
|
| 40 |
+
)
|
| 41 |
+
self.post_init()
|
| 42 |
+
|
| 43 |
+
def get_input_embeddings(self):
|
| 44 |
+
return self.language_model.get_input_embeddings()
|
| 45 |
+
|
| 46 |
+
def set_input_embeddings(self, value):
|
| 47 |
+
self.language_model.set_input_embeddings(value)
|
| 48 |
+
|
| 49 |
+
def get_output_embeddings(self):
|
| 50 |
+
return self.language_model.get_output_embeddings()
|
| 51 |
+
|
| 52 |
+
def set_output_embeddings(self, new_embeddings):
|
| 53 |
+
self.language_model.set_output_embeddings(new_embeddings)
|
| 54 |
+
|
| 55 |
+
def set_decoder(self, decoder):
|
| 56 |
+
self.language_model.set_decoder(decoder)
|
| 57 |
+
|
| 58 |
+
def get_decoder(self):
|
| 59 |
+
return self.language_model.get_decoder()
|
| 60 |
+
|
| 61 |
+
def tie_weights(self):
|
| 62 |
+
return self.language_model.tie_weights()
|
| 63 |
+
|
| 64 |
+
def forward(
|
| 65 |
+
self,
|
| 66 |
+
input_ids: Optional[torch.LongTensor] = None,
|
| 67 |
+
audio_features: Optional[torch.FloatTensor] = None,
|
| 68 |
+
pixel_values: Optional[torch.FloatTensor] = None,
|
| 69 |
+
aspect_ratio_mask: Optional[torch.Tensor] = None,
|
| 70 |
+
aspect_ratio_ids: Optional[torch.Tensor] = None,
|
| 71 |
+
attention_mask: Optional[torch.Tensor] = None,
|
| 72 |
+
cross_attention_mask: Optional[torch.Tensor] = None,
|
| 73 |
+
cross_attention_states: Optional[torch.Tensor] = None,
|
| 74 |
+
position_ids: Optional[torch.LongTensor] = None,
|
| 75 |
+
past_key_values: Optional[List[torch.FloatTensor]] = None,
|
| 76 |
+
inputs_embeds: Optional[torch.FloatTensor] = None,
|
| 77 |
+
labels: Optional[torch.LongTensor] = None,
|
| 78 |
+
use_cache: Optional[bool] = None,
|
| 79 |
+
output_attentions: Optional[bool] = None,
|
| 80 |
+
output_hidden_states: Optional[bool] = None,
|
| 81 |
+
return_dict: Optional[bool] = None,
|
| 82 |
+
cache_position: Optional[torch.LongTensor] = None,
|
| 83 |
+
num_logits_to_keep: int = 0,
|
| 84 |
+
) -> Union[Tuple, CausalLMOutputWithPast]:
|
| 85 |
+
r"""
|
| 86 |
+
Args:
|
| 87 |
+
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
|
| 88 |
+
Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
|
| 89 |
+
config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
|
| 90 |
+
(masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.
|
| 91 |
+
|
| 92 |
+
num_logits_to_keep (`int`, *optional*):
|
| 93 |
+
Calculate logits for the last `num_logits_to_keep` tokens. If `0`, calculate logits for all
|
| 94 |
+
`input_ids` (special case). Only last token logits are needed for generation, and calculating them only for that
|
| 95 |
+
token can save memory, which becomes pretty significant for long sequences or large vocabulary size.
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
Returns:
|
| 99 |
+
|
| 100 |
+
Example:
|
| 101 |
+
|
| 102 |
+
```python
|
| 103 |
+
>>> from PIL import Image
|
| 104 |
+
>>> import requests
|
| 105 |
+
>>> from transformers import AutoProcessor, MllamaForConditionalGeneration
|
| 106 |
+
|
| 107 |
+
>>> checkpoint = "meta-llama/Llama-3.2-11B-Vision"
|
| 108 |
+
>>> model = MllamaForConditionalGeneration.from_pretrained(checkpoint)
|
| 109 |
+
>>> processor = AutoProcessor.from_pretrained(checkpoint)
|
| 110 |
+
|
| 111 |
+
>>> prompt = "<|image|>If I had to write a haiku for this one"
|
| 112 |
+
>>> url = "https://www.ilankelman.org/stopsigns/australia.jpg"
|
| 113 |
+
>>> image = Image.open(requests.get(url, stream=True).raw)
|
| 114 |
+
|
| 115 |
+
>>> inputs = processor(text=prompt, images=image, return_tensors="pt")
|
| 116 |
+
|
| 117 |
+
>>> # Generate
|
| 118 |
+
>>> output = model.generate(**inputs, max_new_tokens=15)
|
| 119 |
+
|
| 120 |
+
>>> prompt_len = inputs.input_ids.shape[-1]
|
| 121 |
+
>>> generated_ids = output[:, prompt_len:]
|
| 122 |
+
>>> generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)
|
| 123 |
+
>>> print(generated_text)
|
| 124 |
+
[', it would be:.\\nA stop sign in Chinatown.\\n']
|
| 125 |
+
```
|
| 126 |
+
"""
|
| 127 |
+
output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
|
| 128 |
+
output_hidden_states = (
|
| 129 |
+
output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
|
| 130 |
+
)
|
| 131 |
+
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
|
| 132 |
+
|
| 133 |
+
if (input_ids is None) ^ (inputs_embeds is not None):
|
| 134 |
+
raise ValueError("You must specify exactly one of input_ids or inputs_embeds")
|
| 135 |
+
|
| 136 |
+
if pixel_values is not None and inputs_embeds is not None:
|
| 137 |
+
raise ValueError(
|
| 138 |
+
"You cannot specify both pixel_values and inputs_embeds at the same time, and must specify either one"
|
| 139 |
+
)
|
| 140 |
+
|
| 141 |
+
if pixel_values is not None and cross_attention_states is not None:
|
| 142 |
+
raise ValueError("`pixel_values` and `cross_attention_states` cannot be provided simultaneously")
|
| 143 |
+
|
| 144 |
+
if pixel_values is not None:
|
| 145 |
+
if aspect_ratio_ids is None:
|
| 146 |
+
raise ValueError("`aspect_ratio_ids` must be provided if `pixel_values` is provided")
|
| 147 |
+
# get vision tokens from vision model
|
| 148 |
+
vision_outputs = self.vision_model(
|
| 149 |
+
pixel_values=pixel_values,
|
| 150 |
+
aspect_ratio_ids=aspect_ratio_ids,
|
| 151 |
+
aspect_ratio_mask=aspect_ratio_mask,
|
| 152 |
+
output_hidden_states=output_hidden_states,
|
| 153 |
+
output_attentions=output_attentions,
|
| 154 |
+
return_dict=return_dict,
|
| 155 |
+
)
|
| 156 |
+
cross_attention_states = vision_outputs[0]
|
| 157 |
+
cross_attention_states = self.multi_modal_projector(cross_attention_states).reshape(
|
| 158 |
+
-1, cross_attention_states.shape[-2], self.hidden_size
|
| 159 |
+
)
|
| 160 |
+
|
| 161 |
+
if cross_attention_mask is not None:
|
| 162 |
+
cross_attention_mask, full_text_row_masked_out_mask = _prepare_cross_attention_mask(
|
| 163 |
+
cross_attention_mask,
|
| 164 |
+
num_vision_tokens=self.vision_model.num_patches,
|
| 165 |
+
dtype=self.dtype,
|
| 166 |
+
)
|
| 167 |
+
else:
|
| 168 |
+
full_text_row_masked_out_mask = None
|
| 169 |
+
|
| 170 |
+
if cross_attention_mask is not None and cache_position is not None:
|
| 171 |
+
cross_attention_mask = cross_attention_mask[:, :, cache_position]
|
| 172 |
+
full_text_row_masked_out_mask = full_text_row_masked_out_mask[:, :, cache_position]
|
| 173 |
+
|
| 174 |
+
if audio_features is not None:
|
| 175 |
+
if input_ids is None:
|
| 176 |
+
raise ValueError("You must provide `input_ids` if you pass `audio_features`.")
|
| 177 |
+
|
| 178 |
+
inputs_embeds = self.audio_model(
|
| 179 |
+
audio_feature=audio_features,
|
| 180 |
+
input_ids=input_ids,
|
| 181 |
+
return_dict=False,
|
| 182 |
+
)
|
| 183 |
+
input_ids = None
|
| 184 |
+
|
| 185 |
+
outputs = self.language_model(
|
| 186 |
+
input_ids=input_ids,
|
| 187 |
+
attention_mask=attention_mask,
|
| 188 |
+
position_ids=position_ids,
|
| 189 |
+
cross_attention_states=cross_attention_states,
|
| 190 |
+
cross_attention_mask=cross_attention_mask,
|
| 191 |
+
full_text_row_masked_out_mask=full_text_row_masked_out_mask,
|
| 192 |
+
past_key_values=past_key_values,
|
| 193 |
+
use_cache=use_cache,
|
| 194 |
+
inputs_embeds=inputs_embeds,
|
| 195 |
+
labels=labels,
|
| 196 |
+
output_hidden_states=output_hidden_states,
|
| 197 |
+
output_attentions=output_attentions,
|
| 198 |
+
return_dict=return_dict,
|
| 199 |
+
cache_position=cache_position,
|
| 200 |
+
num_logits_to_keep=num_logits_to_keep,
|
| 201 |
+
)
|
| 202 |
+
|
| 203 |
+
return outputs
|
| 204 |
+
|
| 205 |
+
def prepare_inputs_for_generation(
|
| 206 |
+
self,
|
| 207 |
+
input_ids=None,
|
| 208 |
+
inputs_embeds=None,
|
| 209 |
+
attention_mask=None,
|
| 210 |
+
position_ids=None,
|
| 211 |
+
pixel_values=None,
|
| 212 |
+
aspect_ratio_ids=None,
|
| 213 |
+
aspect_ratio_mask=None,
|
| 214 |
+
cross_attention_mask=None,
|
| 215 |
+
past_key_values=None,
|
| 216 |
+
use_cache=False,
|
| 217 |
+
cache_position=None,
|
| 218 |
+
num_logits_to_keep=None,
|
| 219 |
+
**kwargs,
|
| 220 |
+
):
|
| 221 |
+
# Overwritten -- in specific circumstances we don't want to forward image inputs to the model
|
| 222 |
+
|
| 223 |
+
# If we have cache: let's slice `input_ids` through `cache_position`, to keep only the unprocessed tokens
|
| 224 |
+
# Exception 1: when passing input_embeds, input_ids may be missing entries
|
| 225 |
+
# Exception 2: some generation methods do special slicing of input_ids, so we don't need to do it here
|
| 226 |
+
if past_key_values is not None:
|
| 227 |
+
if inputs_embeds is not None: # Exception 1
|
| 228 |
+
input_ids = input_ids[:, -cache_position.shape[0] :]
|
| 229 |
+
elif input_ids.shape[1] != cache_position.shape[0]: # Default case (the "else", a no op, is Exception 2)
|
| 230 |
+
input_ids = input_ids[:, cache_position]
|
| 231 |
+
|
| 232 |
+
# TODO: we have no attention_mask so this won't work, check if we really won't need attention mask and find another way
|
| 233 |
+
if attention_mask is not None and position_ids is None:
|
| 234 |
+
# create position_ids on the fly for batch generation
|
| 235 |
+
position_ids = attention_mask.long().cumsum(-1) - 1
|
| 236 |
+
position_ids.masked_fill_(attention_mask == 0, 1)
|
| 237 |
+
if past_key_values:
|
| 238 |
+
position_ids = position_ids[:, -input_ids.shape[1] :]
|
| 239 |
+
|
| 240 |
+
# This `clone` call is needed to avoid recapturing cuda graphs with `torch.compile`'s `mode="reduce-overhead`, as otherwise the input `position_ids` would have various stride during the decoding. Here, simply using `.contiguous()` is not sufficient as in the batch size = 1 case, `position_ids` is already contiguous but with varying stride which retriggers a capture.
|
| 241 |
+
position_ids = position_ids.clone(memory_format=torch.contiguous_format)
|
| 242 |
+
|
| 243 |
+
# if `inputs_embeds` are passed, we only want to use them in the 1st generation step
|
| 244 |
+
if inputs_embeds is not None and cache_position[0] == 0:
|
| 245 |
+
model_inputs = {"inputs_embeds": inputs_embeds, "input_ids": None}
|
| 246 |
+
else:
|
| 247 |
+
# The clone here is for the same reason as for `position_ids`.
|
| 248 |
+
model_inputs = {"input_ids": input_ids.clone(memory_format=torch.contiguous_format), "inputs_embeds": None}
|
| 249 |
+
|
| 250 |
+
if num_logits_to_keep is not None:
|
| 251 |
+
model_inputs["num_logits_to_keep"] = num_logits_to_keep
|
| 252 |
+
|
| 253 |
+
model_inputs.update(
|
| 254 |
+
{
|
| 255 |
+
"position_ids": position_ids,
|
| 256 |
+
"cache_position": cache_position,
|
| 257 |
+
"past_key_values": past_key_values,
|
| 258 |
+
"use_cache": use_cache,
|
| 259 |
+
"attention_mask": attention_mask,
|
| 260 |
+
"cross_attention_mask": cross_attention_mask,
|
| 261 |
+
}
|
| 262 |
+
)
|
| 263 |
+
|
| 264 |
+
# If we're in pre-fill or cacheless decoding step, then we need pixel_values and aspect ratios
|
| 265 |
+
# to compute image hidden states, otherwise they are cached within each cross attn layer
|
| 266 |
+
if cache_position[0] == 0:
|
| 267 |
+
model_inputs["pixel_values"] = pixel_values
|
| 268 |
+
model_inputs["aspect_ratio_ids"] = aspect_ratio_ids
|
| 269 |
+
model_inputs["aspect_ratio_mask"] = aspect_ratio_mask
|
| 270 |
+
|
| 271 |
+
return model_inputs
|
| 272 |
+
|
| 273 |
+
def _update_model_kwargs_for_generation(self, outputs, model_kwargs, is_encoder_decoder, **kwargs):
|
| 274 |
+
cross_attention_mask_prev = model_kwargs.get("cross_attention_mask", None)
|
| 275 |
+
model_kwargs = super()._update_model_kwargs_for_generation(
|
| 276 |
+
outputs=outputs,
|
| 277 |
+
model_kwargs=model_kwargs,
|
| 278 |
+
is_encoder_decoder=is_encoder_decoder,
|
| 279 |
+
**kwargs,
|
| 280 |
+
)
|
| 281 |
+
|
| 282 |
+
# add cross-attn mask for new token
|
| 283 |
+
if cross_attention_mask_prev is not None:
|
| 284 |
+
model_kwargs["cross_attention_mask"] = torch.cat(
|
| 285 |
+
[cross_attention_mask_prev, cross_attention_mask_prev[:, -1:, ...]], dim=1
|
| 286 |
+
)
|
| 287 |
+
return model_kwargs
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_pad": true,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.48145466,
|
| 9 |
+
0.4578275,
|
| 10 |
+
0.40821073
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "MllamaImageProcessor",
|
| 13 |
+
"image_std": [
|
| 14 |
+
0.26862954,
|
| 15 |
+
0.26130258,
|
| 16 |
+
0.27577711
|
| 17 |
+
],
|
| 18 |
+
"max_image_tiles": 4,
|
| 19 |
+
"resample": 2,
|
| 20 |
+
"rescale_factor": 0.00392156862745098,
|
| 21 |
+
"size": {
|
| 22 |
+
"height": 560,
|
| 23 |
+
"width": 560
|
| 24 |
+
}
|
| 25 |
+
}
|
processing_mllama.py
ADDED
|
@@ -0,0 +1,365 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# coding=utf-8
|
| 2 |
+
# Copyright 2024 The HuggingFace Inc. team.
|
| 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 |
+
"""Processor class for Mllama."""
|
| 17 |
+
|
| 18 |
+
from typing import List, Optional, Union
|
| 19 |
+
|
| 20 |
+
import numpy as np
|
| 21 |
+
|
| 22 |
+
from transformers.feature_extraction_utils import BatchFeature
|
| 23 |
+
from transformers.image_utils import ImageInput
|
| 24 |
+
from transformers.processing_utils import ImagesKwargs, ProcessingKwargs, ProcessorMixin, Unpack, AudioKwargs
|
| 25 |
+
from transformers.tokenization_utils_base import (
|
| 26 |
+
PreTokenizedInput,
|
| 27 |
+
TextInput,
|
| 28 |
+
AudioInput,
|
| 29 |
+
)
|
| 30 |
+
|
| 31 |
+
# TODO: Can we do it that way or its better include as "Copied from ..."
|
| 32 |
+
from transformers.models.mllama.image_processing_mllama import make_list_of_images
|
| 33 |
+
from .audio_processing_mllama import make_list_of_audio_clips, build_audio_tokens, pack_audio_clips
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
class MllamaImagesKwargs(ImagesKwargs, total=False):
|
| 37 |
+
max_image_tiles: Optional[int]
|
| 38 |
+
|
| 39 |
+
class MllamaProcessorKwargs(ProcessingKwargs, total=False):
|
| 40 |
+
images_kwargs: MllamaImagesKwargs
|
| 41 |
+
|
| 42 |
+
_defaults = {
|
| 43 |
+
"image_kwargs": {
|
| 44 |
+
"max_image_tiles": 4,
|
| 45 |
+
},
|
| 46 |
+
}
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
def get_cross_attention_token_mask(input_ids: List[int], image_token_id: int) -> List[List[int]]:
|
| 50 |
+
"""
|
| 51 |
+
Generate a cross-attention token mask for image tokens in the input sequence.
|
| 52 |
+
|
| 53 |
+
This function identifies the positions of image tokens in the input sequence and creates
|
| 54 |
+
a mask that defines which subsequent tokens each image token should attend to.
|
| 55 |
+
|
| 56 |
+
Args:
|
| 57 |
+
input_ids (List[int]): A list of token ids representing the input sequence.
|
| 58 |
+
image_token_id (int): The id of the token used to represent images in the sequence.
|
| 59 |
+
|
| 60 |
+
Returns:
|
| 61 |
+
List[List[int]]: A list of [start, end] pairs, where each pair represents the range
|
| 62 |
+
of tokens an image token should attend to.
|
| 63 |
+
|
| 64 |
+
Notes:
|
| 65 |
+
- If no image tokens are present, an empty list is returned.
|
| 66 |
+
- For a single image token, it attends to all subsequent tokens until the end of the sequence.
|
| 67 |
+
- For multiple image tokens, each attends to tokens up to the next image token or the end of the sequence.
|
| 68 |
+
- Consecutive image tokens are treated as a group and attend to all subsequent tokens together.
|
| 69 |
+
"""
|
| 70 |
+
|
| 71 |
+
image_token_locations = [i for i, token in enumerate(input_ids) if token == image_token_id]
|
| 72 |
+
|
| 73 |
+
if len(image_token_locations) == 0:
|
| 74 |
+
return []
|
| 75 |
+
|
| 76 |
+
# only one image present, unmask until end of sequence
|
| 77 |
+
if len(image_token_locations) == 1:
|
| 78 |
+
return [[image_token_locations[0], -1]]
|
| 79 |
+
|
| 80 |
+
vision_masks = [[loc1, loc2] for loc1, loc2 in zip(image_token_locations[:-1], image_token_locations[1:])]
|
| 81 |
+
|
| 82 |
+
# last image will attend to all subsequent text
|
| 83 |
+
vision_masks.append([image_token_locations[-1], len(input_ids)])
|
| 84 |
+
|
| 85 |
+
# if there are two or more consecutive vision tokens,
|
| 86 |
+
# they should all attend to all subsequent
|
| 87 |
+
# text present
|
| 88 |
+
last_mask_end = vision_masks[-1][1]
|
| 89 |
+
for vision_mask in vision_masks[::-1]:
|
| 90 |
+
if vision_mask[0] == vision_mask[1] - 1:
|
| 91 |
+
vision_mask[1] = last_mask_end
|
| 92 |
+
last_mask_end = vision_mask[1]
|
| 93 |
+
|
| 94 |
+
return vision_masks
|
| 95 |
+
|
| 96 |
+
|
| 97 |
+
def convert_sparse_cross_attention_mask_to_dense(
|
| 98 |
+
cross_attention_token_mask: List[List[List[int]]],
|
| 99 |
+
num_tiles: List[List[int]],
|
| 100 |
+
max_num_tiles: int,
|
| 101 |
+
length: int,
|
| 102 |
+
) -> np.ndarray:
|
| 103 |
+
"""
|
| 104 |
+
Convert the cross attention mask indices to a cross attention mask 4D array.
|
| 105 |
+
|
| 106 |
+
This function takes a sparse representation of cross attention masks and converts it to a dense 4D numpy array.
|
| 107 |
+
The sparse representation is a nested list structure that defines attention ranges for each image in each batch item.
|
| 108 |
+
|
| 109 |
+
Args:
|
| 110 |
+
cross_attention_token_mask (List[List[List[int]]]): A nested list structure where:
|
| 111 |
+
- The outer list represents the batch dimension.
|
| 112 |
+
- The middle list represents different images within each batch item.
|
| 113 |
+
- The inner list contains pairs of integers [start, end] representing token ranges for each image.
|
| 114 |
+
num_tiles (List[List[int]]): A nested list structure specifying the number of tiles for each image in each batch item.
|
| 115 |
+
max_num_tiles (int): The maximum possible number of tiles.
|
| 116 |
+
length (int): The total sequence length of the input.
|
| 117 |
+
|
| 118 |
+
Returns:
|
| 119 |
+
np.ndarray: A 4D numpy array of shape (batch_size, length, max_num_images, max_num_tiles)
|
| 120 |
+
The array contains `1` where attention is allowed and `0` where it is not.
|
| 121 |
+
|
| 122 |
+
Note:
|
| 123 |
+
- Special handling is done for cases where the end token is -1, which is interpreted as attending to the end of the sequence.
|
| 124 |
+
"""
|
| 125 |
+
|
| 126 |
+
batch_size = len(cross_attention_token_mask)
|
| 127 |
+
max_num_images = max([len(masks) for masks in cross_attention_token_mask])
|
| 128 |
+
|
| 129 |
+
cross_attention_mask = np.zeros(
|
| 130 |
+
shape=(batch_size, length, max_num_images, max_num_tiles),
|
| 131 |
+
dtype=np.int64,
|
| 132 |
+
)
|
| 133 |
+
|
| 134 |
+
for sample_idx, (sample_masks, sample_num_tiles) in enumerate(zip(cross_attention_token_mask, num_tiles)):
|
| 135 |
+
for mask_idx, (locations, mask_num_tiles) in enumerate(zip(sample_masks, sample_num_tiles)):
|
| 136 |
+
if len(locations) == 2:
|
| 137 |
+
start, end = locations
|
| 138 |
+
end = min(end, length)
|
| 139 |
+
if end == -1:
|
| 140 |
+
end = length
|
| 141 |
+
cross_attention_mask[sample_idx, start:end, mask_idx, :mask_num_tiles] = 1
|
| 142 |
+
return cross_attention_mask
|
| 143 |
+
|
| 144 |
+
|
| 145 |
+
def build_string_from_input(prompt: str, bos_token: str, image_token: str) -> str:
|
| 146 |
+
"""
|
| 147 |
+
Builds a string from the input prompt by adding `bos_token` if not already present.
|
| 148 |
+
|
| 149 |
+
Args:
|
| 150 |
+
prompt (`str`):
|
| 151 |
+
The input prompt string.
|
| 152 |
+
bos_token (`str`):
|
| 153 |
+
The beginning of sentence token to be added.
|
| 154 |
+
image_token (`str`):
|
| 155 |
+
The image token used to identify the start of an image sequence.
|
| 156 |
+
|
| 157 |
+
Returns:
|
| 158 |
+
str: The modified prompt string with the `bos_token` added if necessary.
|
| 159 |
+
|
| 160 |
+
Examples:
|
| 161 |
+
>>> build_string_from_input("Hello world", "<begin_of_text>", "<|image|>")
|
| 162 |
+
'<begin_of_text>Hello world'
|
| 163 |
+
|
| 164 |
+
>>> build_string_from_input("<|image|>Hello world", "<begin_of_text>", "<|image|>")
|
| 165 |
+
'<|image|><begin_of_text>Hello world'
|
| 166 |
+
|
| 167 |
+
>>> build_string_from_input("<begin_of_text>Hello world", "<begin_of_text>", "<|image|>")
|
| 168 |
+
'<begin_of_text>Hello world'
|
| 169 |
+
"""
|
| 170 |
+
|
| 171 |
+
if bos_token in prompt:
|
| 172 |
+
return prompt
|
| 173 |
+
|
| 174 |
+
num_image_tokens_on_start = 0
|
| 175 |
+
while prompt.startswith(image_token):
|
| 176 |
+
prompt = prompt[len(image_token) :]
|
| 177 |
+
num_image_tokens_on_start += 1
|
| 178 |
+
|
| 179 |
+
return f"{image_token * num_image_tokens_on_start}{bos_token}{prompt}"
|
| 180 |
+
|
| 181 |
+
|
| 182 |
+
class MllamaProcessor(ProcessorMixin):
|
| 183 |
+
r"""
|
| 184 |
+
Constructs a Mllama processor which wraps [`MllamaImageProcessor`] and
|
| 185 |
+
[`PretrainedTokenizerFast`] into a single processor that inherits both the image processor and
|
| 186 |
+
tokenizer functionalities. See the [`~MllamaProcessor.__call__`] and [`~OwlViTProcessor.decode`] for more
|
| 187 |
+
information.
|
| 188 |
+
The preferred way of passing kwargs is as a dictionary per modality, see usage example below.
|
| 189 |
+
```python
|
| 190 |
+
from transformers import MllamaProcessor
|
| 191 |
+
from PIL import Image
|
| 192 |
+
|
| 193 |
+
processor = MllamaProcessor.from_pretrained("meta-llama/Llama-3.2-11B-Vision")
|
| 194 |
+
|
| 195 |
+
processor(
|
| 196 |
+
images=your_pil_image,
|
| 197 |
+
text=["<|image|>If I had to write a haiku for this one"],
|
| 198 |
+
images_kwargs = {"size": {"height": 448, "width": 448}},
|
| 199 |
+
text_kwargs = {"padding": "right"},
|
| 200 |
+
common_kwargs = {"return_tensors": "pt"},
|
| 201 |
+
)
|
| 202 |
+
```
|
| 203 |
+
|
| 204 |
+
Args:
|
| 205 |
+
image_processor ([`MllamaImageProcessor`]):
|
| 206 |
+
The image processor is a required input.
|
| 207 |
+
tokenizer ([`PreTrainedTokenizer`, `PreTrainedTokenizerFast`]):
|
| 208 |
+
The tokenizer is a required input.
|
| 209 |
+
|
| 210 |
+
"""
|
| 211 |
+
|
| 212 |
+
attributes = ["image_processor", "audio_processor", "tokenizer"]
|
| 213 |
+
image_processor_class = "MllamaImageProcessor"
|
| 214 |
+
audio_processor_class = "MllamaAudioFeatureExtractor"
|
| 215 |
+
tokenizer_class = "PreTrainedTokenizerFast"
|
| 216 |
+
|
| 217 |
+
def __init__(self, image_processor, audio_processor, tokenizer):
|
| 218 |
+
self.image_token = "<|image|>"
|
| 219 |
+
self.image_token_id = tokenizer.convert_tokens_to_ids(self.image_token)
|
| 220 |
+
self.audio_token = "<|audio|>"
|
| 221 |
+
self.audio_token_id = tokenizer.convert_tokens_to_ids(self.audio_token)
|
| 222 |
+
self.python_token = "<|python_tag|>"
|
| 223 |
+
self.python_token_id = tokenizer.convert_tokens_to_ids(self.python_token)
|
| 224 |
+
self.bos_token = tokenizer.bos_token
|
| 225 |
+
self.chat_template = tokenizer.chat_template
|
| 226 |
+
super().__init__(image_processor, audio_processor, tokenizer)
|
| 227 |
+
|
| 228 |
+
def __call__(
|
| 229 |
+
self,
|
| 230 |
+
images: Optional[ImageInput] = None,
|
| 231 |
+
text: Optional[Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]]] = None,
|
| 232 |
+
audio: Optional[AudioInput] = None,
|
| 233 |
+
videos=None,
|
| 234 |
+
**kwargs: Unpack[MllamaProcessorKwargs],
|
| 235 |
+
) -> BatchFeature:
|
| 236 |
+
"""
|
| 237 |
+
Main method to prepare text(s) and image(s) to be fed as input to the model. This method forwards the `text`
|
| 238 |
+
arguments to PreTrainedTokenizerFast's [`~PreTrainedTokenizerFast.__call__`] if `text` is not `None` to encode
|
| 239 |
+
the text. To prepare the image(s), this method forwards the `images` arguments to
|
| 240 |
+
MllamaImageProcessor's [`~MllamaImageProcessor.__call__`] if `images` is not `None`. Please refer
|
| 241 |
+
to the docstring of the above two methods for more information.
|
| 242 |
+
|
| 243 |
+
Args:
|
| 244 |
+
images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`):
|
| 245 |
+
The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
|
| 246 |
+
tensor. Both channels-first and channels-last formats are supported.
|
| 247 |
+
text (`str`, `List[str]`, `List[List[str]]`):
|
| 248 |
+
The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
|
| 249 |
+
(pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
|
| 250 |
+
`is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
|
| 251 |
+
return_tensors (`str` or [`~utils.TensorType`], *optional*):
|
| 252 |
+
If set, will return tensors of a particular framework. Acceptable values are:
|
| 253 |
+
- `'tf'`: Return TensorFlow `tf.constant` objects.
|
| 254 |
+
- `'pt'`: Return PyTorch `torch.Tensor` objects.
|
| 255 |
+
- `'np'`: Return NumPy `np.ndarray` objects.
|
| 256 |
+
- `'jax'`: Return JAX `jnp.ndarray` objects.
|
| 257 |
+
Returns:
|
| 258 |
+
[`BatchFeature`]: A [`BatchFeature`] with the following fields:
|
| 259 |
+
|
| 260 |
+
- **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`.
|
| 261 |
+
- **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when
|
| 262 |
+
`return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not
|
| 263 |
+
`None`).
|
| 264 |
+
- **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`.
|
| 265 |
+
- **audio_features** -- Audio features extracted using SeamlessM4TFeatureExtractor. Returned when `audio` is not `None`.
|
| 266 |
+
TODO: add aspect_ratio_ids and aspect_ratio_mask and cross_attention_mask
|
| 267 |
+
"""
|
| 268 |
+
if text is None:
|
| 269 |
+
raise ValueError("You must specify text.")
|
| 270 |
+
|
| 271 |
+
output_kwargs = self._merge_kwargs(
|
| 272 |
+
MllamaProcessorKwargs,
|
| 273 |
+
tokenizer_init_kwargs=self.tokenizer.init_kwargs,
|
| 274 |
+
**kwargs,
|
| 275 |
+
)
|
| 276 |
+
|
| 277 |
+
text_kwargs = output_kwargs["text_kwargs"]
|
| 278 |
+
images_kwargs = output_kwargs["images_kwargs"]
|
| 279 |
+
common_kwargs = output_kwargs["common_kwargs"]
|
| 280 |
+
|
| 281 |
+
data = {}
|
| 282 |
+
|
| 283 |
+
if audio is not None:
|
| 284 |
+
audio_batch = make_list_of_audio_clips(audio)
|
| 285 |
+
audio_features = self.audio_processor(audio_batch)
|
| 286 |
+
data.update(audio_features)
|
| 287 |
+
|
| 288 |
+
if isinstance(text, str):
|
| 289 |
+
text = [text]
|
| 290 |
+
elif not (isinstance(text, (list, tuple)) and all(isinstance(t, str) for t in text)):
|
| 291 |
+
raise ValueError("Invalid input text. Please provide a string, or a list of strings")
|
| 292 |
+
n_images_in_text = [t.count(self.image_token) for t in text]
|
| 293 |
+
text = [build_string_from_input(text_item, self.bos_token, self.image_token) for text_item in text]
|
| 294 |
+
_ = text_kwargs.pop("padding_side", None) # hack until padding-side is an accepted kwarg by tokenizers
|
| 295 |
+
encoding = self.tokenizer(text, **text_kwargs)
|
| 296 |
+
if audio is not None:
|
| 297 |
+
encoding = build_audio_tokens(encoding, audio_features, self.audio_token_id)
|
| 298 |
+
data.update(encoding)
|
| 299 |
+
|
| 300 |
+
n_images_in_images = [0]
|
| 301 |
+
if images is not None:
|
| 302 |
+
images = make_list_of_images(images)
|
| 303 |
+
n_images_in_images = [len(sample) for sample in images]
|
| 304 |
+
|
| 305 |
+
if text is not None:
|
| 306 |
+
if any(batch_img == 0 for batch_img in n_images_in_text) and not all(
|
| 307 |
+
batch_img == 0 for batch_img in n_images_in_text
|
| 308 |
+
):
|
| 309 |
+
raise ValueError(
|
| 310 |
+
"If a batch of text is provided, there should be either no images or at least one image per sample"
|
| 311 |
+
)
|
| 312 |
+
if sum(n_images_in_images) != sum(n_images_in_text):
|
| 313 |
+
if images is None:
|
| 314 |
+
raise ValueError("No image were provided, but there are image tokens in the prompt")
|
| 315 |
+
else:
|
| 316 |
+
raise ValueError(
|
| 317 |
+
f"The number of image token ({sum(n_images_in_text)}) should be the same as in the number of provided images ({sum(n_images_in_images)})"
|
| 318 |
+
)
|
| 319 |
+
|
| 320 |
+
if images is not None:
|
| 321 |
+
image_features = self.image_processor(images, **images_kwargs)
|
| 322 |
+
num_tiles = image_features.pop("num_tiles")
|
| 323 |
+
data.update(image_features)
|
| 324 |
+
|
| 325 |
+
# Create cross attention mask
|
| 326 |
+
if images is not None and text is not None:
|
| 327 |
+
cross_attention_token_mask = [
|
| 328 |
+
get_cross_attention_token_mask(token_ids, self.image_token_id) for token_ids in encoding["input_ids"]
|
| 329 |
+
]
|
| 330 |
+
cross_attention_mask = convert_sparse_cross_attention_mask_to_dense(
|
| 331 |
+
cross_attention_token_mask,
|
| 332 |
+
num_tiles=num_tiles,
|
| 333 |
+
max_num_tiles=self.image_processor.max_image_tiles,
|
| 334 |
+
length=max(len(input_ids) for input_ids in encoding["input_ids"]),
|
| 335 |
+
)
|
| 336 |
+
data["cross_attention_mask"] = cross_attention_mask
|
| 337 |
+
|
| 338 |
+
return_tensors = common_kwargs.pop("return_tensors", None)
|
| 339 |
+
batch_feature = BatchFeature(data=data, tensor_type=return_tensors)
|
| 340 |
+
|
| 341 |
+
return batch_feature
|
| 342 |
+
|
| 343 |
+
def batch_decode(self, *args, **kwargs):
|
| 344 |
+
"""
|
| 345 |
+
This method forwards all its arguments to PreTrainedTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please
|
| 346 |
+
refer to the docstring of this method for more information.
|
| 347 |
+
"""
|
| 348 |
+
return self.tokenizer.batch_decode(*args, **kwargs)
|
| 349 |
+
|
| 350 |
+
def decode(self, *args, **kwargs):
|
| 351 |
+
"""
|
| 352 |
+
This method forwards all its arguments to PreTrainedTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to
|
| 353 |
+
the docstring of this method for more information.
|
| 354 |
+
"""
|
| 355 |
+
return self.tokenizer.decode(*args, **kwargs)
|
| 356 |
+
|
| 357 |
+
@property
|
| 358 |
+
def model_input_names(self):
|
| 359 |
+
tokenizer_input_names = self.tokenizer.model_input_names
|
| 360 |
+
image_processor_input_names = self.image_processor.model_input_names
|
| 361 |
+
audio_processor_input_names = self.audio_processor.model_input_names
|
| 362 |
+
return list(tokenizer_input_names +
|
| 363 |
+
image_processor_input_names +
|
| 364 |
+
["cross_attention_mask"] +
|
| 365 |
+
audio_processor_input_names)
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|eot_id|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|finetune_right_pad_id|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,2079 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|finetune_right_pad_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|step_id|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|eom_id|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|python_tag|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_2|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_3|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_4|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_5|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_6|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_7|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_8|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_9|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_10|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_11|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_12|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_13|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_14|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_15|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_16|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_17|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_18|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_19|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_20|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_21|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_22|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_23|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_24|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_25|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_26|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_27|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_28|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_29|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_30|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_31|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_32|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_33|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_34|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_35|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_36|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_37|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_38|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_39|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_40|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_41|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_42|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_43|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_44|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_45|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_46|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_47|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_48|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_49|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_50|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_51|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_52|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_53|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_54|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_55|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_56|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_57|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_58|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_59|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_60|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_61|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_62|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_63|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_64|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_65|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_66|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_67|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_68|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_69|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_70|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_71|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_72|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_73|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_74|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_75|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_76|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_77|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_78|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_79|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_80|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_81|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_82|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_83|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_84|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_85|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_86|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_87|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_88|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_89|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_90|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_91|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_92|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_93|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_94|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_95|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_96|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_97|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_98|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_99|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_100|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_101|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_102|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_103|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_104|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_105|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_106|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_107|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_108|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_109|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_110|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_111|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_112|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_113|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_114|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_115|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_116|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_117|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_118|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_119|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_120|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_121|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_122|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_123|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_124|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_125|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_126|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_127|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_128|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_129|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_130|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_131|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_132|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_133|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_134|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_135|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_136|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_137|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_138|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_139|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_140|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_141|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_142|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_143|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_144|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_145|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_146|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_147|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_148|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_149|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_150|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_151|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_152|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_153|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_154|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_155|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_156|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_157|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_158|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_159|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_160|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_161|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_162|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_163|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_164|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_165|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_166|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_167|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_168|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_169|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_170|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_171|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_172|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_173|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_174|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_175|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_176|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_177|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_178|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_179|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_180|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_181|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_182|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_183|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_184|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_185|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_186|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_187|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_188|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_189|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_190|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_191|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_192|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_193|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_194|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_195|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_196|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_197|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_198|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_199|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_200|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_201|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_202|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_203|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_204|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_205|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_206|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_207|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_208|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_209|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_210|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_211|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_212|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_213|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_214|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_215|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_216|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_217|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_218|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_219|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_220|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_221|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_222|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_223|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_224|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_225|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_226|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_227|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_228|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_229|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_230|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_231|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_232|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_233|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_234|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_235|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_236|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_237|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_238|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_239|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_240|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|begin_of_audio|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|end_of_audio|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_243|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_244|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_245|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_246|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
},
|
| 2051 |
+
"128256": {
|
| 2052 |
+
"content": "<|image|>",
|
| 2053 |
+
"lstrip": false,
|
| 2054 |
+
"normalized": false,
|
| 2055 |
+
"rstrip": false,
|
| 2056 |
+
"single_word": false,
|
| 2057 |
+
"special": true
|
| 2058 |
+
},
|
| 2059 |
+
"128257": {
|
| 2060 |
+
"content": "<|audio|>",
|
| 2061 |
+
"lstrip": false,
|
| 2062 |
+
"normalized": false,
|
| 2063 |
+
"rstrip": false,
|
| 2064 |
+
"single_word": false,
|
| 2065 |
+
"special": true
|
| 2066 |
+
}
|
| 2067 |
+
},
|
| 2068 |
+
"bos_token": "<|begin_of_text|>",
|
| 2069 |
+
"chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- Find out if there are any images #}\n{% set image_ns = namespace(has_images=false) %} \n{%- for message in messages %}\n {%- for content in message['content'] %}\n {%- if content['type'] == 'image' %}\n {%- set image_ns.has_images = true %}\n {%- endif %}\n {%- endfor %}\n{%- endfor %}\n\n{#- Error out if there are images and system message #}\n{%- if image_ns.has_images and not system_message == \"\" %}\n {{- raise_exception(\"Prompting with images is incompatible with system messages.\") }}\n{%- endif %}\n\n{#- System message if there are no images #}\n{%- if not image_ns.has_images %}\n {{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n {%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n {%- endif %}\n {{- \"Cutting Knowledge Date: December 2023\\n\" }}\n {{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n {%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {%- endif %}\n {{- system_message }}\n {{- \"<|eot_id|>\" }}\n{%- endif %}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n' }}\n {%- if message['content'] is string %}\n {{- message['content'] }}\n {%- else %}\n {%- for content in message['content'] %}\n {%- if content['type'] == 'image' %}\n {{- '<|image|>' }}\n {%- elif content['type'] == 'text' %}\n {{- content['text'] }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
|
| 2070 |
+
"clean_up_tokenization_spaces": true,
|
| 2071 |
+
"eos_token": "<|eot_id|>",
|
| 2072 |
+
"model_input_names": [
|
| 2073 |
+
"input_ids",
|
| 2074 |
+
"attention_mask"
|
| 2075 |
+
],
|
| 2076 |
+
"model_max_length": 131072,
|
| 2077 |
+
"pad_token": "<|finetune_right_pad_id|>",
|
| 2078 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2079 |
+
}
|