Hugging Face's logo

ensembleai
/
Llama-3-8B-CSQA-NdLinearLoRA

PyTorch
English
Model card Files
xet
Community
zhongfang-zhuang commited on
Commit
5863d6f
·
verified ·
1 Parent(s): 35fb9da

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. .gitattributes +1 -0
  2. Meta-Llama-3-8B-CSQA-NdLinearLoRA.safetensors +3 -0
  3. README.md +67 -3
  4. modeling_ndlinear.py +53 -0
  5. ndlinear.py +82 -0
  6. ndlinear_lora_config.json +2708 -0
  7. pytorch_model.bin +3 -0
  8. special_tokens_map.json +17 -0
  9. tokenizer.json +3 -0
  10. tokenizer_config.json +2063 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
Meta-Llama-3-8B-CSQA-NdLinearLoRA.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a8335c1009d7878c921bba61a919c04427001aa7c1e5ba42ce91782f0c5cc71
3
+ size 32130190008
README.md CHANGED
@@ -1,3 +1,67 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ language: en
4
+ ---
5
+
6
+ # NdLinear-LoRA Fine-Tuned Models
7
+
8
+ This repository contains a collection of language models fine-tuned using a custom NdLinear-LoRA architecture. NdLinear-LoRA is a variant of Low-Rank Adaptation (LoRA) that reshapes weight matrices into N-dimensional tensors and applies a factorized linear transformation for parameter-efficient fine-tuning.
9
+
10
+ ## Available Models
11
+
12
+ Below is a list of the fine-tuned models. For best results, it's recommended to host each model in its own repository on the Hugging Face Hub.
13
+
14
+ | Fine-Tuned Model Name | Base Model | Fine-Tuning Dataset |
15
+ | ------------------------------------------------ | -------------------------- | ------------------- |
16
+ | `Meta-Llama-3-8B-CSQA-NdLinearLoRA` | `meta-llama/Llama-3-8B` | `commonsense_qa` |
17
+ | `Meta-Llama-3-8B-Math10K-NdLinearLoRA` | `meta-llama/Llama-3-8B` | `lmms-lab/Math10K` |
18
+ | `Qwen3-1.7B-CSQA-NdLinearLoRA` | `Qwen/Qwen3-1.7B-Base` | `commonsense_qa` |
19
+ | `Qwen3-1.7B-Math10K-NdLinearLoRA` | `Qwen/Qwen3-1.7B-Base` | `lmms-lab/Math10K` |
20
+
21
+ ## How to Use
22
+
23
+ Because these models use a custom architecture, you must pass `trust_remote_code=True` when loading them. This allows the `transformers` library to download and use the `modeling_ndlinear.py` file that should be included in each model's repository.
24
+
25
+ **Dependencies:** Before you start, make sure you have the necessary libraries installed:
26
+ ```bash
27
+ pip install torch transformers safetensors huggingface_hub accelerate
28
+ pip install ndlinear
29
+ ```
30
+
31
+ ### Example Loading Script
32
+ This script will work for any of the models listed above. Just change the `REPO_ID`.
33
+
34
+ ```python
35
+ import torch
36
+ from transformers import AutoModelForCausalLM, AutoTokenizer
37
+
38
+ # --- Example Usage ---
39
+
40
+ # 1. Choose the model you want to use from the table above
41
+ # Replace "YourUsername" with your Hugging Face username or organization.
42
+ REPO_ID = "YourUsername/Qwen3-1.7B-Math10K-NdLinearLoRA"
43
+
44
+ # 2. Load the model and tokenizer
45
+ # `trust_remote_code=True` is required to load the custom architecture.
46
+ print(f"Loading model: {REPO_ID}")
47
+ model = AutoModelForCausalLM.from_pretrained(
48
+ REPO_ID,
49
+ torch_dtype="auto",
50
+ device_map="auto",
51
+ trust_remote_code=True
52
+ )
53
+ tokenizer = AutoTokenizer.from_pretrained(REPO_ID)
54
+ print("Model and tokenizer loaded successfully.")
55
+
56
+
57
+ # 3. Generate text
58
+ # This prompt is geared for a math model. Adjust it for a QA model if needed.
59
+ prompt = "### Instruction:\\nSolve the following math problem: If a train travels at 60 miles per hour, how long does it take to travel 180 miles?\\n\\n### Solution:\\n"
60
+ inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
61
+
62
+ with torch.no_grad():
63
+ outputs = model.generate(**inputs, max_new_tokens=150, eos_token_id=tokenizer.eos_token_id)
64
+
65
+ print("\\n--- Generated Output ---")
66
+ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
67
+ ```
modeling_ndlinear.py ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import torch
2
+ import torch.nn as nn
3
+ from ndlinear import NdLinear
4
+
5
+ # This file contains the custom building blocks for the NdLinear-LoRA architecture.
6
+ # It should be in the same directory as the model when loading it.
7
+
8
+ def find_factor(n):
9
+ """Finds the most balanced integer factors for n."""
10
+ for i in range(int(n ** 0.5), 0, -1):
11
+ if n % i == 0:
12
+ return (i, n // i)
13
+ return (1, n)
14
+
15
+ class NdLinearLoRA(nn.Module):
16
+ """The NdLinear-LoRA adapter layer."""
17
+ def __init__(self, d_in, d_out, alpha=1.0, dropout=0.0):
18
+ super().__init__()
19
+ self.d_in = d_in
20
+ self.d_out = d_out
21
+ self.in_factors = find_factor(d_in)
22
+ self.out_factors = find_factor(d_out)
23
+ self.adapter = NdLinear(
24
+ input_dims=self.in_factors,
25
+ hidden_size=self.out_factors,
26
+ transform_outer=False,
27
+ bias=False
28
+ )
29
+ self.scaling = alpha
30
+ self.drop = nn.Dropout(dropout)
31
+
32
+ def forward(self, x):
33
+ orig_shape = x.shape
34
+ x = self.drop(x).view(-1, *self.in_factors)
35
+ y = self.adapter(x).view(*orig_shape[:-1], self.d_out)
36
+ return y * self.scaling
37
+
38
+ class LinearWithNdLinearLoRA(nn.Module):
39
+ """A nn.Linear layer wrapped with the NdLinear-LoRA adapter."""
40
+ def __init__(self, base_layer, alpha=1.0, dropout=0.0):
41
+ super().__init__()
42
+ self.base_layer = base_layer
43
+ for param in self.base_layer.parameters():
44
+ param.requires_grad = False
45
+ self.adapter = NdLinearLoRA(
46
+ d_in=self.base_layer.in_features,
47
+ d_out=self.base_layer.out_features,
48
+ alpha=alpha,
49
+ dropout=dropout
50
+ )
51
+
52
+ def forward(self, x):
53
+ return self.base_layer(x) + self.adapter(x)
ndlinear.py ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import torch
2
+ import torch.nn as nn
3
+ import torch.optim as optim
4
+
5
+
6
+ class NdLinear(nn.Module):
7
+ def __init__(self, input_dims: tuple, hidden_size: tuple, transform_outer=True, bias: bool = True):
8
+ """
9
+ NdLinear: A PyTorch layer for projecting tensors into multi-space representations.
10
+
11
+ Unlike conventional embedding layers that map into a single vector space, NdLinear
12
+ transforms tensors across a collection of vector spaces, capturing multivariate structure
13
+ and topical information that standard deep learning architectures typically lose.
14
+
15
+ Args:
16
+ input_dims (tuple): Shape of input tensor (excluding batch dimension).
17
+ hidden_size (tuple): Target hidden dimensions after transformation.
18
+ """
19
+ super(NdLinear, self).__init__()
20
+
21
+ if len(input_dims) != len(hidden_size):
22
+ raise Exception("Input shape and hidden shape do not match.")
23
+
24
+ self.input_dims = input_dims
25
+ self.hidden_size = hidden_size
26
+ self.num_layers = len(input_dims) # Must match since dims are equal
27
+ # self.relu = nn.ReLU() # self.relu is not being used.
28
+ self.transform_outer = transform_outer
29
+ self.bias = bias
30
+
31
+ # Define transformation layers per dimension
32
+ self.align_layers = nn.ModuleList([
33
+ nn.Linear(input_dims[i], hidden_size[i], bias=self.bias) for i in range(self.num_layers)
34
+ ])
35
+
36
+
37
+ def forward(self, X):
38
+ """
39
+ Forward pass to project input tensor into a new multi-space representation.
40
+ - Incrementally transposes, flattens, applies linear layers, and restores shape.
41
+
42
+ Expected Input Shape: [batch_size, *input_dims]
43
+ Output Shape: [batch_size, *hidden_size]
44
+
45
+ Args:
46
+ X (torch.Tensor): Input tensor with shape [batch_size, *input_dims]
47
+
48
+ Returns:
49
+ torch.Tensor: Output tensor with shape [batch_size, *hidden_size]
50
+ """
51
+ num_transforms = self.num_layers # Number of transformations
52
+
53
+ # Define iteration order
54
+ # transform_indices = range(num_transforms) if transform_outer else reversed(range(num_transforms))
55
+
56
+ for i in range(num_transforms):
57
+ if self.transform_outer:
58
+ layer = self.align_layers[i]
59
+ transpose_dim = i + 1
60
+ else:
61
+ layer = self.align_layers[num_transforms - (i+1)]
62
+ transpose_dim = num_transforms - i
63
+
64
+ # Transpose the selected dimension to the last position
65
+ X = torch.transpose(X, transpose_dim, num_transforms).contiguous()
66
+
67
+ # Store original shape before transformation
68
+ X_size = X.shape[:-1]
69
+
70
+ # Flatten everything except the last dimension
71
+ X = X.view(-1, X.shape[-1])
72
+
73
+ # Apply transformation
74
+ X = layer(X)
75
+
76
+ # Reshape back to the original spatial structure (with new embedding dim)
77
+ X = X.view(*X_size, X.shape[-1])
78
+
79
+ # Transpose the dimension back to its original position
80
+ X = torch.transpose(X, transpose_dim, num_transforms).contiguous()
81
+
82
+ return X
ndlinear_lora_config.json ADDED
@@ -0,0 +1,2708 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_name": "meta-llama/Meta-Llama-3-8B",
3
+ "lora_r": 1,
4
+ "lora_alpha": 1,
5
+ "target_modules": [
6
+ "q_proj",
7
+ "k_proj",
8
+ "v_proj",
9
+ "o_proj",
10
+ "gate_proj",
11
+ "up_proj",
12
+ "down_proj"
13
+ ],
14
+ "use_factorized": true,
15
+ "wrapped_modules": {
16
+ "model.layers.0.self_attn.q_proj": {
17
+ "in_features": 4096,
18
+ "out_features": 4096,
19
+ "in_factors": [
20
+ 64,
21
+ 64
22
+ ],
23
+ "out_factors": [
24
+ 64,
25
+ 64
26
+ ]
27
+ },
28
+ "model.layers.0.self_attn.k_proj": {
29
+ "in_features": 4096,
30
+ "out_features": 1024,
31
+ "in_factors": [
32
+ 64,
33
+ 64
34
+ ],
35
+ "out_factors": [
36
+ 32,
37
+ 32
38
+ ]
39
+ },
40
+ "model.layers.0.self_attn.v_proj": {
41
+ "in_features": 4096,
42
+ "out_features": 1024,
43
+ "in_factors": [
44
+ 64,
45
+ 64
46
+ ],
47
+ "out_factors": [
48
+ 32,
49
+ 32
50
+ ]
51
+ },
52
+ "model.layers.0.self_attn.o_proj": {
53
+ "in_features": 4096,
54
+ "out_features": 4096,
55
+ "in_factors": [
56
+ 64,
57
+ 64
58
+ ],
59
+ "out_factors": [
60
+ 64,
61
+ 64
62
+ ]
63
+ },
64
+ "model.layers.0.mlp.gate_proj": {
65
+ "in_features": 4096,
66
+ "out_features": 14336,
67
+ "in_factors": [
68
+ 64,
69
+ 64
70
+ ],
71
+ "out_factors": [
72
+ 112,
73
+ 128
74
+ ]
75
+ },
76
+ "model.layers.0.mlp.up_proj": {
77
+ "in_features": 4096,
78
+ "out_features": 14336,
79
+ "in_factors": [
80
+ 64,
81
+ 64
82
+ ],
83
+ "out_factors": [
84
+ 112,
85
+ 128
86
+ ]
87
+ },
88
+ "model.layers.0.mlp.down_proj": {
89
+ "in_features": 14336,
90
+ "out_features": 4096,
91
+ "in_factors": [
92
+ 112,
93
+ 128
94
+ ],
95
+ "out_factors": [
96
+ 64,
97
+ 64
98
+ ]
99
+ },
100
+ "model.layers.1.self_attn.q_proj": {
101
+ "in_features": 4096,
102
+ "out_features": 4096,
103
+ "in_factors": [
104
+ 64,
105
+ 64
106
+ ],
107
+ "out_factors": [
108
+ 64,
109
+ 64
110
+ ]
111
+ },
112
+ "model.layers.1.self_attn.k_proj": {
113
+ "in_features": 4096,
114
+ "out_features": 1024,
115
+ "in_factors": [
116
+ 64,
117
+ 64
118
+ ],
119
+ "out_factors": [
120
+ 32,
121
+ 32
122
+ ]
123
+ },
124
+ "model.layers.1.self_attn.v_proj": {
125
+ "in_features": 4096,
126
+ "out_features": 1024,
127
+ "in_factors": [
128
+ 64,
129
+ 64
130
+ ],
131
+ "out_factors": [
132
+ 32,
133
+ 32
134
+ ]
135
+ },
136
+ "model.layers.1.self_attn.o_proj": {
137
+ "in_features": 4096,
138
+ "out_features": 4096,
139
+ "in_factors": [
140
+ 64,
141
+ 64
142
+ ],
143
+ "out_factors": [
144
+ 64,
145
+ 64
146
+ ]
147
+ },
148
+ "model.layers.1.mlp.gate_proj": {
149
+ "in_features": 4096,
150
+ "out_features": 14336,
151
+ "in_factors": [
152
+ 64,
153
+ 64
154
+ ],
155
+ "out_factors": [
156
+ 112,
157
+ 128
158
+ ]
159
+ },
160
+ "model.layers.1.mlp.up_proj": {
161
+ "in_features": 4096,
162
+ "out_features": 14336,
163
+ "in_factors": [
164
+ 64,
165
+ 64
166
+ ],
167
+ "out_factors": [
168
+ 112,
169
+ 128
170
+ ]
171
+ },
172
+ "model.layers.1.mlp.down_proj": {
173
+ "in_features": 14336,
174
+ "out_features": 4096,
175
+ "in_factors": [
176
+ 112,
177
+ 128
178
+ ],
179
+ "out_factors": [
180
+ 64,
181
+ 64
182
+ ]
183
+ },
184
+ "model.layers.2.self_attn.q_proj": {
185
+ "in_features": 4096,
186
+ "out_features": 4096,
187
+ "in_factors": [
188
+ 64,
189
+ 64
190
+ ],
191
+ "out_factors": [
192
+ 64,
193
+ 64
194
+ ]
195
+ },
196
+ "model.layers.2.self_attn.k_proj": {
197
+ "in_features": 4096,
198
+ "out_features": 1024,
199
+ "in_factors": [
200
+ 64,
201
+ 64
202
+ ],
203
+ "out_factors": [
204
+ 32,
205
+ 32
206
+ ]
207
+ },
208
+ "model.layers.2.self_attn.v_proj": {
209
+ "in_features": 4096,
210
+ "out_features": 1024,
211
+ "in_factors": [
212
+ 64,
213
+ 64
214
+ ],
215
+ "out_factors": [
216
+ 32,
217
+ 32
218
+ ]
219
+ },
220
+ "model.layers.2.self_attn.o_proj": {
221
+ "in_features": 4096,
222
+ "out_features": 4096,
223
+ "in_factors": [
224
+ 64,
225
+ 64
226
+ ],
227
+ "out_factors": [
228
+ 64,
229
+ 64
230
+ ]
231
+ },
232
+ "model.layers.2.mlp.gate_proj": {
233
+ "in_features": 4096,
234
+ "out_features": 14336,
235
+ "in_factors": [
236
+ 64,
237
+ 64
238
+ ],
239
+ "out_factors": [
240
+ 112,
241
+ 128
242
+ ]
243
+ },
244
+ "model.layers.2.mlp.up_proj": {
245
+ "in_features": 4096,
246
+ "out_features": 14336,
247
+ "in_factors": [
248
+ 64,
249
+ 64
250
+ ],
251
+ "out_factors": [
252
+ 112,
253
+ 128
254
+ ]
255
+ },
256
+ "model.layers.2.mlp.down_proj": {
257
+ "in_features": 14336,
258
+ "out_features": 4096,
259
+ "in_factors": [
260
+ 112,
261
+ 128
262
+ ],
263
+ "out_factors": [
264
+ 64,
265
+ 64
266
+ ]
267
+ },
268
+ "model.layers.3.self_attn.q_proj": {
269
+ "in_features": 4096,
270
+ "out_features": 4096,
271
+ "in_factors": [
272
+ 64,
273
+ 64
274
+ ],
275
+ "out_factors": [
276
+ 64,
277
+ 64
278
+ ]
279
+ },
280
+ "model.layers.3.self_attn.k_proj": {
281
+ "in_features": 4096,
282
+ "out_features": 1024,
283
+ "in_factors": [
284
+ 64,
285
+ 64
286
+ ],
287
+ "out_factors": [
288
+ 32,
289
+ 32
290
+ ]
291
+ },
292
+ "model.layers.3.self_attn.v_proj": {
293
+ "in_features": 4096,
294
+ "out_features": 1024,
295
+ "in_factors": [
296
+ 64,
297
+ 64
298
+ ],
299
+ "out_factors": [
300
+ 32,
301
+ 32
302
+ ]
303
+ },
304
+ "model.layers.3.self_attn.o_proj": {
305
+ "in_features": 4096,
306
+ "out_features": 4096,
307
+ "in_factors": [
308
+ 64,
309
+ 64
310
+ ],
311
+ "out_factors": [
312
+ 64,
313
+ 64
314
+ ]
315
+ },
316
+ "model.layers.3.mlp.gate_proj": {
317
+ "in_features": 4096,
318
+ "out_features": 14336,
319
+ "in_factors": [
320
+ 64,
321
+ 64
322
+ ],
323
+ "out_factors": [
324
+ 112,
325
+ 128
326
+ ]
327
+ },
328
+ "model.layers.3.mlp.up_proj": {
329
+ "in_features": 4096,
330
+ "out_features": 14336,
331
+ "in_factors": [
332
+ 64,
333
+ 64
334
+ ],
335
+ "out_factors": [
336
+ 112,
337
+ 128
338
+ ]
339
+ },
340
+ "model.layers.3.mlp.down_proj": {
341
+ "in_features": 14336,
342
+ "out_features": 4096,
343
+ "in_factors": [
344
+ 112,
345
+ 128
346
+ ],
347
+ "out_factors": [
348
+ 64,
349
+ 64
350
+ ]
351
+ },
352
+ "model.layers.4.self_attn.q_proj": {
353
+ "in_features": 4096,
354
+ "out_features": 4096,
355
+ "in_factors": [
356
+ 64,
357
+ 64
358
+ ],
359
+ "out_factors": [
360
+ 64,
361
+ 64
362
+ ]
363
+ },
364
+ "model.layers.4.self_attn.k_proj": {
365
+ "in_features": 4096,
366
+ "out_features": 1024,
367
+ "in_factors": [
368
+ 64,
369
+ 64
370
+ ],
371
+ "out_factors": [
372
+ 32,
373
+ 32
374
+ ]
375
+ },
376
+ "model.layers.4.self_attn.v_proj": {
377
+ "in_features": 4096,
378
+ "out_features": 1024,
379
+ "in_factors": [
380
+ 64,
381
+ 64
382
+ ],
383
+ "out_factors": [
384
+ 32,
385
+ 32
386
+ ]
387
+ },
388
+ "model.layers.4.self_attn.o_proj": {
389
+ "in_features": 4096,
390
+ "out_features": 4096,
391
+ "in_factors": [
392
+ 64,
393
+ 64
394
+ ],
395
+ "out_factors": [
396
+ 64,
397
+ 64
398
+ ]
399
+ },
400
+ "model.layers.4.mlp.gate_proj": {
401
+ "in_features": 4096,
402
+ "out_features": 14336,
403
+ "in_factors": [
404
+ 64,
405
+ 64
406
+ ],
407
+ "out_factors": [
408
+ 112,
409
+ 128
410
+ ]
411
+ },
412
+ "model.layers.4.mlp.up_proj": {
413
+ "in_features": 4096,
414
+ "out_features": 14336,
415
+ "in_factors": [
416
+ 64,
417
+ 64
418
+ ],
419
+ "out_factors": [
420
+ 112,
421
+ 128
422
+ ]
423
+ },
424
+ "model.layers.4.mlp.down_proj": {
425
+ "in_features": 14336,
426
+ "out_features": 4096,
427
+ "in_factors": [
428
+ 112,
429
+ 128
430
+ ],
431
+ "out_factors": [
432
+ 64,
433
+ 64
434
+ ]
435
+ },
436
+ "model.layers.5.self_attn.q_proj": {
437
+ "in_features": 4096,
438
+ "out_features": 4096,
439
+ "in_factors": [
440
+ 64,
441
+ 64
442
+ ],
443
+ "out_factors": [
444
+ 64,
445
+ 64
446
+ ]
447
+ },
448
+ "model.layers.5.self_attn.k_proj": {
449
+ "in_features": 4096,
450
+ "out_features": 1024,
451
+ "in_factors": [
452
+ 64,
453
+ 64
454
+ ],
455
+ "out_factors": [
456
+ 32,
457
+ 32
458
+ ]
459
+ },
460
+ "model.layers.5.self_attn.v_proj": {
461
+ "in_features": 4096,
462
+ "out_features": 1024,
463
+ "in_factors": [
464
+ 64,
465
+ 64
466
+ ],
467
+ "out_factors": [
468
+ 32,
469
+ 32
470
+ ]
471
+ },
472
+ "model.layers.5.self_attn.o_proj": {
473
+ "in_features": 4096,
474
+ "out_features": 4096,
475
+ "in_factors": [
476
+ 64,
477
+ 64
478
+ ],
479
+ "out_factors": [
480
+ 64,
481
+ 64
482
+ ]
483
+ },
484
+ "model.layers.5.mlp.gate_proj": {
485
+ "in_features": 4096,
486
+ "out_features": 14336,
487
+ "in_factors": [
488
+ 64,
489
+ 64
490
+ ],
491
+ "out_factors": [
492
+ 112,
493
+ 128
494
+ ]
495
+ },
496
+ "model.layers.5.mlp.up_proj": {
497
+ "in_features": 4096,
498
+ "out_features": 14336,
499
+ "in_factors": [
500
+ 64,
501
+ 64
502
+ ],
503
+ "out_factors": [
504
+ 112,
505
+ 128
506
+ ]
507
+ },
508
+ "model.layers.5.mlp.down_proj": {
509
+ "in_features": 14336,
510
+ "out_features": 4096,
511
+ "in_factors": [
512
+ 112,
513
+ 128
514
+ ],
515
+ "out_factors": [
516
+ 64,
517
+ 64
518
+ ]
519
+ },
520
+ "model.layers.6.self_attn.q_proj": {
521
+ "in_features": 4096,
522
+ "out_features": 4096,
523
+ "in_factors": [
524
+ 64,
525
+ 64
526
+ ],
527
+ "out_factors": [
528
+ 64,
529
+ 64
530
+ ]
531
+ },
532
+ "model.layers.6.self_attn.k_proj": {
533
+ "in_features": 4096,
534
+ "out_features": 1024,
535
+ "in_factors": [
536
+ 64,
537
+ 64
538
+ ],
539
+ "out_factors": [
540
+ 32,
541
+ 32
542
+ ]
543
+ },
544
+ "model.layers.6.self_attn.v_proj": {
545
+ "in_features": 4096,
546
+ "out_features": 1024,
547
+ "in_factors": [
548
+ 64,
549
+ 64
550
+ ],
551
+ "out_factors": [
552
+ 32,
553
+ 32
554
+ ]
555
+ },
556
+ "model.layers.6.self_attn.o_proj": {
557
+ "in_features": 4096,
558
+ "out_features": 4096,
559
+ "in_factors": [
560
+ 64,
561
+ 64
562
+ ],
563
+ "out_factors": [
564
+ 64,
565
+ 64
566
+ ]
567
+ },
568
+ "model.layers.6.mlp.gate_proj": {
569
+ "in_features": 4096,
570
+ "out_features": 14336,
571
+ "in_factors": [
572
+ 64,
573
+ 64
574
+ ],
575
+ "out_factors": [
576
+ 112,
577
+ 128
578
+ ]
579
+ },
580
+ "model.layers.6.mlp.up_proj": {
581
+ "in_features": 4096,
582
+ "out_features": 14336,
583
+ "in_factors": [
584
+ 64,
585
+ 64
586
+ ],
587
+ "out_factors": [
588
+ 112,
589
+ 128
590
+ ]
591
+ },
592
+ "model.layers.6.mlp.down_proj": {
593
+ "in_features": 14336,
594
+ "out_features": 4096,
595
+ "in_factors": [
596
+ 112,
597
+ 128
598
+ ],
599
+ "out_factors": [
600
+ 64,
601
+ 64
602
+ ]
603
+ },
604
+ "model.layers.7.self_attn.q_proj": {
605
+ "in_features": 4096,
606
+ "out_features": 4096,
607
+ "in_factors": [
608
+ 64,
609
+ 64
610
+ ],
611
+ "out_factors": [
612
+ 64,
613
+ 64
614
+ ]
615
+ },
616
+ "model.layers.7.self_attn.k_proj": {
617
+ "in_features": 4096,
618
+ "out_features": 1024,
619
+ "in_factors": [
620
+ 64,
621
+ 64
622
+ ],
623
+ "out_factors": [
624
+ 32,
625
+ 32
626
+ ]
627
+ },
628
+ "model.layers.7.self_attn.v_proj": {
629
+ "in_features": 4096,
630
+ "out_features": 1024,
631
+ "in_factors": [
632
+ 64,
633
+ 64
634
+ ],
635
+ "out_factors": [
636
+ 32,
637
+ 32
638
+ ]
639
+ },
640
+ "model.layers.7.self_attn.o_proj": {
641
+ "in_features": 4096,
642
+ "out_features": 4096,
643
+ "in_factors": [
644
+ 64,
645
+ 64
646
+ ],
647
+ "out_factors": [
648
+ 64,
649
+ 64
650
+ ]
651
+ },
652
+ "model.layers.7.mlp.gate_proj": {
653
+ "in_features": 4096,
654
+ "out_features": 14336,
655
+ "in_factors": [
656
+ 64,
657
+ 64
658
+ ],
659
+ "out_factors": [
660
+ 112,
661
+ 128
662
+ ]
663
+ },
664
+ "model.layers.7.mlp.up_proj": {
665
+ "in_features": 4096,
666
+ "out_features": 14336,
667
+ "in_factors": [
668
+ 64,
669
+ 64
670
+ ],
671
+ "out_factors": [
672
+ 112,
673
+ 128
674
+ ]
675
+ },
676
+ "model.layers.7.mlp.down_proj": {
677
+ "in_features": 14336,
678
+ "out_features": 4096,
679
+ "in_factors": [
680
+ 112,
681
+ 128
682
+ ],
683
+ "out_factors": [
684
+ 64,
685
+ 64
686
+ ]
687
+ },
688
+ "model.layers.8.self_attn.q_proj": {
689
+ "in_features": 4096,
690
+ "out_features": 4096,
691
+ "in_factors": [
692
+ 64,
693
+ 64
694
+ ],
695
+ "out_factors": [
696
+ 64,
697
+ 64
698
+ ]
699
+ },
700
+ "model.layers.8.self_attn.k_proj": {
701
+ "in_features": 4096,
702
+ "out_features": 1024,
703
+ "in_factors": [
704
+ 64,
705
+ 64
706
+ ],
707
+ "out_factors": [
708
+ 32,
709
+ 32
710
+ ]
711
+ },
712
+ "model.layers.8.self_attn.v_proj": {
713
+ "in_features": 4096,
714
+ "out_features": 1024,
715
+ "in_factors": [
716
+ 64,
717
+ 64
718
+ ],
719
+ "out_factors": [
720
+ 32,
721
+ 32
722
+ ]
723
+ },
724
+ "model.layers.8.self_attn.o_proj": {
725
+ "in_features": 4096,
726
+ "out_features": 4096,
727
+ "in_factors": [
728
+ 64,
729
+ 64
730
+ ],
731
+ "out_factors": [
732
+ 64,
733
+ 64
734
+ ]
735
+ },
736
+ "model.layers.8.mlp.gate_proj": {
737
+ "in_features": 4096,
738
+ "out_features": 14336,
739
+ "in_factors": [
740
+ 64,
741
+ 64
742
+ ],
743
+ "out_factors": [
744
+ 112,
745
+ 128
746
+ ]
747
+ },
748
+ "model.layers.8.mlp.up_proj": {
749
+ "in_features": 4096,
750
+ "out_features": 14336,
751
+ "in_factors": [
752
+ 64,
753
+ 64
754
+ ],
755
+ "out_factors": [
756
+ 112,
757
+ 128
758
+ ]
759
+ },
760
+ "model.layers.8.mlp.down_proj": {
761
+ "in_features": 14336,
762
+ "out_features": 4096,
763
+ "in_factors": [
764
+ 112,
765
+ 128
766
+ ],
767
+ "out_factors": [
768
+ 64,
769
+ 64
770
+ ]
771
+ },
772
+ "model.layers.9.self_attn.q_proj": {
773
+ "in_features": 4096,
774
+ "out_features": 4096,
775
+ "in_factors": [
776
+ 64,
777
+ 64
778
+ ],
779
+ "out_factors": [
780
+ 64,
781
+ 64
782
+ ]
783
+ },
784
+ "model.layers.9.self_attn.k_proj": {
785
+ "in_features": 4096,
786
+ "out_features": 1024,
787
+ "in_factors": [
788
+ 64,
789
+ 64
790
+ ],
791
+ "out_factors": [
792
+ 32,
793
+ 32
794
+ ]
795
+ },
796
+ "model.layers.9.self_attn.v_proj": {
797
+ "in_features": 4096,
798
+ "out_features": 1024,
799
+ "in_factors": [
800
+ 64,
801
+ 64
802
+ ],
803
+ "out_factors": [
804
+ 32,
805
+ 32
806
+ ]
807
+ },
808
+ "model.layers.9.self_attn.o_proj": {
809
+ "in_features": 4096,
810
+ "out_features": 4096,
811
+ "in_factors": [
812
+ 64,
813
+ 64
814
+ ],
815
+ "out_factors": [
816
+ 64,
817
+ 64
818
+ ]
819
+ },
820
+ "model.layers.9.mlp.gate_proj": {
821
+ "in_features": 4096,
822
+ "out_features": 14336,
823
+ "in_factors": [
824
+ 64,
825
+ 64
826
+ ],
827
+ "out_factors": [
828
+ 112,
829
+ 128
830
+ ]
831
+ },
832
+ "model.layers.9.mlp.up_proj": {
833
+ "in_features": 4096,
834
+ "out_features": 14336,
835
+ "in_factors": [
836
+ 64,
837
+ 64
838
+ ],
839
+ "out_factors": [
840
+ 112,
841
+ 128
842
+ ]
843
+ },
844
+ "model.layers.9.mlp.down_proj": {
845
+ "in_features": 14336,
846
+ "out_features": 4096,
847
+ "in_factors": [
848
+ 112,
849
+ 128
850
+ ],
851
+ "out_factors": [
852
+ 64,
853
+ 64
854
+ ]
855
+ },
856
+ "model.layers.10.self_attn.q_proj": {
857
+ "in_features": 4096,
858
+ "out_features": 4096,
859
+ "in_factors": [
860
+ 64,
861
+ 64
862
+ ],
863
+ "out_factors": [
864
+ 64,
865
+ 64
866
+ ]
867
+ },
868
+ "model.layers.10.self_attn.k_proj": {
869
+ "in_features": 4096,
870
+ "out_features": 1024,
871
+ "in_factors": [
872
+ 64,
873
+ 64
874
+ ],
875
+ "out_factors": [
876
+ 32,
877
+ 32
878
+ ]
879
+ },
880
+ "model.layers.10.self_attn.v_proj": {
881
+ "in_features": 4096,
882
+ "out_features": 1024,
883
+ "in_factors": [
884
+ 64,
885
+ 64
886
+ ],
887
+ "out_factors": [
888
+ 32,
889
+ 32
890
+ ]
891
+ },
892
+ "model.layers.10.self_attn.o_proj": {
893
+ "in_features": 4096,
894
+ "out_features": 4096,
895
+ "in_factors": [
896
+ 64,
897
+ 64
898
+ ],
899
+ "out_factors": [
900
+ 64,
901
+ 64
902
+ ]
903
+ },
904
+ "model.layers.10.mlp.gate_proj": {
905
+ "in_features": 4096,
906
+ "out_features": 14336,
907
+ "in_factors": [
908
+ 64,
909
+ 64
910
+ ],
911
+ "out_factors": [
912
+ 112,
913
+ 128
914
+ ]
915
+ },
916
+ "model.layers.10.mlp.up_proj": {
917
+ "in_features": 4096,
918
+ "out_features": 14336,
919
+ "in_factors": [
920
+ 64,
921
+ 64
922
+ ],
923
+ "out_factors": [
924
+ 112,
925
+ 128
926
+ ]
927
+ },
928
+ "model.layers.10.mlp.down_proj": {
929
+ "in_features": 14336,
930
+ "out_features": 4096,
931
+ "in_factors": [
932
+ 112,
933
+ 128
934
+ ],
935
+ "out_factors": [
936
+ 64,
937
+ 64
938
+ ]
939
+ },
940
+ "model.layers.11.self_attn.q_proj": {
941
+ "in_features": 4096,
942
+ "out_features": 4096,
943
+ "in_factors": [
944
+ 64,
945
+ 64
946
+ ],
947
+ "out_factors": [
948
+ 64,
949
+ 64
950
+ ]
951
+ },
952
+ "model.layers.11.self_attn.k_proj": {
953
+ "in_features": 4096,
954
+ "out_features": 1024,
955
+ "in_factors": [
956
+ 64,
957
+ 64
958
+ ],
959
+ "out_factors": [
960
+ 32,
961
+ 32
962
+ ]
963
+ },
964
+ "model.layers.11.self_attn.v_proj": {
965
+ "in_features": 4096,
966
+ "out_features": 1024,
967
+ "in_factors": [
968
+ 64,
969
+ 64
970
+ ],
971
+ "out_factors": [
972
+ 32,
973
+ 32
974
+ ]
975
+ },
976
+ "model.layers.11.self_attn.o_proj": {
977
+ "in_features": 4096,
978
+ "out_features": 4096,
979
+ "in_factors": [
980
+ 64,
981
+ 64
982
+ ],
983
+ "out_factors": [
984
+ 64,
985
+ 64
986
+ ]
987
+ },
988
+ "model.layers.11.mlp.gate_proj": {
989
+ "in_features": 4096,
990
+ "out_features": 14336,
991
+ "in_factors": [
992
+ 64,
993
+ 64
994
+ ],
995
+ "out_factors": [
996
+ 112,
997
+ 128
998
+ ]
999
+ },
1000
+ "model.layers.11.mlp.up_proj": {
1001
+ "in_features": 4096,
1002
+ "out_features": 14336,
1003
+ "in_factors": [
1004
+ 64,
1005
+ 64
1006
+ ],
1007
+ "out_factors": [
1008
+ 112,
1009
+ 128
1010
+ ]
1011
+ },
1012
+ "model.layers.11.mlp.down_proj": {
1013
+ "in_features": 14336,
1014
+ "out_features": 4096,
1015
+ "in_factors": [
1016
+ 112,
1017
+ 128
1018
+ ],
1019
+ "out_factors": [
1020
+ 64,
1021
+ 64
1022
+ ]
1023
+ },
1024
+ "model.layers.12.self_attn.q_proj": {
1025
+ "in_features": 4096,
1026
+ "out_features": 4096,
1027
+ "in_factors": [
1028
+ 64,
1029
+ 64
1030
+ ],
1031
+ "out_factors": [
1032
+ 64,
1033
+ 64
1034
+ ]
1035
+ },
1036
+ "model.layers.12.self_attn.k_proj": {
1037
+ "in_features": 4096,
1038
+ "out_features": 1024,
1039
+ "in_factors": [
1040
+ 64,
1041
+ 64
1042
+ ],
1043
+ "out_factors": [
1044
+ 32,
1045
+ 32
1046
+ ]
1047
+ },
1048
+ "model.layers.12.self_attn.v_proj": {
1049
+ "in_features": 4096,
1050
+ "out_features": 1024,
1051
+ "in_factors": [
1052
+ 64,
1053
+ 64
1054
+ ],
1055
+ "out_factors": [
1056
+ 32,
1057
+ 32
1058
+ ]
1059
+ },
1060
+ "model.layers.12.self_attn.o_proj": {
1061
+ "in_features": 4096,
1062
+ "out_features": 4096,
1063
+ "in_factors": [
1064
+ 64,
1065
+ 64
1066
+ ],
1067
+ "out_factors": [
1068
+ 64,
1069
+ 64
1070
+ ]
1071
+ },
1072
+ "model.layers.12.mlp.gate_proj": {
1073
+ "in_features": 4096,
1074
+ "out_features": 14336,
1075
+ "in_factors": [
1076
+ 64,
1077
+ 64
1078
+ ],
1079
+ "out_factors": [
1080
+ 112,
1081
+ 128
1082
+ ]
1083
+ },
1084
+ "model.layers.12.mlp.up_proj": {
1085
+ "in_features": 4096,
1086
+ "out_features": 14336,
1087
+ "in_factors": [
1088
+ 64,
1089
+ 64
1090
+ ],
1091
+ "out_factors": [
1092
+ 112,
1093
+ 128
1094
+ ]
1095
+ },
1096
+ "model.layers.12.mlp.down_proj": {
1097
+ "in_features": 14336,
1098
+ "out_features": 4096,
1099
+ "in_factors": [
1100
+ 112,
1101
+ 128
1102
+ ],
1103
+ "out_factors": [
1104
+ 64,
1105
+ 64
1106
+ ]
1107
+ },
1108
+ "model.layers.13.self_attn.q_proj": {
1109
+ "in_features": 4096,
1110
+ "out_features": 4096,
1111
+ "in_factors": [
1112
+ 64,
1113
+ 64
1114
+ ],
1115
+ "out_factors": [
1116
+ 64,
1117
+ 64
1118
+ ]
1119
+ },
1120
+ "model.layers.13.self_attn.k_proj": {
1121
+ "in_features": 4096,
1122
+ "out_features": 1024,
1123
+ "in_factors": [
1124
+ 64,
1125
+ 64
1126
+ ],
1127
+ "out_factors": [
1128
+ 32,
1129
+ 32
1130
+ ]
1131
+ },
1132
+ "model.layers.13.self_attn.v_proj": {
1133
+ "in_features": 4096,
1134
+ "out_features": 1024,
1135
+ "in_factors": [
1136
+ 64,
1137
+ 64
1138
+ ],
1139
+ "out_factors": [
1140
+ 32,
1141
+ 32
1142
+ ]
1143
+ },
1144
+ "model.layers.13.self_attn.o_proj": {
1145
+ "in_features": 4096,
1146
+ "out_features": 4096,
1147
+ "in_factors": [
1148
+ 64,
1149
+ 64
1150
+ ],
1151
+ "out_factors": [
1152
+ 64,
1153
+ 64
1154
+ ]
1155
+ },
1156
+ "model.layers.13.mlp.gate_proj": {
1157
+ "in_features": 4096,
1158
+ "out_features": 14336,
1159
+ "in_factors": [
1160
+ 64,
1161
+ 64
1162
+ ],
1163
+ "out_factors": [
1164
+ 112,
1165
+ 128
1166
+ ]
1167
+ },
1168
+ "model.layers.13.mlp.up_proj": {
1169
+ "in_features": 4096,
1170
+ "out_features": 14336,
1171
+ "in_factors": [
1172
+ 64,
1173
+ 64
1174
+ ],
1175
+ "out_factors": [
1176
+ 112,
1177
+ 128
1178
+ ]
1179
+ },
1180
+ "model.layers.13.mlp.down_proj": {
1181
+ "in_features": 14336,
1182
+ "out_features": 4096,
1183
+ "in_factors": [
1184
+ 112,
1185
+ 128
1186
+ ],
1187
+ "out_factors": [
1188
+ 64,
1189
+ 64
1190
+ ]
1191
+ },
1192
+ "model.layers.14.self_attn.q_proj": {
1193
+ "in_features": 4096,
1194
+ "out_features": 4096,
1195
+ "in_factors": [
1196
+ 64,
1197
+ 64
1198
+ ],
1199
+ "out_factors": [
1200
+ 64,
1201
+ 64
1202
+ ]
1203
+ },
1204
+ "model.layers.14.self_attn.k_proj": {
1205
+ "in_features": 4096,
1206
+ "out_features": 1024,
1207
+ "in_factors": [
1208
+ 64,
1209
+ 64
1210
+ ],
1211
+ "out_factors": [
1212
+ 32,
1213
+ 32
1214
+ ]
1215
+ },
1216
+ "model.layers.14.self_attn.v_proj": {
1217
+ "in_features": 4096,
1218
+ "out_features": 1024,
1219
+ "in_factors": [
1220
+ 64,
1221
+ 64
1222
+ ],
1223
+ "out_factors": [
1224
+ 32,
1225
+ 32
1226
+ ]
1227
+ },
1228
+ "model.layers.14.self_attn.o_proj": {
1229
+ "in_features": 4096,
1230
+ "out_features": 4096,
1231
+ "in_factors": [
1232
+ 64,
1233
+ 64
1234
+ ],
1235
+ "out_factors": [
1236
+ 64,
1237
+ 64
1238
+ ]
1239
+ },
1240
+ "model.layers.14.mlp.gate_proj": {
1241
+ "in_features": 4096,
1242
+ "out_features": 14336,
1243
+ "in_factors": [
1244
+ 64,
1245
+ 64
1246
+ ],
1247
+ "out_factors": [
1248
+ 112,
1249
+ 128
1250
+ ]
1251
+ },
1252
+ "model.layers.14.mlp.up_proj": {
1253
+ "in_features": 4096,
1254
+ "out_features": 14336,
1255
+ "in_factors": [
1256
+ 64,
1257
+ 64
1258
+ ],
1259
+ "out_factors": [
1260
+ 112,
1261
+ 128
1262
+ ]
1263
+ },
1264
+ "model.layers.14.mlp.down_proj": {
1265
+ "in_features": 14336,
1266
+ "out_features": 4096,
1267
+ "in_factors": [
1268
+ 112,
1269
+ 128
1270
+ ],
1271
+ "out_factors": [
1272
+ 64,
1273
+ 64
1274
+ ]
1275
+ },
1276
+ "model.layers.15.self_attn.q_proj": {
1277
+ "in_features": 4096,
1278
+ "out_features": 4096,
1279
+ "in_factors": [
1280
+ 64,
1281
+ 64
1282
+ ],
1283
+ "out_factors": [
1284
+ 64,
1285
+ 64
1286
+ ]
1287
+ },
1288
+ "model.layers.15.self_attn.k_proj": {
1289
+ "in_features": 4096,
1290
+ "out_features": 1024,
1291
+ "in_factors": [
1292
+ 64,
1293
+ 64
1294
+ ],
1295
+ "out_factors": [
1296
+ 32,
1297
+ 32
1298
+ ]
1299
+ },
1300
+ "model.layers.15.self_attn.v_proj": {
1301
+ "in_features": 4096,
1302
+ "out_features": 1024,
1303
+ "in_factors": [
1304
+ 64,
1305
+ 64
1306
+ ],
1307
+ "out_factors": [
1308
+ 32,
1309
+ 32
1310
+ ]
1311
+ },
1312
+ "model.layers.15.self_attn.o_proj": {
1313
+ "in_features": 4096,
1314
+ "out_features": 4096,
1315
+ "in_factors": [
1316
+ 64,
1317
+ 64
1318
+ ],
1319
+ "out_factors": [
1320
+ 64,
1321
+ 64
1322
+ ]
1323
+ },
1324
+ "model.layers.15.mlp.gate_proj": {
1325
+ "in_features": 4096,
1326
+ "out_features": 14336,
1327
+ "in_factors": [
1328
+ 64,
1329
+ 64
1330
+ ],
1331
+ "out_factors": [
1332
+ 112,
1333
+ 128
1334
+ ]
1335
+ },
1336
+ "model.layers.15.mlp.up_proj": {
1337
+ "in_features": 4096,
1338
+ "out_features": 14336,
1339
+ "in_factors": [
1340
+ 64,
1341
+ 64
1342
+ ],
1343
+ "out_factors": [
1344
+ 112,
1345
+ 128
1346
+ ]
1347
+ },
1348
+ "model.layers.15.mlp.down_proj": {
1349
+ "in_features": 14336,
1350
+ "out_features": 4096,
1351
+ "in_factors": [
1352
+ 112,
1353
+ 128
1354
+ ],
1355
+ "out_factors": [
1356
+ 64,
1357
+ 64
1358
+ ]
1359
+ },
1360
+ "model.layers.16.self_attn.q_proj": {
1361
+ "in_features": 4096,
1362
+ "out_features": 4096,
1363
+ "in_factors": [
1364
+ 64,
1365
+ 64
1366
+ ],
1367
+ "out_factors": [
1368
+ 64,
1369
+ 64
1370
+ ]
1371
+ },
1372
+ "model.layers.16.self_attn.k_proj": {
1373
+ "in_features": 4096,
1374
+ "out_features": 1024,
1375
+ "in_factors": [
1376
+ 64,
1377
+ 64
1378
+ ],
1379
+ "out_factors": [
1380
+ 32,
1381
+ 32
1382
+ ]
1383
+ },
1384
+ "model.layers.16.self_attn.v_proj": {
1385
+ "in_features": 4096,
1386
+ "out_features": 1024,
1387
+ "in_factors": [
1388
+ 64,
1389
+ 64
1390
+ ],
1391
+ "out_factors": [
1392
+ 32,
1393
+ 32
1394
+ ]
1395
+ },
1396
+ "model.layers.16.self_attn.o_proj": {
1397
+ "in_features": 4096,
1398
+ "out_features": 4096,
1399
+ "in_factors": [
1400
+ 64,
1401
+ 64
1402
+ ],
1403
+ "out_factors": [
1404
+ 64,
1405
+ 64
1406
+ ]
1407
+ },
1408
+ "model.layers.16.mlp.gate_proj": {
1409
+ "in_features": 4096,
1410
+ "out_features": 14336,
1411
+ "in_factors": [
1412
+ 64,
1413
+ 64
1414
+ ],
1415
+ "out_factors": [
1416
+ 112,
1417
+ 128
1418
+ ]
1419
+ },
1420
+ "model.layers.16.mlp.up_proj": {
1421
+ "in_features": 4096,
1422
+ "out_features": 14336,
1423
+ "in_factors": [
1424
+ 64,
1425
+ 64
1426
+ ],
1427
+ "out_factors": [
1428
+ 112,
1429
+ 128
1430
+ ]
1431
+ },
1432
+ "model.layers.16.mlp.down_proj": {
1433
+ "in_features": 14336,
1434
+ "out_features": 4096,
1435
+ "in_factors": [
1436
+ 112,
1437
+ 128
1438
+ ],
1439
+ "out_factors": [
1440
+ 64,
1441
+ 64
1442
+ ]
1443
+ },
1444
+ "model.layers.17.self_attn.q_proj": {
1445
+ "in_features": 4096,
1446
+ "out_features": 4096,
1447
+ "in_factors": [
1448
+ 64,
1449
+ 64
1450
+ ],
1451
+ "out_factors": [
1452
+ 64,
1453
+ 64
1454
+ ]
1455
+ },
1456
+ "model.layers.17.self_attn.k_proj": {
1457
+ "in_features": 4096,
1458
+ "out_features": 1024,
1459
+ "in_factors": [
1460
+ 64,
1461
+ 64
1462
+ ],
1463
+ "out_factors": [
1464
+ 32,
1465
+ 32
1466
+ ]
1467
+ },
1468
+ "model.layers.17.self_attn.v_proj": {
1469
+ "in_features": 4096,
1470
+ "out_features": 1024,
1471
+ "in_factors": [
1472
+ 64,
1473
+ 64
1474
+ ],
1475
+ "out_factors": [
1476
+ 32,
1477
+ 32
1478
+ ]
1479
+ },
1480
+ "model.layers.17.self_attn.o_proj": {
1481
+ "in_features": 4096,
1482
+ "out_features": 4096,
1483
+ "in_factors": [
1484
+ 64,
1485
+ 64
1486
+ ],
1487
+ "out_factors": [
1488
+ 64,
1489
+ 64
1490
+ ]
1491
+ },
1492
+ "model.layers.17.mlp.gate_proj": {
1493
+ "in_features": 4096,
1494
+ "out_features": 14336,
1495
+ "in_factors": [
1496
+ 64,
1497
+ 64
1498
+ ],
1499
+ "out_factors": [
1500
+ 112,
1501
+ 128
1502
+ ]
1503
+ },
1504
+ "model.layers.17.mlp.up_proj": {
1505
+ "in_features": 4096,
1506
+ "out_features": 14336,
1507
+ "in_factors": [
1508
+ 64,
1509
+ 64
1510
+ ],
1511
+ "out_factors": [
1512
+ 112,
1513
+ 128
1514
+ ]
1515
+ },
1516
+ "model.layers.17.mlp.down_proj": {
1517
+ "in_features": 14336,
1518
+ "out_features": 4096,
1519
+ "in_factors": [
1520
+ 112,
1521
+ 128
1522
+ ],
1523
+ "out_factors": [
1524
+ 64,
1525
+ 64
1526
+ ]
1527
+ },
1528
+ "model.layers.18.self_attn.q_proj": {
1529
+ "in_features": 4096,
1530
+ "out_features": 4096,
1531
+ "in_factors": [
1532
+ 64,
1533
+ 64
1534
+ ],
1535
+ "out_factors": [
1536
+ 64,
1537
+ 64
1538
+ ]
1539
+ },
1540
+ "model.layers.18.self_attn.k_proj": {
1541
+ "in_features": 4096,
1542
+ "out_features": 1024,
1543
+ "in_factors": [
1544
+ 64,
1545
+ 64
1546
+ ],
1547
+ "out_factors": [
1548
+ 32,
1549
+ 32
1550
+ ]
1551
+ },
1552
+ "model.layers.18.self_attn.v_proj": {
1553
+ "in_features": 4096,
1554
+ "out_features": 1024,
1555
+ "in_factors": [
1556
+ 64,
1557
+ 64
1558
+ ],
1559
+ "out_factors": [
1560
+ 32,
1561
+ 32
1562
+ ]
1563
+ },
1564
+ "model.layers.18.self_attn.o_proj": {
1565
+ "in_features": 4096,
1566
+ "out_features": 4096,
1567
+ "in_factors": [
1568
+ 64,
1569
+ 64
1570
+ ],
1571
+ "out_factors": [
1572
+ 64,
1573
+ 64
1574
+ ]
1575
+ },
1576
+ "model.layers.18.mlp.gate_proj": {
1577
+ "in_features": 4096,
1578
+ "out_features": 14336,
1579
+ "in_factors": [
1580
+ 64,
1581
+ 64
1582
+ ],
1583
+ "out_factors": [
1584
+ 112,
1585
+ 128
1586
+ ]
1587
+ },
1588
+ "model.layers.18.mlp.up_proj": {
1589
+ "in_features": 4096,
1590
+ "out_features": 14336,
1591
+ "in_factors": [
1592
+ 64,
1593
+ 64
1594
+ ],
1595
+ "out_factors": [
1596
+ 112,
1597
+ 128
1598
+ ]
1599
+ },
1600
+ "model.layers.18.mlp.down_proj": {
1601
+ "in_features": 14336,
1602
+ "out_features": 4096,
1603
+ "in_factors": [
1604
+ 112,
1605
+ 128
1606
+ ],
1607
+ "out_factors": [
1608
+ 64,
1609
+ 64
1610
+ ]
1611
+ },
1612
+ "model.layers.19.self_attn.q_proj": {
1613
+ "in_features": 4096,
1614
+ "out_features": 4096,
1615
+ "in_factors": [
1616
+ 64,
1617
+ 64
1618
+ ],
1619
+ "out_factors": [
1620
+ 64,
1621
+ 64
1622
+ ]
1623
+ },
1624
+ "model.layers.19.self_attn.k_proj": {
1625
+ "in_features": 4096,
1626
+ "out_features": 1024,
1627
+ "in_factors": [
1628
+ 64,
1629
+ 64
1630
+ ],
1631
+ "out_factors": [
1632
+ 32,
1633
+ 32
1634
+ ]
1635
+ },
1636
+ "model.layers.19.self_attn.v_proj": {
1637
+ "in_features": 4096,
1638
+ "out_features": 1024,
1639
+ "in_factors": [
1640
+ 64,
1641
+ 64
1642
+ ],
1643
+ "out_factors": [
1644
+ 32,
1645
+ 32
1646
+ ]
1647
+ },
1648
+ "model.layers.19.self_attn.o_proj": {
1649
+ "in_features": 4096,
1650
+ "out_features": 4096,
1651
+ "in_factors": [
1652
+ 64,
1653
+ 64
1654
+ ],
1655
+ "out_factors": [
1656
+ 64,
1657
+ 64
1658
+ ]
1659
+ },
1660
+ "model.layers.19.mlp.gate_proj": {
1661
+ "in_features": 4096,
1662
+ "out_features": 14336,
1663
+ "in_factors": [
1664
+ 64,
1665
+ 64
1666
+ ],
1667
+ "out_factors": [
1668
+ 112,
1669
+ 128
1670
+ ]
1671
+ },
1672
+ "model.layers.19.mlp.up_proj": {
1673
+ "in_features": 4096,
1674
+ "out_features": 14336,
1675
+ "in_factors": [
1676
+ 64,
1677
+ 64
1678
+ ],
1679
+ "out_factors": [
1680
+ 112,
1681
+ 128
1682
+ ]
1683
+ },
1684
+ "model.layers.19.mlp.down_proj": {
1685
+ "in_features": 14336,
1686
+ "out_features": 4096,
1687
+ "in_factors": [
1688
+ 112,
1689
+ 128
1690
+ ],
1691
+ "out_factors": [
1692
+ 64,
1693
+ 64
1694
+ ]
1695
+ },
1696
+ "model.layers.20.self_attn.q_proj": {
1697
+ "in_features": 4096,
1698
+ "out_features": 4096,
1699
+ "in_factors": [
1700
+ 64,
1701
+ 64
1702
+ ],
1703
+ "out_factors": [
1704
+ 64,
1705
+ 64
1706
+ ]
1707
+ },
1708
+ "model.layers.20.self_attn.k_proj": {
1709
+ "in_features": 4096,
1710
+ "out_features": 1024,
1711
+ "in_factors": [
1712
+ 64,
1713
+ 64
1714
+ ],
1715
+ "out_factors": [
1716
+ 32,
1717
+ 32
1718
+ ]
1719
+ },
1720
+ "model.layers.20.self_attn.v_proj": {
1721
+ "in_features": 4096,
1722
+ "out_features": 1024,
1723
+ "in_factors": [
1724
+ 64,
1725
+ 64
1726
+ ],
1727
+ "out_factors": [
1728
+ 32,
1729
+ 32
1730
+ ]
1731
+ },
1732
+ "model.layers.20.self_attn.o_proj": {
1733
+ "in_features": 4096,
1734
+ "out_features": 4096,
1735
+ "in_factors": [
1736
+ 64,
1737
+ 64
1738
+ ],
1739
+ "out_factors": [
1740
+ 64,
1741
+ 64
1742
+ ]
1743
+ },
1744
+ "model.layers.20.mlp.gate_proj": {
1745
+ "in_features": 4096,
1746
+ "out_features": 14336,
1747
+ "in_factors": [
1748
+ 64,
1749
+ 64
1750
+ ],
1751
+ "out_factors": [
1752
+ 112,
1753
+ 128
1754
+ ]
1755
+ },
1756
+ "model.layers.20.mlp.up_proj": {
1757
+ "in_features": 4096,
1758
+ "out_features": 14336,
1759
+ "in_factors": [
1760
+ 64,
1761
+ 64
1762
+ ],
1763
+ "out_factors": [
1764
+ 112,
1765
+ 128
1766
+ ]
1767
+ },
1768
+ "model.layers.20.mlp.down_proj": {
1769
+ "in_features": 14336,
1770
+ "out_features": 4096,
1771
+ "in_factors": [
1772
+ 112,
1773
+ 128
1774
+ ],
1775
+ "out_factors": [
1776
+ 64,
1777
+ 64
1778
+ ]
1779
+ },
1780
+ "model.layers.21.self_attn.q_proj": {
1781
+ "in_features": 4096,
1782
+ "out_features": 4096,
1783
+ "in_factors": [
1784
+ 64,
1785
+ 64
1786
+ ],
1787
+ "out_factors": [
1788
+ 64,
1789
+ 64
1790
+ ]
1791
+ },
1792
+ "model.layers.21.self_attn.k_proj": {
1793
+ "in_features": 4096,
1794
+ "out_features": 1024,
1795
+ "in_factors": [
1796
+ 64,
1797
+ 64
1798
+ ],
1799
+ "out_factors": [
1800
+ 32,
1801
+ 32
1802
+ ]
1803
+ },
1804
+ "model.layers.21.self_attn.v_proj": {
1805
+ "in_features": 4096,
1806
+ "out_features": 1024,
1807
+ "in_factors": [
1808
+ 64,
1809
+ 64
1810
+ ],
1811
+ "out_factors": [
1812
+ 32,
1813
+ 32
1814
+ ]
1815
+ },
1816
+ "model.layers.21.self_attn.o_proj": {
1817
+ "in_features": 4096,
1818
+ "out_features": 4096,
1819
+ "in_factors": [
1820
+ 64,
1821
+ 64
1822
+ ],
1823
+ "out_factors": [
1824
+ 64,
1825
+ 64
1826
+ ]
1827
+ },
1828
+ "model.layers.21.mlp.gate_proj": {
1829
+ "in_features": 4096,
1830
+ "out_features": 14336,
1831
+ "in_factors": [
1832
+ 64,
1833
+ 64
1834
+ ],
1835
+ "out_factors": [
1836
+ 112,
1837
+ 128
1838
+ ]
1839
+ },
1840
+ "model.layers.21.mlp.up_proj": {
1841
+ "in_features": 4096,
1842
+ "out_features": 14336,
1843
+ "in_factors": [
1844
+ 64,
1845
+ 64
1846
+ ],
1847
+ "out_factors": [
1848
+ 112,
1849
+ 128
1850
+ ]
1851
+ },
1852
+ "model.layers.21.mlp.down_proj": {
1853
+ "in_features": 14336,
1854
+ "out_features": 4096,
1855
+ "in_factors": [
1856
+ 112,
1857
+ 128
1858
+ ],
1859
+ "out_factors": [
1860
+ 64,
1861
+ 64
1862
+ ]
1863
+ },
1864
+ "model.layers.22.self_attn.q_proj": {
1865
+ "in_features": 4096,
1866
+ "out_features": 4096,
1867
+ "in_factors": [
1868
+ 64,
1869
+ 64
1870
+ ],
1871
+ "out_factors": [
1872
+ 64,
1873
+ 64
1874
+ ]
1875
+ },
1876
+ "model.layers.22.self_attn.k_proj": {
1877
+ "in_features": 4096,
1878
+ "out_features": 1024,
1879
+ "in_factors": [
1880
+ 64,
1881
+ 64
1882
+ ],
1883
+ "out_factors": [
1884
+ 32,
1885
+ 32
1886
+ ]
1887
+ },
1888
+ "model.layers.22.self_attn.v_proj": {
1889
+ "in_features": 4096,
1890
+ "out_features": 1024,
1891
+ "in_factors": [
1892
+ 64,
1893
+ 64
1894
+ ],
1895
+ "out_factors": [
1896
+ 32,
1897
+ 32
1898
+ ]
1899
+ },
1900
+ "model.layers.22.self_attn.o_proj": {
1901
+ "in_features": 4096,
1902
+ "out_features": 4096,
1903
+ "in_factors": [
1904
+ 64,
1905
+ 64
1906
+ ],
1907
+ "out_factors": [
1908
+ 64,
1909
+ 64
1910
+ ]
1911
+ },
1912
+ "model.layers.22.mlp.gate_proj": {
1913
+ "in_features": 4096,
1914
+ "out_features": 14336,
1915
+ "in_factors": [
1916
+ 64,
1917
+ 64
1918
+ ],
1919
+ "out_factors": [
1920
+ 112,
1921
+ 128
1922
+ ]
1923
+ },
1924
+ "model.layers.22.mlp.up_proj": {
1925
+ "in_features": 4096,
1926
+ "out_features": 14336,
1927
+ "in_factors": [
1928
+ 64,
1929
+ 64
1930
+ ],
1931
+ "out_factors": [
1932
+ 112,
1933
+ 128
1934
+ ]
1935
+ },
1936
+ "model.layers.22.mlp.down_proj": {
1937
+ "in_features": 14336,
1938
+ "out_features": 4096,
1939
+ "in_factors": [
1940
+ 112,
1941
+ 128
1942
+ ],
1943
+ "out_factors": [
1944
+ 64,
1945
+ 64
1946
+ ]
1947
+ },
1948
+ "model.layers.23.self_attn.q_proj": {
1949
+ "in_features": 4096,
1950
+ "out_features": 4096,
1951
+ "in_factors": [
1952
+ 64,
1953
+ 64
1954
+ ],
1955
+ "out_factors": [
1956
+ 64,
1957
+ 64
1958
+ ]
1959
+ },
1960
+ "model.layers.23.self_attn.k_proj": {
1961
+ "in_features": 4096,
1962
+ "out_features": 1024,
1963
+ "in_factors": [
1964
+ 64,
1965
+ 64
1966
+ ],
1967
+ "out_factors": [
1968
+ 32,
1969
+ 32
1970
+ ]
1971
+ },
1972
+ "model.layers.23.self_attn.v_proj": {
1973
+ "in_features": 4096,
1974
+ "out_features": 1024,
1975
+ "in_factors": [
1976
+ 64,
1977
+ 64
1978
+ ],
1979
+ "out_factors": [
1980
+ 32,
1981
+ 32
1982
+ ]
1983
+ },
1984
+ "model.layers.23.self_attn.o_proj": {
1985
+ "in_features": 4096,
1986
+ "out_features": 4096,
1987
+ "in_factors": [
1988
+ 64,
1989
+ 64
1990
+ ],
1991
+ "out_factors": [
1992
+ 64,
1993
+ 64
1994
+ ]
1995
+ },
1996
+ "model.layers.23.mlp.gate_proj": {
1997
+ "in_features": 4096,
1998
+ "out_features": 14336,
1999
+ "in_factors": [
2000
+ 64,
2001
+ 64
2002
+ ],
2003
+ "out_factors": [
2004
+ 112,
2005
+ 128
2006
+ ]
2007
+ },
2008
+ "model.layers.23.mlp.up_proj": {
2009
+ "in_features": 4096,
2010
+ "out_features": 14336,
2011
+ "in_factors": [
2012
+ 64,
2013
+ 64
2014
+ ],
2015
+ "out_factors": [
2016
+ 112,
2017
+ 128
2018
+ ]
2019
+ },
2020
+ "model.layers.23.mlp.down_proj": {
2021
+ "in_features": 14336,
2022
+ "out_features": 4096,
2023
+ "in_factors": [
2024
+ 112,
2025
+ 128
2026
+ ],
2027
+ "out_factors": [
2028
+ 64,
2029
+ 64
2030
+ ]
2031
+ },
2032
+ "model.layers.24.self_attn.q_proj": {
2033
+ "in_features": 4096,
2034
+ "out_features": 4096,
2035
+ "in_factors": [
2036
+ 64,
2037
+ 64
2038
+ ],
2039
+ "out_factors": [
2040
+ 64,
2041
+ 64
2042
+ ]
2043
+ },
2044
+ "model.layers.24.self_attn.k_proj": {
2045
+ "in_features": 4096,
2046
+ "out_features": 1024,
2047
+ "in_factors": [
2048
+ 64,
2049
+ 64
2050
+ ],
2051
+ "out_factors": [
2052
+ 32,
2053
+ 32
2054
+ ]
2055
+ },
2056
+ "model.layers.24.self_attn.v_proj": {
2057
+ "in_features": 4096,
2058
+ "out_features": 1024,
2059
+ "in_factors": [
2060
+ 64,
2061
+ 64
2062
+ ],
2063
+ "out_factors": [
2064
+ 32,
2065
+ 32
2066
+ ]
2067
+ },
2068
+ "model.layers.24.self_attn.o_proj": {
2069
+ "in_features": 4096,
2070
+ "out_features": 4096,
2071
+ "in_factors": [
2072
+ 64,
2073
+ 64
2074
+ ],
2075
+ "out_factors": [
2076
+ 64,
2077
+ 64
2078
+ ]
2079
+ },
2080
+ "model.layers.24.mlp.gate_proj": {
2081
+ "in_features": 4096,
2082
+ "out_features": 14336,
2083
+ "in_factors": [
2084
+ 64,
2085
+ 64
2086
+ ],
2087
+ "out_factors": [
2088
+ 112,
2089
+ 128
2090
+ ]
2091
+ },
2092
+ "model.layers.24.mlp.up_proj": {
2093
+ "in_features": 4096,
2094
+ "out_features": 14336,
2095
+ "in_factors": [
2096
+ 64,
2097
+ 64
2098
+ ],
2099
+ "out_factors": [
2100
+ 112,
2101
+ 128
2102
+ ]
2103
+ },
2104
+ "model.layers.24.mlp.down_proj": {
2105
+ "in_features": 14336,
2106
+ "out_features": 4096,
2107
+ "in_factors": [
2108
+ 112,
2109
+ 128
2110
+ ],
2111
+ "out_factors": [
2112
+ 64,
2113
+ 64
2114
+ ]
2115
+ },
2116
+ "model.layers.25.self_attn.q_proj": {
2117
+ "in_features": 4096,
2118
+ "out_features": 4096,
2119
+ "in_factors": [
2120
+ 64,
2121
+ 64
2122
+ ],
2123
+ "out_factors": [
2124
+ 64,
2125
+ 64
2126
+ ]
2127
+ },
2128
+ "model.layers.25.self_attn.k_proj": {
2129
+ "in_features": 4096,
2130
+ "out_features": 1024,
2131
+ "in_factors": [
2132
+ 64,
2133
+ 64
2134
+ ],
2135
+ "out_factors": [
2136
+ 32,
2137
+ 32
2138
+ ]
2139
+ },
2140
+ "model.layers.25.self_attn.v_proj": {
2141
+ "in_features": 4096,
2142
+ "out_features": 1024,
2143
+ "in_factors": [
2144
+ 64,
2145
+ 64
2146
+ ],
2147
+ "out_factors": [
2148
+ 32,
2149
+ 32
2150
+ ]
2151
+ },
2152
+ "model.layers.25.self_attn.o_proj": {
2153
+ "in_features": 4096,
2154
+ "out_features": 4096,
2155
+ "in_factors": [
2156
+ 64,
2157
+ 64
2158
+ ],
2159
+ "out_factors": [
2160
+ 64,
2161
+ 64
2162
+ ]
2163
+ },
2164
+ "model.layers.25.mlp.gate_proj": {
2165
+ "in_features": 4096,
2166
+ "out_features": 14336,
2167
+ "in_factors": [
2168
+ 64,
2169
+ 64
2170
+ ],
2171
+ "out_factors": [
2172
+ 112,
2173
+ 128
2174
+ ]
2175
+ },
2176
+ "model.layers.25.mlp.up_proj": {
2177
+ "in_features": 4096,
2178
+ "out_features": 14336,
2179
+ "in_factors": [
2180
+ 64,
2181
+ 64
2182
+ ],
2183
+ "out_factors": [
2184
+ 112,
2185
+ 128
2186
+ ]
2187
+ },
2188
+ "model.layers.25.mlp.down_proj": {
2189
+ "in_features": 14336,
2190
+ "out_features": 4096,
2191
+ "in_factors": [
2192
+ 112,
2193
+ 128
2194
+ ],
2195
+ "out_factors": [
2196
+ 64,
2197
+ 64
2198
+ ]
2199
+ },
2200
+ "model.layers.26.self_attn.q_proj": {
2201
+ "in_features": 4096,
2202
+ "out_features": 4096,
2203
+ "in_factors": [
2204
+ 64,
2205
+ 64
2206
+ ],
2207
+ "out_factors": [
2208
+ 64,
2209
+ 64
2210
+ ]
2211
+ },
2212
+ "model.layers.26.self_attn.k_proj": {
2213
+ "in_features": 4096,
2214
+ "out_features": 1024,
2215
+ "in_factors": [
2216
+ 64,
2217
+ 64
2218
+ ],
2219
+ "out_factors": [
2220
+ 32,
2221
+ 32
2222
+ ]
2223
+ },
2224
+ "model.layers.26.self_attn.v_proj": {
2225
+ "in_features": 4096,
2226
+ "out_features": 1024,
2227
+ "in_factors": [
2228
+ 64,
2229
+ 64
2230
+ ],
2231
+ "out_factors": [
2232
+ 32,
2233
+ 32
2234
+ ]
2235
+ },
2236
+ "model.layers.26.self_attn.o_proj": {
2237
+ "in_features": 4096,
2238
+ "out_features": 4096,
2239
+ "in_factors": [
2240
+ 64,
2241
+ 64
2242
+ ],
2243
+ "out_factors": [
2244
+ 64,
2245
+ 64
2246
+ ]
2247
+ },
2248
+ "model.layers.26.mlp.gate_proj": {
2249
+ "in_features": 4096,
2250
+ "out_features": 14336,
2251
+ "in_factors": [
2252
+ 64,
2253
+ 64
2254
+ ],
2255
+ "out_factors": [
2256
+ 112,
2257
+ 128
2258
+ ]
2259
+ },
2260
+ "model.layers.26.mlp.up_proj": {
2261
+ "in_features": 4096,
2262
+ "out_features": 14336,
2263
+ "in_factors": [
2264
+ 64,
2265
+ 64
2266
+ ],
2267
+ "out_factors": [
2268
+ 112,
2269
+ 128
2270
+ ]
2271
+ },
2272
+ "model.layers.26.mlp.down_proj": {
2273
+ "in_features": 14336,
2274
+ "out_features": 4096,
2275
+ "in_factors": [
2276
+ 112,
2277
+ 128
2278
+ ],
2279
+ "out_factors": [
2280
+ 64,
2281
+ 64
2282
+ ]
2283
+ },
2284
+ "model.layers.27.self_attn.q_proj": {
2285
+ "in_features": 4096,
2286
+ "out_features": 4096,
2287
+ "in_factors": [
2288
+ 64,
2289
+ 64
2290
+ ],
2291
+ "out_factors": [
2292
+ 64,
2293
+ 64
2294
+ ]
2295
+ },
2296
+ "model.layers.27.self_attn.k_proj": {
2297
+ "in_features": 4096,
2298
+ "out_features": 1024,
2299
+ "in_factors": [
2300
+ 64,
2301
+ 64
2302
+ ],
2303
+ "out_factors": [
2304
+ 32,
2305
+ 32
2306
+ ]
2307
+ },
2308
+ "model.layers.27.self_attn.v_proj": {
2309
+ "in_features": 4096,
2310
+ "out_features": 1024,
2311
+ "in_factors": [
2312
+ 64,
2313
+ 64
2314
+ ],
2315
+ "out_factors": [
2316
+ 32,
2317
+ 32
2318
+ ]
2319
+ },
2320
+ "model.layers.27.self_attn.o_proj": {
2321
+ "in_features": 4096,
2322
+ "out_features": 4096,
2323
+ "in_factors": [
2324
+ 64,
2325
+ 64
2326
+ ],
2327
+ "out_factors": [
2328
+ 64,
2329
+ 64
2330
+ ]
2331
+ },
2332
+ "model.layers.27.mlp.gate_proj": {
2333
+ "in_features": 4096,
2334
+ "out_features": 14336,
2335
+ "in_factors": [
2336
+ 64,
2337
+ 64
2338
+ ],
2339
+ "out_factors": [
2340
+ 112,
2341
+ 128
2342
+ ]
2343
+ },
2344
+ "model.layers.27.mlp.up_proj": {
2345
+ "in_features": 4096,
2346
+ "out_features": 14336,
2347
+ "in_factors": [
2348
+ 64,
2349
+ 64
2350
+ ],
2351
+ "out_factors": [
2352
+ 112,
2353
+ 128
2354
+ ]
2355
+ },
2356
+ "model.layers.27.mlp.down_proj": {
2357
+ "in_features": 14336,
2358
+ "out_features": 4096,
2359
+ "in_factors": [
2360
+ 112,
2361
+ 128
2362
+ ],
2363
+ "out_factors": [
2364
+ 64,
2365
+ 64
2366
+ ]
2367
+ },
2368
+ "model.layers.28.self_attn.q_proj": {
2369
+ "in_features": 4096,
2370
+ "out_features": 4096,
2371
+ "in_factors": [
2372
+ 64,
2373
+ 64
2374
+ ],
2375
+ "out_factors": [
2376
+ 64,
2377
+ 64
2378
+ ]
2379
+ },
2380
+ "model.layers.28.self_attn.k_proj": {
2381
+ "in_features": 4096,
2382
+ "out_features": 1024,
2383
+ "in_factors": [
2384
+ 64,
2385
+ 64
2386
+ ],
2387
+ "out_factors": [
2388
+ 32,
2389
+ 32
2390
+ ]
2391
+ },
2392
+ "model.layers.28.self_attn.v_proj": {
2393
+ "in_features": 4096,
2394
+ "out_features": 1024,
2395
+ "in_factors": [
2396
+ 64,
2397
+ 64
2398
+ ],
2399
+ "out_factors": [
2400
+ 32,
2401
+ 32
2402
+ ]
2403
+ },
2404
+ "model.layers.28.self_attn.o_proj": {
2405
+ "in_features": 4096,
2406
+ "out_features": 4096,
2407
+ "in_factors": [
2408
+ 64,
2409
+ 64
2410
+ ],
2411
+ "out_factors": [
2412
+ 64,
2413
+ 64
2414
+ ]
2415
+ },
2416
+ "model.layers.28.mlp.gate_proj": {
2417
+ "in_features": 4096,
2418
+ "out_features": 14336,
2419
+ "in_factors": [
2420
+ 64,
2421
+ 64
2422
+ ],
2423
+ "out_factors": [
2424
+ 112,
2425
+ 128
2426
+ ]
2427
+ },
2428
+ "model.layers.28.mlp.up_proj": {
2429
+ "in_features": 4096,
2430
+ "out_features": 14336,
2431
+ "in_factors": [
2432
+ 64,
2433
+ 64
2434
+ ],
2435
+ "out_factors": [
2436
+ 112,
2437
+ 128
2438
+ ]
2439
+ },
2440
+ "model.layers.28.mlp.down_proj": {
2441
+ "in_features": 14336,
2442
+ "out_features": 4096,
2443
+ "in_factors": [
2444
+ 112,
2445
+ 128
2446
+ ],
2447
+ "out_factors": [
2448
+ 64,
2449
+ 64
2450
+ ]
2451
+ },
2452
+ "model.layers.29.self_attn.q_proj": {
2453
+ "in_features": 4096,
2454
+ "out_features": 4096,
2455
+ "in_factors": [
2456
+ 64,
2457
+ 64
2458
+ ],
2459
+ "out_factors": [
2460
+ 64,
2461
+ 64
2462
+ ]
2463
+ },
2464
+ "model.layers.29.self_attn.k_proj": {
2465
+ "in_features": 4096,
2466
+ "out_features": 1024,
2467
+ "in_factors": [
2468
+ 64,
2469
+ 64
2470
+ ],
2471
+ "out_factors": [
2472
+ 32,
2473
+ 32
2474
+ ]
2475
+ },
2476
+ "model.layers.29.self_attn.v_proj": {
2477
+ "in_features": 4096,
2478
+ "out_features": 1024,
2479
+ "in_factors": [
2480
+ 64,
2481
+ 64
2482
+ ],
2483
+ "out_factors": [
2484
+ 32,
2485
+ 32
2486
+ ]
2487
+ },
2488
+ "model.layers.29.self_attn.o_proj": {
2489
+ "in_features": 4096,
2490
+ "out_features": 4096,
2491
+ "in_factors": [
2492
+ 64,
2493
+ 64
2494
+ ],
2495
+ "out_factors": [
2496
+ 64,
2497
+ 64
2498
+ ]
2499
+ },
2500
+ "model.layers.29.mlp.gate_proj": {
2501
+ "in_features": 4096,
2502
+ "out_features": 14336,
2503
+ "in_factors": [
2504
+ 64,
2505
+ 64
2506
+ ],
2507
+ "out_factors": [
2508
+ 112,
2509
+ 128
2510
+ ]
2511
+ },
2512
+ "model.layers.29.mlp.up_proj": {
2513
+ "in_features": 4096,
2514
+ "out_features": 14336,
2515
+ "in_factors": [
2516
+ 64,
2517
+ 64
2518
+ ],
2519
+ "out_factors": [
2520
+ 112,
2521
+ 128
2522
+ ]
2523
+ },
2524
+ "model.layers.29.mlp.down_proj": {
2525
+ "in_features": 14336,
2526
+ "out_features": 4096,
2527
+ "in_factors": [
2528
+ 112,
2529
+ 128
2530
+ ],
2531
+ "out_factors": [
2532
+ 64,
2533
+ 64
2534
+ ]
2535
+ },
2536
+ "model.layers.30.self_attn.q_proj": {
2537
+ "in_features": 4096,
2538
+ "out_features": 4096,
2539
+ "in_factors": [
2540
+ 64,
2541
+ 64
2542
+ ],
2543
+ "out_factors": [
2544
+ 64,
2545
+ 64
2546
+ ]
2547
+ },
2548
+ "model.layers.30.self_attn.k_proj": {
2549
+ "in_features": 4096,
2550
+ "out_features": 1024,
2551
+ "in_factors": [
2552
+ 64,
2553
+ 64
2554
+ ],
2555
+ "out_factors": [
2556
+ 32,
2557
+ 32
2558
+ ]
2559
+ },
2560
+ "model.layers.30.self_attn.v_proj": {
2561
+ "in_features": 4096,
2562
+ "out_features": 1024,
2563
+ "in_factors": [
2564
+ 64,
2565
+ 64
2566
+ ],
2567
+ "out_factors": [
2568
+ 32,
2569
+ 32
2570
+ ]
2571
+ },
2572
+ "model.layers.30.self_attn.o_proj": {
2573
+ "in_features": 4096,
2574
+ "out_features": 4096,
2575
+ "in_factors": [
2576
+ 64,
2577
+ 64
2578
+ ],
2579
+ "out_factors": [
2580
+ 64,
2581
+ 64
2582
+ ]
2583
+ },
2584
+ "model.layers.30.mlp.gate_proj": {
2585
+ "in_features": 4096,
2586
+ "out_features": 14336,
2587
+ "in_factors": [
2588
+ 64,
2589
+ 64
2590
+ ],
2591
+ "out_factors": [
2592
+ 112,
2593
+ 128
2594
+ ]
2595
+ },
2596
+ "model.layers.30.mlp.up_proj": {
2597
+ "in_features": 4096,
2598
+ "out_features": 14336,
2599
+ "in_factors": [
2600
+ 64,
2601
+ 64
2602
+ ],
2603
+ "out_factors": [
2604
+ 112,
2605
+ 128
2606
+ ]
2607
+ },
2608
+ "model.layers.30.mlp.down_proj": {
2609
+ "in_features": 14336,
2610
+ "out_features": 4096,
2611
+ "in_factors": [
2612
+ 112,
2613
+ 128
2614
+ ],
2615
+ "out_factors": [
2616
+ 64,
2617
+ 64
2618
+ ]
2619
+ },
2620
+ "model.layers.31.self_attn.q_proj": {
2621
+ "in_features": 4096,
2622
+ "out_features": 4096,
2623
+ "in_factors": [
2624
+ 64,
2625
+ 64
2626
+ ],
2627
+ "out_factors": [
2628
+ 64,
2629
+ 64
2630
+ ]
2631
+ },
2632
+ "model.layers.31.self_attn.k_proj": {
2633
+ "in_features": 4096,
2634
+ "out_features": 1024,
2635
+ "in_factors": [
2636
+ 64,
2637
+ 64
2638
+ ],
2639
+ "out_factors": [
2640
+ 32,
2641
+ 32
2642
+ ]
2643
+ },
2644
+ "model.layers.31.self_attn.v_proj": {
2645
+ "in_features": 4096,
2646
+ "out_features": 1024,
2647
+ "in_factors": [
2648
+ 64,
2649
+ 64
2650
+ ],
2651
+ "out_factors": [
2652
+ 32,
2653
+ 32
2654
+ ]
2655
+ },
2656
+ "model.layers.31.self_attn.o_proj": {
2657
+ "in_features": 4096,
2658
+ "out_features": 4096,
2659
+ "in_factors": [
2660
+ 64,
2661
+ 64
2662
+ ],
2663
+ "out_factors": [
2664
+ 64,
2665
+ 64
2666
+ ]
2667
+ },
2668
+ "model.layers.31.mlp.gate_proj": {
2669
+ "in_features": 4096,
2670
+ "out_features": 14336,
2671
+ "in_factors": [
2672
+ 64,
2673
+ 64
2674
+ ],
2675
+ "out_factors": [
2676
+ 112,
2677
+ 128
2678
+ ]
2679
+ },
2680
+ "model.layers.31.mlp.up_proj": {
2681
+ "in_features": 4096,
2682
+ "out_features": 14336,
2683
+ "in_factors": [
2684
+ 64,
2685
+ 64
2686
+ ],
2687
+ "out_factors": [
2688
+ 112,
2689
+ 128
2690
+ ]
2691
+ },
2692
+ "model.layers.31.mlp.down_proj": {
2693
+ "in_features": 14336,
2694
+ "out_features": 4096,
2695
+ "in_factors": [
2696
+ 112,
2697
+ 128
2698
+ ],
2699
+ "out_factors": [
2700
+ 64,
2701
+ 64
2702
+ ]
2703
+ }
2704
+ },
2705
+ "best_epoch": 2,
2706
+ "early_stopped": true,
2707
+ "best_val_loss": 0.22870923079550265
2708
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:488627ecc018516553a05ef257f6cabc5279eaba25647b9e0eec8ef598e0f13f
3
+ size 32130516735
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|end_of_text|>"
17
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2e19a8db99d6ba7c2f811d31119e13ecfb8555f629d7bf08a3c9f1a2fedc11f
3
+ size 17210060
tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
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": "<|reserved_special_token_4|>",
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": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizer"
2063
+ }