Upload model
Browse files- README.md +199 -0
- config.json +18 -0
- configuration_medts.py +23 -0
- model.safetensors +3 -0
- modeling_medts.py +150 -0
README.md
ADDED
@@ -0,0 +1,199 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
tags: []
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
config.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"MedTSModel"
|
4 |
+
],
|
5 |
+
"auto_map": {
|
6 |
+
"AutoConfig": "configuration_medts.MedTSConfig",
|
7 |
+
"AutoModel": "modeling_medts.MedTSModel"
|
8 |
+
},
|
9 |
+
"block_size": 32,
|
10 |
+
"dropout": 0.1,
|
11 |
+
"model_type": "MedTS",
|
12 |
+
"n_embd": 512,
|
13 |
+
"n_head": 2,
|
14 |
+
"n_layer": 2,
|
15 |
+
"torch_dtype": "float32",
|
16 |
+
"transformers_version": "4.41.1",
|
17 |
+
"vocab_size": 4
|
18 |
+
}
|
configuration_medts.py
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from transformers import PretrainedConfig
|
2 |
+
|
3 |
+
|
4 |
+
class MedTSConfig(PretrainedConfig):
|
5 |
+
model_type = "MedTS"
|
6 |
+
|
7 |
+
def __init__(
|
8 |
+
self,
|
9 |
+
vocab_size = 4,
|
10 |
+
n_embd = 128,
|
11 |
+
block_size=32,
|
12 |
+
n_layer=2,
|
13 |
+
n_head=2,
|
14 |
+
dropout=0.1,
|
15 |
+
**kwargs,
|
16 |
+
):
|
17 |
+
self.vocab_size = vocab_size
|
18 |
+
self.n_embd = n_embd
|
19 |
+
self.block_size = block_size
|
20 |
+
self.n_layer = n_layer
|
21 |
+
self.n_head = n_head
|
22 |
+
self.dropout = dropout
|
23 |
+
super().__init__(**kwargs)
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef3fe4e70562e0b33085b10f917213dbf96230cd6f5ddb55d17da512c2e3b76a
|
3 |
+
size 25250512
|
modeling_medts.py
ADDED
@@ -0,0 +1,150 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from transformers import PreTrainedModel
|
2 |
+
import torch
|
3 |
+
import torch.nn as nn
|
4 |
+
from torch.nn import functional as F
|
5 |
+
from .configuration_medts import MedTSConfig
|
6 |
+
|
7 |
+
|
8 |
+
class FeedFoward(nn.Module):
|
9 |
+
""" a simple linear layer followed by a non-linearity """
|
10 |
+
def __init__(self, n_embd, dropout):
|
11 |
+
super().__init__()
|
12 |
+
self.net = nn.Sequential(
|
13 |
+
nn.Linear(n_embd, 4 * n_embd),
|
14 |
+
nn.ReLU(),
|
15 |
+
nn.Linear(4 * n_embd, n_embd),
|
16 |
+
nn.Dropout(dropout),
|
17 |
+
)
|
18 |
+
|
19 |
+
def forward(self, x):
|
20 |
+
return self.net(x)
|
21 |
+
|
22 |
+
|
23 |
+
class Head(nn.Module):
|
24 |
+
""" one head of self-attention """
|
25 |
+
def __init__(self, head_size, n_embd, block_size):
|
26 |
+
super().__init__()
|
27 |
+
self.key = nn.Linear(n_embd, head_size, bias=False)
|
28 |
+
self.query = nn.Linear(n_embd, head_size, bias=False)
|
29 |
+
self.value = nn.Linear(n_embd, head_size, bias=False)
|
30 |
+
self.register_buffer('tril', torch.tril(torch.ones(block_size, block_size)))
|
31 |
+
def forward(self, x):
|
32 |
+
# input of size (batch, time-step, channels)
|
33 |
+
# output of size (batch, time-step, head size)
|
34 |
+
B,T,C = x.shape
|
35 |
+
k = self.key(x) # (B,T,hs)
|
36 |
+
q = self.query(x) # (B,T,hs)
|
37 |
+
# compute attention scores ("affinities")
|
38 |
+
wei = q @ k.transpose(-2,-1) * k.shape[-1]**-0.5 # (B, T, hs) @ (B, hs, T) -> (B, T, T)
|
39 |
+
wei = wei.masked_fill(self.tril[:T, :T] == 0, float('-inf')) # (B, T, T)
|
40 |
+
wei = F.softmax(wei, dim=-1) # (B, T, T)
|
41 |
+
# perform the weighted aggregation of the values
|
42 |
+
v = self.value(x) # (B,T,hs)
|
43 |
+
out = wei @ v # (B, T, T) @ (B, T, hs) -> (B, T, hs)
|
44 |
+
return out
|
45 |
+
|
46 |
+
class MultiHeadAttention(nn.Module):
|
47 |
+
""" multiple heads of self-attention in parallel """
|
48 |
+
def __init__(self, num_heads, head_size, n_embd, dropout, block_size):
|
49 |
+
super().__init__()
|
50 |
+
self.heads = nn.ModuleList([Head(head_size, n_embd, block_size) for _ in range(num_heads)])
|
51 |
+
self.proj = nn.Linear(head_size * num_heads, n_embd)
|
52 |
+
self.dropout = nn.Dropout(dropout)
|
53 |
+
def forward(self, x):
|
54 |
+
out = torch.cat([h(x) for h in self.heads], dim=-1)
|
55 |
+
out = self.dropout(self.proj(out))
|
56 |
+
return out
|
57 |
+
|
58 |
+
class Block(nn.Module):
|
59 |
+
""" Transformer block: communication followed by computation """
|
60 |
+
def __init__(self, n_embd, n_head, dropout, block_size):
|
61 |
+
# n_embd: embedding dimension, n_head: the number of heads we'd like
|
62 |
+
super().__init__()
|
63 |
+
head_size = n_embd // n_head
|
64 |
+
self.sa = MultiHeadAttention(n_head, head_size, n_embd, dropout, block_size)
|
65 |
+
self.ffwd = FeedFoward(n_embd, dropout)
|
66 |
+
self.ln1 = nn.LayerNorm(n_embd)
|
67 |
+
self.ln2 = nn.LayerNorm(n_embd)
|
68 |
+
|
69 |
+
def forward(self, x):
|
70 |
+
x = x + self.sa(self.ln1(x))
|
71 |
+
x = x + self.ffwd(self.ln2(x))
|
72 |
+
return x
|
73 |
+
|
74 |
+
|
75 |
+
class PatientsTimeSeriesModel(nn.Module):
|
76 |
+
def __init__(self, vocab_size, n_embd, block_size, device, n_layer, n_head, dropout):
|
77 |
+
'''
|
78 |
+
args:
|
79 |
+
- vocab_size: int, the number of unique tokens in the vocabulary, i.e. the number of unique tests results
|
80 |
+
- n_embd: int, the dimension of the embedding, i.e. the number of tests results (same as vocab_size)
|
81 |
+
- block_size: int, the length of the context
|
82 |
+
'''
|
83 |
+
super().__init__()
|
84 |
+
# each token directly reads off the logits for the next token from a lookup table
|
85 |
+
self.position_embedding_table = nn.Embedding(block_size, vocab_size)
|
86 |
+
# self.sa =Head(n_embd, n_embd, block_size)
|
87 |
+
self.blocks = nn.Sequential(*[Block(n_embd, n_head, dropout, block_size) for _ in range(n_layer)])
|
88 |
+
self.ln_f = nn.LayerNorm(n_embd) # final layer norm
|
89 |
+
|
90 |
+
self.lm_prefix = nn.Linear(vocab_size, n_embd) # linear layer to project the tokens to the embedding dimension
|
91 |
+
self.lm_head = nn.Linear(n_embd, vocab_size) # linear layer to project the embeddings to the vocabulary size
|
92 |
+
self.device = device
|
93 |
+
self.apply(self._init_weights)
|
94 |
+
|
95 |
+
def _init_weights(self, module):
|
96 |
+
if isinstance(module, nn.Linear):
|
97 |
+
torch.nn.init.normal_(module.weight, mean=0.0, std=0.02)
|
98 |
+
if module.bias is not None:
|
99 |
+
torch.nn.init.zeros_(module.bias)
|
100 |
+
elif isinstance(module, nn.Embedding):
|
101 |
+
torch.nn.init.normal_(module.weight, mean=0.0, std=0.02)
|
102 |
+
|
103 |
+
def forward(self, tok_emb, targets=None):
|
104 |
+
# tok_emb and targets are both (B,T,C) tensors
|
105 |
+
# where B is the batch size, T is the number of time steps and C is the number of tests results
|
106 |
+
B, T, C = tok_emb.shape
|
107 |
+
pos_emb = self.position_embedding_table(torch.arange(T, device=self.device)) # (T,Vocab_size)
|
108 |
+
x = tok_emb + pos_emb # (B,T,Vocab_size)
|
109 |
+
x = self.lm_prefix(x) # (B,T,C)
|
110 |
+
x = self.blocks(x) # (B,T,C)
|
111 |
+
x = self.ln_f(x) # (B,T,C)
|
112 |
+
logits = self.lm_head(x) # (B,T,vocab_size)
|
113 |
+
if targets is None:
|
114 |
+
return {"logits": logits}
|
115 |
+
else:
|
116 |
+
B, T, C = logits.shape
|
117 |
+
logits = logits.view(B*T, C)
|
118 |
+
targets = targets.view(B*T, C)
|
119 |
+
# TODO: Add padding mask to the loss computation
|
120 |
+
# loss = F.mse_loss(logits, targets)
|
121 |
+
loss = self.mse_loss(logits, targets, reduction="mean")
|
122 |
+
return {"logits": logits, "loss": loss}
|
123 |
+
|
124 |
+
def mse_loss(self, out, target, reduction):
|
125 |
+
mask = (target == 0)
|
126 |
+
loss = (out[~mask]-target[~mask])**2
|
127 |
+
if reduction == "mean":
|
128 |
+
return loss.mean()
|
129 |
+
elif reduction == "None":
|
130 |
+
return loss
|
131 |
+
|
132 |
+
|
133 |
+
class MedTSModel(PreTrainedModel):
|
134 |
+
config_class = MedTSConfig
|
135 |
+
|
136 |
+
def __init__(self, config):
|
137 |
+
super().__init__(config)
|
138 |
+
|
139 |
+
self.model = PatientsTimeSeriesModel(
|
140 |
+
vocab_size=config.vocab_size,
|
141 |
+
n_embd=config.n_embd,
|
142 |
+
block_size=config.block_size,
|
143 |
+
device= 'mps' if torch.backends.mps.is_available() else 'cuda' if torch.cuda.is_available() else 'cpu',
|
144 |
+
n_layer=config.n_layer,
|
145 |
+
n_head=config.n_head,
|
146 |
+
dropout=config.dropout
|
147 |
+
)
|
148 |
+
|
149 |
+
def forward(self, tensor, targets=None):
|
150 |
+
return self.model(tensor, targets)
|