Upload TransformerClassifier

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- 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. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,18 @@
+{
+  "architectures": [
+    "TransformerClassifier"
+  ],
+  "auto_map": {
+    "AutoConfig": "transformer.TransformerClassifierConfig",
+    "AutoModel": "transformer.TransformerClassifier"
+  },
+  "d_model": 128,
+  "ff_dim": 512,
+  "in_dim": 42,
+  "model_type": "transformer-checker",
+  "n_classes": 2,
+  "n_heads": 8,
+  "n_layers": 6,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aca2eeb41e38f5807e6c7d0be481f42aba8ba5ef4785cf040221fed515fd183
+size 4790520

transformer.py

@@ -0,0 +1,174 @@
+import math
+
+import torch
+import torch.nn as nn
+from transformer_lens.HookedTransformer import HookedTransformer
+from transformer_lens.HookedTransformerConfig import HookedTransformerConfig
+from transformer_lens.train import HookedTransformerTrainConfig, train
+from transformers import PretrainedConfig, PreTrainedModel
+
+
+def generate_config(
+    n_ctx,
+    d_model,
+    d_head,
+    n_heads,
+    d_mlp,
+    n_layers,
+    attention_dir,
+    act_fn,
+    d_vocab,
+    d_vocab_out,
+    use_attn_result,
+    device,
+    use_hook_tokens,
+):
+    return HookedTransformerConfig(
+        n_ctx=n_ctx,
+        d_model=d_model,
+        d_head=d_head,
+        n_heads=n_heads,
+        d_mlp=d_mlp,
+        n_layers=n_layers,
+        attention_dir=attention_dir,
+        act_fn=act_fn,
+        d_vocab=d_vocab,
+        d_vocab_out=d_vocab_out,
+        use_attn_result=use_attn_result,
+        device=device,
+        use_hook_tokens=use_hook_tokens,
+    )
+
+
+def generate_model(config):
+    return HookedTransformer(config)
+
+
+def train_model(model, n_epochs, batch_size, lr, dataset):
+    train_cfg = HookedTransformerTrainConfig(
+        num_epochs=n_epochs, batch_size=128, lr=0.001, device="cuda:0"
+    )
+
+    return train(model, train_cfg, dataset)
+
+
+class ScaledDotProductAttention(nn.Module):
+    def __init__(self, scale):
+        super().__init__()
+        self.scale = scale
+
+    def forward(self, q, k, v, mask=None):
+        attn = torch.matmul(q, k.transpose(-2, -1)) * 1 / self.scale
+        if mask is not None:
+            attn = attn.masked_fill(mask == 0, float("-inf"))
+
+        attn = torch.softmax(attn, dim=-1)
+
+        out = torch.matmul(attn, v)
+        return out, attn
+
+
+class MultiHeadAttention(nn.Module):
+    def __init__(self, n_heads, d_model):
+        super().__init__()
+        assert d_model % n_heads == 0, "d_model should be divisible by n_heads"
+
+        self.d_model = d_model
+        self.n_heads = n_heads
+        self.depth = d_model // n_heads
+
+        self.wq = nn.Linear(d_model, d_model)
+        self.wk = nn.Linear(d_model, d_model)
+        self.wv = nn.Linear(d_model, d_model)
+
+        self.dense = nn.Linear(d_model, d_model)
+
+        self.attn = ScaledDotProductAttention(scale=math.sqrt(self.depth))
+
+    def forward(self, q, k, v, mask=None):
+        batch_size = q.size(0)
+
+        q = self.wq(q).view(batch_size, -1, self.n_heads, self.depth).transpose(1, 2)
+        k = self.wk(k).view(batch_size, -1, self.n_heads, self.depth).transpose(1, 2)
+        v = self.wv(v).view(batch_size, -1, self.n_heads, self.depth).transpose(1, 2)
+
+        attn_out, _ = self.attn(q, k, v, mask=mask)
+        attn_out = (
+            attn_out.transpose(1, 2).contiguous().view(batch_size, -1, self.d_model)
+        )
+
+        out = self.dense(attn_out)
+
+        return out
+
+
+class TransformerEncoderLayer(nn.Module):
+    def __init__(self, d_model, n_heads, ff_dim, dropout=0.1):
+        super().__init__()
+        self.attn = MultiHeadAttention(n_heads, d_model)
+        self.ff = nn.Sequential(
+            nn.Linear(d_model, ff_dim),
+            nn.ReLU(),
+            nn.Linear(ff_dim, d_model),
+        )
+
+        self.ln1 = nn.LayerNorm(d_model)
+        self.ln2 = nn.LayerNorm(d_model)
+
+        self.dropout = nn.Dropout(dropout)
+
+    def forward(self, x, mask=None):
+        attn_out = self.attn(x, x, x, mask=mask)
+        x = self.ln1(x + self.dropout(attn_out))
+
+        ff_out = self.ff(x)
+        x = self.ln2(x + self.dropout(ff_out))
+
+        return x
+
+
+class TransformerClassifierConfig(PretrainedConfig):
+    model_type = "transformer-checker"
+
+    def __init__(
+        self,
+        in_dim=512,
+        d_model=256,
+        n_heads=8,
+        ff_dim=2048,
+        n_layers=6,
+        n_classes=2,
+        **kwargs,
+    ):
+        self.in_dim = in_dim
+        self.d_model = d_model
+        self.n_heads = n_heads
+        self.ff_dim = ff_dim
+        self.n_layers = n_layers
+        self.n_classes = n_classes
+
+        super().__init__(**kwargs)
+
+
+class TransformerClassifier(PreTrainedModel):
+    config_class = TransformerClassifierConfig
+
+    def __init__(self, config: TransformerClassifierConfig):
+        super().__init__(config)
+        self.embedding = nn.Linear(config.in_dim, config.d_model)
+        self.encoders = nn.ModuleList(
+            [
+                TransformerEncoderLayer(config.d_model, config.n_heads, config.ff_dim)
+                for _ in range(config.n_layers)
+            ]
+        )
+        self.classifier = nn.Linear(config.d_model, config.n_classes)
+
+    def forward(self, x, mask=None):
+        x = self.embedding(x)
+        for encoder in self.encoders:
+            x = encoder(x, mask=mask)
+
+        x = self.classifier(x[:, 0])
+
+        return x