Upload MoEBertForSentenceSimilarity

README.md

@@ -0,0 +1,201 @@
+---
+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 +1,97 @@
+{
+  "ESM": false,
+  "MI": false,
+  "MOE": true,
+  "_name_or_path": "output/checkpoint-80000",
+  "a_col": "a",
+  "architectures": [
+    "MoEBertForSentenceSimilarity"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "b_col": "b",
+  "classifier_dropout": null,
+  "contact_head": false,
+  "data_paths": [
+    "lhallee/abstract_domain_cvd",
+    "lhallee/abstract_domain_copd",
+    "lhallee/abstract_domain_skincancer",
+    "lhallee/abstract_domain_autoimmune",
+    "lhallee/abstract_domain_parasitic"
+  ],
+  "domains": [
+    "[CVD]",
+    "[COP]",
+    "[CAN]",
+    "[IMM]",
+    "[PAR]"
+  ],
+  "eval": false,
+  "eval_accumulation_steps": null,
+  "eval_steps": 5000,
+  "evaluation_strategy": "steps",
+  "expert_loss": true,
+  "fp16": true,
+  "gradient_accumulation_steps": 1,
+  "group_by_length": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.05,
+  "hidden_size": 768,
+  "huggingface_username": "lhallee",
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label_col": "label",
+  "layer_norm_eps": 1e-12,
+  "learning_rate": 1e-05,
+  "length_column_name": "length",
+  "limits": false,
+  "log_path": "./results.txt",
+  "logging_dir": "./logs",
+  "logging_steps": 100,
+  "logging_strategy": "steps",
+  "lr_scheduler_type": "cosine",
+  "max_length": 512,
+  "max_position_embeddings": 512,
+  "metric_for_best_model": "f1_max",
+  "model_path": "allenai/scibert_scivocab_uncased",
+  "model_type": "bert",
+  "moe_type": "topk",
+  "n_col": "negatives",
+  "new_special_tokens": true,
+  "num_attention_heads": 12,
+  "num_experts": 8,
+  "num_hidden_layers": 12,
+  "num_tasks": 5,
+  "num_train_epochs": 10,
+  "output_dir": "./output",
+  "p_col": "positives",
+  "pad_token_id": 0,
+  "patience": 10,
+  "per_device_eval_batch_size": 20,
+  "per_device_train_batch_size": 20,
+  "position_embedding_type": "absolute",
+  "save_path": "nlp_single_moe_no_MI.pt",
+  "save_steps": 5000,
+  "save_strategy": "steps",
+  "save_total_limit": 3,
+  "seed": 42,
+  "single_moe": true,
+  "test_size": 10000,
+  "token": null,
+  "token_moe": true,
+  "topk": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "valid_size": 10000,
+  "vocab_size": 31100,
+  "wBAL": 0.05,
+  "wEX": 0.01,
+  "wandb": false,
+  "wandb_name": "triplet_test",
+  "wandb_project": "SSPR",
+  "warmup_steps": 100,
+  "weight_decay": 0.01,
+  "weight_path": null,
+  "yaml_path": "yamls/MOE/all_nlp.yaml"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12562260a6f784cc732b9c347433cb3d76c8953bcf3ebf5585f2336fd81b50a6
+size 647582524