Initial model files commit.

MLmodel

@@ -0,0 +1,28 @@
+artifact_path: MetaExtractor
+flavors:
+  python_function:
+    env:
+      conda: conda.yaml
+      virtualenv: python_env.yaml
+    loader_module: mlflow.transformers
+    pipeline: pipeline
+    python_version: 3.10.11
+  transformers:
+    code: null
+    components:
+    - tokenizer
+    framework: pt
+    instance_type: TokenClassificationPipeline
+    pipeline: pipeline
+    pipeline_model_type: RobertaForTokenClassification
+    source_model_name: /content/drive/MyDrive/Colab Notebooks/ffossils/roberta-finetune-v3/models/
+    task: ner
+    tokenizer_type: RobertaTokenizerFast
+    transformers_version: 4.29.2
+mlflow_version: 2.3.2
+model_uuid: 3a92ac273adc4fceb829de9c60387524
+run_id: ffa8fa05-0aaa-41ae-8410-d1427b8c7256
+signature:
+  inputs: '[{"type": "string"}]'
+  outputs: '[{"type": "string"}]'
+utc_time_created: '2023-06-01 18:51:35.839997'

conda.yaml

@@ -0,0 +1,44 @@
+channels:
+- conda-forge
+dependencies:
+- python=3.10.11
+- pip<=23.1.2
+- pip:
+  - mlflow==2.3
+  - accelerate==0.19.0
+  - cloudpickle==2.2.1
+  - cryptography==40.0.2
+  - dill==0.3.6
+  - etils==1.2.0
+  - google-api-python-client==2.84.0
+  - google-cloud-bigquery-storage==2.19.1
+  - google-cloud-bigquery==3.9.0
+  - google-cloud-datastore==2.15.1
+  - google-cloud-firestore==2.11.0
+  - google-cloud-language==2.9.1
+  - google-cloud-storage==2.8.0
+  - google-cloud-translate==3.11.1
+  - google-colab==1.0.0
+  - importlib-resources==5.12.0
+  - jaxlib==0.4.10
+  - numpy==1.22.4
+  - oauth2client==4.1.3
+  - packaging==23.1
+  - pandas==1.5.3
+  - pathlib==1.0.1
+  - protobuf==3.20.3
+  - pydot-ng==2.0.0
+  - pydot==1.4.2
+  - pysocks==1.7.1
+  - pyyaml==6.0
+  - requests==2.27.1
+  - rich==13.3.4
+  - scikit-learn==1.2.2
+  - scipy==1.10.1
+  - tblib==1.7.0
+  - tensorflow-probability==0.20.1
+  - tensorflow==2.12.0
+  - torch==2.0.1
+  - torchvision==0.15.2
+  - transformers==4.29.2
+name: mlflow-env

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/Colab Notebooks/ffossils/roberta-finetune-v3/models/",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-AGE",
+    "1": "B-ALTI",
+    "2": "B-EMAIL",
+    "3": "B-GEOG",
+    "4": "B-REGION",
+    "5": "B-SITE",
+    "6": "B-TAXA",
+    "7": "I-AGE",
+    "8": "I-ALTI",
+    "9": "I-GEOG",
+    "10": "I-REGION",
+    "11": "I-SITE",
+    "12": "I-TAXA",
+    "13": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-AGE": 0,
+    "B-ALTI": 1,
+    "B-EMAIL": 2,
+    "B-GEOG": 3,
+    "B-REGION": 4,
+    "B-SITE": 5,
+    "B-TAXA": 6,
+    "I-AGE": 7,
+    "I-ALTI": 8,
+    "I-GEOG": 9,
+    "I-REGION": 10,
+    "I-SITE": 11,
+    "I-TAXA": 12,
+    "O": 13
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model_card.md

@@ -0,0 +1,196 @@
+
+# Model Card for MetaExtractor
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This model extracts metadata from Paleoecology research article text.
+
+- **Developed by:** Ty Andrews, Jenit Jain, Shaun Hutchinson, Kelly Wu, and Simon Goring
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** English
+- **License:** MIT
+- **Finetuned from model [optional]:** roberta-base
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** https://github.com/NeotomaDB/MetaExtractor
+- **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 Data 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 Data 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]
+
+

model_card_data.yaml

@@ -0,0 +1,5 @@
+language: en
+library_name: pt
+library_version: 4.29.2
+license: mit
+name: MetaExtractor

python_env.yaml

@@ -0,0 +1,7 @@
+python: 3.10.11
+build_dependencies:
+- pip==23.1.2
+- setuptools==67.7.2
+- wheel==0.40.0
+dependencies:
+- -r requirements.txt

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4f40c00bc3c9f9fd0866974d99d9726182a68afb3a6aee234f75e7091d33b9f
+size 496333165

requirements.txt

@@ -0,0 +1,37 @@
+mlflow==2.3
+accelerate==0.19.0
+cloudpickle==2.2.1
+cryptography==40.0.2
+dill==0.3.6
+etils==1.2.0
+google-api-python-client==2.84.0
+google-cloud-bigquery-storage==2.19.1
+google-cloud-bigquery==3.9.0
+google-cloud-datastore==2.15.1
+google-cloud-firestore==2.11.0
+google-cloud-language==2.9.1
+google-cloud-storage==2.8.0
+google-cloud-translate==3.11.1
+google-colab==1.0.0
+importlib-resources==5.12.0
+jaxlib==0.4.10
+numpy==1.22.4
+oauth2client==4.1.3
+packaging==23.1
+pandas==1.5.3
+pathlib==1.0.1
+protobuf==3.20.3
+pydot-ng==2.0.0
+pydot==1.4.2
+pysocks==1.7.1
+pyyaml==6.0
+requests==2.27.1
+rich==13.3.4
+scikit-learn==1.2.2
+scipy==1.10.1
+tblib==1.7.0
+tensorflow-probability==0.20.1
+tensorflow==2.12.0
+torch==2.0.1
+torchvision==0.15.2
+transformers==4.29.2

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": true,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}