Upload ModernBertForSequenceClassification

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 +1,329 @@
+{
+  "_name_or_path": "answerdotai/ModernBERT-large",
+  "architectures": [
+    "ModernBertForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50281,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "classifiers_size": [
+    3,
+    2,
+    2,
+    2,
+    2,
+    2,
+    1,
+    2,
+    3,
+    2,
+    2,
+    2,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2,
+    3,
+    2,
+    2,
+    2,
+    2,
+    2,
+    6,
+    2,
+    2,
+    2,
+    2,
+    2,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2,
+    2,
+    2,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    16,
+    100,
+    13,
+    100,
+    8,
+    3,
+    3,
+    2,
+    3,
+    2,
+    4,
+    3,
+    2,
+    3,
+    2,
+    2,
+    2,
+    2,
+    2,
+    3,
+    2,
+    3,
+    2,
+    4,
+    3,
+    3,
+    3,
+    2,
+    3,
+    1,
+    2,
+    2,
+    3,
+    13,
+    2,
+    2,
+    3,
+    2,
+    2,
+    3,
+    3,
+    3,
+    3,
+    2,
+    3,
+    2,
+    3,
+    2,
+    3,
+    2,
+    2,
+    2,
+    2,
+    2,
+    3,
+    4,
+    3,
+    3,
+    2,
+    2,
+    3,
+    3,
+    2,
+    2,
+    2,
+    2,
+    2,
+    4,
+    3,
+    2,
+    2,
+    2,
+    3,
+    3,
+    3,
+    2,
+    3
+  ],
+  "cls_token_id": 50281,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "embedding_dropout": 0.0,
+  "eos_token_id": 50282,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "entailment",
+    "1": "neutral",
+    "2": "contradiction"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 2624,
+  "label2id": {
+    "contradiction": 2,
+    "entailment": 0,
+    "neutral": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "pad_token_id": 50283,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "reference_compile": true,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "tasks": [
+    "glue/mnli",
+    "glue/qnli",
+    "glue/rte",
+    "glue/wnli",
+    "glue/mrpc",
+    "glue/qqp",
+    "glue/stsb",
+    "super_glue/boolq",
+    "super_glue/cb",
+    "super_glue/multirc",
+    "super_glue/wic",
+    "super_glue/axg",
+    "anli/a1",
+    "anli/a2",
+    "anli/a3",
+    "sick/label",
+    "sick/entailment_AB",
+    "snli",
+    "scitail/snli_format",
+    "hans",
+    "WANLI",
+    "recast/recast_ner",
+    "recast/recast_sentiment",
+    "recast/recast_verbnet",
+    "recast/recast_megaveridicality",
+    "recast/recast_verbcorner",
+    "recast/recast_kg_relations",
+    "recast/recast_factuality",
+    "recast/recast_puns",
+    "probability_words_nli/reasoning_1hop",
+    "probability_words_nli/usnli",
+    "probability_words_nli/reasoning_2hop",
+    "nan-nli",
+    "nli_fever",
+    "breaking_nli",
+    "conj_nli",
+    "fracas",
+    "dialogue_nli",
+    "mpe",
+    "dnc",
+    "recast_white/fnplus",
+    "recast_white/sprl",
+    "recast_white/dpr",
+    "robust_nli/IS_CS",
+    "robust_nli/LI_LI",
+    "robust_nli/ST_WO",
+    "robust_nli/PI_SP",
+    "robust_nli/PI_CD",
+    "robust_nli/ST_SE",
+    "robust_nli/ST_NE",
+    "robust_nli/ST_LM",
+    "robust_nli_is_sd",
+    "robust_nli_li_ts",
+    "add_one_rte",
+    "paws/labeled_final",
+    "glue/cola",
+    "glue/sst2",
+    "pragmeval/pdtb",
+    "lex_glue/eurlex",
+    "lex_glue/scotus",
+    "lex_glue/ledgar",
+    "lex_glue/unfair_tos",
+    "dynasent/dynabench.dynasent.r1.all/r1",
+    "dynasent/dynabench.dynasent.r2.all/r2",
+    "cycic_classification",
+    "lingnli",
+    "monotonicity-entailment",
+    "scinli",
+    "naturallogic",
+    "dynahate",
+    "syntactic-augmentation-nli",
+    "autotnli",
+    "defeasible-nli/atomic",
+    "defeasible-nli/snli",
+    "help-nli",
+    "nli-veridicality-transitivity",
+    "lonli",
+    "dadc-limit-nli",
+    "folio",
+    "tomi-nli",
+    "puzzte",
+    "temporal-nli",
+    "counterfactually-augmented-snli",
+    "cnli",
+    "boolq-natural-perturbations",
+    "equate",
+    "chaos-mnli-ambiguity",
+    "logiqa-2.0-nli",
+    "mindgames",
+    "ConTRoL-nli",
+    "logical-fallacy",
+    "cladder",
+    "conceptrules_v2",
+    "zero-shot-label-nli",
+    "scone",
+    "monli",
+    "SpaceNLI",
+    "propsegment/nli",
+    "FLD.v2/default",
+    "FLD.v2/star",
+    "SDOH-NLI",
+    "scifact_entailment",
+    "feasibilityQA",
+    "AdjectiveScaleProbe-nli",
+    "resnli",
+    "semantic_fragments_nli",
+    "dataset_train_nli",
+    "nlgraph",
+    "ruletaker",
+    "PARARULE-Plus",
+    "logical-entailment",
+    "nope",
+    "LogicNLI",
+    "contract-nli/contractnli_a/seg",
+    "contract-nli/contractnli_b/full",
+    "nli4ct_semeval2024",
+    "biosift-nli",
+    "SIGA-nli",
+    "FOL-nli",
+    "doc-nli",
+    "mctest-nli",
+    "natural-language-satisfiability",
+    "idioms-nli",
+    "lifecycle-entailment",
+    "MSciNLI",
+    "hover-3way/nli",
+    "seahorse_summarization_evaluation",
+    "missing-item-prediction/contrastive",
+    "Pol_NLI",
+    "synthetic-retrieval-NLI/count",
+    "synthetic-retrieval-NLI/position",
+    "synthetic-retrieval-NLI/binary",
+    "babi_nli",
+    "gen_debiased_nli"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0.dev0",
+  "vocab_size": 50368
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f56738ff6d17e2c4b28eac0969290cc5325be886a7be069ddc2c6d69128f1e2a
+size 1583355740