Upload 14 files

final_classifier.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02467c4ebc63c582e4624fdadfb424cd2906ca732e0ca4160bad480eb5eafbf7
+size 7007

patentsberta_finetuned_final/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

patentsberta_finetuned_final/README.md

@@ -0,0 +1,446 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:2000
+- loss:CosineSimilarityLoss
+base_model: AI-Growth-Lab/PatentSBERTa
+widget:
+- source_sentence: '1. A method, comprising: adjusting a wastegate actuator coupled
+    to a wastegate valve in an engine exhaust to control an engine boost level of
+    an engine, the adjustment based on a magnetic field of a magnet in the wastegate
+    actuator corrected based on a magnet temperature; wherein the adjustment includes
+    adjusting a current supplied to the actuator, and wherein the adjustment is further
+    based on an actuator winding resistance, the resistance based on the magnet temperature.'
+  sentences:
+  - '1. A beverage bottle for a portable electronic device, comprising: a hand-held
+    container which comprises a body unit having a fluid compartment for containing
+    beverage therein, and a spout unit, having a mouth piece, detachably coupled at
+    said body unit to enclose said fluid compartment; and an accessible station which
+    comprises a supporting frame integrated with one of said body unit and said spout
+    unit of said hand-held container for stably supporting the portable electronic
+    device at a position that the '
+  - '1. A composition that comprises an immunotherapeutic agent in admixture with
+    a compound having a structure: wherein n is 1, 2, or 3; wherein the immunotherapeutic
+    agent comprises a cancer vaccine; a cancer antigen; or at least one antibody selected
+    from the group consisting of an anti-programmed cell death protein 1 (PD-1) antibody
+    and an anti-programmed cell death ligand (PDL-1) antibody.'
+  - '1. A first terminal apparatus of a plurality of terminal apparatuses that are
+    mutually connected via a network, the plurality of terminal apparatuses being
+    allotted unique first identification information, the first terminal apparatus
+    carrying out a transmission and reception of contents information among the plurality
+    of terminal apparatuses via an overlay network that is formed by the plurality
+    of terminal apparatuses, the first terminal apparatus comprising: a routing table
+    storage section configured to '
+- source_sentence: '1. A fuel pellet comprising: petroleum coke, having a sulfur content
+    up to 5.5%; a biomass constituent; an alkali constituent adapted to capture SO2
+    emissions by reacting with sulfur of the petroleum coke upon burn of the pellet;
+    and an iron oxide catalyst capturing in the range of 90 to 95.3 percent of SO2
+    emissions;'
+  sentences:
+  - '1. A firewall apparatus comprising: a memory storing a plurality of firewall
+    configurations defined by a plurality of different customers, each firewall configuration
+    of the plurality of firewall configurations comprising (i) a production profile
+    comprising a different first set of firewall rules or policies actively protecting
+    customer content and services against real-world traffic and (ii) an audit profile
+    comprising a different second set of firewall rules or policies testing new rules
+    or policies again'
+  - '1. An apparatus for creating and managing security policies for data leakage
+    prevention (DLP), the apparatus comprising: a computer server; server code on
+    the computer server; a database which is accessible by the server code and which
+    stores a three-layer structure of objects comprising a first layer of digital
+    asset objects which describe sensitive information contained in a file, a second
+    layer of content template objects which are each associated with at least one
+    digital asset object, and a third layer'
+  - '1. An imaging device comprising: a plurality of pixels disposed to form a matrix
+    having pixel rows, the pixels including a driving section configured to apply
+    an electric potential to said photoelectric conversion film on each of said pixel
+    rows at least having read timings different from each other with a predetermined
+    timing outside an exposure period of said pixels in a direction opposite to that
+    of an electric potential applied to said photoelectric conversion film during
+    said exposure period of said pi'
+- source_sentence: '1. An energy absorber, comprising: a plurality of crush lobes
+    that deform plastically upon impact to absorb energy, wherein the crush lobes
+    include a base and sides extending from the base to an outer wall, wherein the
+    base, sides and outer wall comprise a first thermoplastic material; and a composite
+    insert in the energy absorber, wherein the insert comprises a second plastic material
+    and reinforcement, wherein the second plastic material is different than the first
+    thermoplastic material, wherein the inse'
+  sentences:
+  - '1. A method of tiling a roof, comprising: positioning at least one row of tiles
+    across a surface in a row direction, a first tile of the at least one row of tiles
+    comprising a rain lock adapted to interlock with a second tile adjacent to and
+    within the same row as the first tile, said rain lock having a lower end, an upper
+    end, and a weakened portion proximate the lower end to allow for removal of a
+    predetermined portion of the rain lock; removing the predetermined portion of
+    the rain lock; and staggering t'
+  - '1. A vending machine for scrubs comprising: a housing configured to store a plurality
+    of different sized scrubs; a scrub dispenser carried by said housing; a labeler
+    carried by said housing; and a controller carried by said housing and configured
+    to wherein said labeler is configured to print indicia on a first badge substrate
+    to be attachable to a second badge substrate carried by the selected scrub to
+    define the time expiring badge.'
+  - 1. A method of treatment comprising the administering of a pharmaceutical composition
+    comprising a purified extract with the secondary fractionation (ATC2) from the
+    extract of Pseudolysimachion rotundum var subintegrum , comprising 30%-60% (w/w)
+    verproside, 0.5%-10% (w/w) veratric acid, 2%-20% (w/w) catalposide, 1%-10% (w/w)
+    picroside II, 1%-10% (w/w) isovanilloyl catalpol and 2%-20% (w/w) 6-O-veratroyl
+    catalpol based on the weight of total extract (100%) of Pseudolysimachion rotundum
+    var subintegrum to a s
+- source_sentence: '1. A board reinforcing structure comprising: a reinforcing member
+    configured to reinforce a circuit board having an electronic component mounted
+    thereon, wherein the electronic component has a plurality of electrodes arranged
+    within a rectangular bonding region on a first surface of the circuit board, wherein
+    the reinforcing member is bonded on a second surface of the circuit board opposite
+    to the first surface at positions corresponding to four corners of the rectangular
+    bonding region; wherein the reinfor'
+  sentences:
+  - '1. A refrigeration unit comprising: (a) a countermeasure to prevent heat exchange
+    efficiency from decreasing due to a temperature glide in a heat exchanger; and
+    (b) a refrigerant composition comprising a refrigerant mixture, the refrigerant
+    mixture consisting essentially of 30 to 35 mass % of difluoromethane (HFC32) and
+    70 to 65 mass % of 2,3,3,3-tetrafluoropropene (HFO1234yf), based on a total of
+    HFC32 and HFO1234yf in the refrigerant composition wherein the total amount of
+    HFC32 and HFO1234yf is taken as '
+  - '1. A style masking engine for a web server, comprising: a receiving unit programmed
+    to receive, at the web server from a client device responsive to user selection
+    within a user interface of a source application output window and a target application
+    output window of a web page displayed by the client device, a user request to
+    modify a style of content displayed within the user-selected target application
+    output window of the web page displayed by the client device; a web application
+    aggregator programmed t'
+  - '1. A steam reforming system comprising: a) a kiln, comprising a susceptor tube;
+    a kiln inlet for receiving a feedstock; a conveyor for transporting said feedstock
+    through said kiln; b) a steam reforming reactor comprising a reformer tube; a
+    reactor inlet in fluid communication with said first kiln outlet for gaseous product
+    of said kiln; and a reactor outlet for a gaseous product; c) an inductive heating
+    means contiguous to said reformer tube for providing heat to said steam reforming
+    reactor; and d) said s'
+- source_sentence: 1. An industrial truck with an electric travel drive ( 14 ) and
+    controls ( 20 ) that can switch the electric travel drive ( 14 ) to regenerative
+    operation to brake the industrial truck, characterized in that an eddy current
+    brake ( wherein the controls ( further characterized in that the controls ( further
+    wherein the controls determine a setpoint for the eddy current brake in a manner
+    such that the braking torque resulting from the regenerative operation of the
+    travel drive and the eddy current brake is co
+  sentences:
+  - '1. A method for reallocating primary and secondary destinations in a virtual
+    server for one or more segmented servers, the method comprising the steps of:
+    a computer allocating buckets to at least two data structures designated to the
+    one or more segmented servers, wherein one of the at least two data structures
+    includes one less bucket than the other data structure; the computer allocating
+    primary destinations to the buckets, wherein a number, the number identifying
+    the bucket destinations, of each primary'
+  - '1. An apparatus including a system for enabling communications via a power line
+    conveying DC power from multiple DC power sources, comprising: first and second
+    power line electrodes for connecting to first and second ends of a power line
+    conveying DC power from a plurality of serially coupled DC power sources; receiver
+    circuitry coupled to said first and second power line electrodes, and responsive
+    to one or more power line voltages at said first and second power line electrodes
+    by providing first and secon'
+  - '1. A hydraulic control system, comprising: a hydraulic circuit; a pump configured
+    to supply pressurized fluid to the hydraulic circuit; a first fluid actuator fluidly
+    connected to receive pressurized fluid from the hydraulic circuit; a first valve
+    arrangement movable to control a flow of fluid to the first fluid actuator; a
+    second fluid actuator fluidly connected to receive pressurized fluid from the
+    hydraulic circuit; a second valve arrangement movable to control a flow of fluid
+    to the second fluid actuato'
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on AI-Growth-Lab/PatentSBERTa
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [AI-Growth-Lab/PatentSBERTa](https://huggingface.co/AI-Growth-Lab/PatentSBERTa). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [AI-Growth-Lab/PatentSBERTa](https://huggingface.co/AI-Growth-Lab/PatentSBERTa) <!-- at revision 3ff1d553c861d8f5bfd902333d97fc95eb6b4c8f -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    '1. An industrial truck with an electric travel drive ( 14 ) and controls ( 20 ) that can switch the electric travel drive ( 14 ) to regenerative operation to brake the industrial truck, characterized in that an eddy current brake ( wherein the controls ( further characterized in that the controls ( further wherein the controls determine a setpoint for the eddy current brake in a manner such that the braking torque resulting from the regenerative operation of the travel drive and the eddy current brake is co',
+    '1. A method for reallocating primary and secondary destinations in a virtual server for one or more segmented servers, the method comprising the steps of: a computer allocating buckets to at least two data structures designated to the one or more segmented servers, wherein one of the at least two data structures includes one less bucket than the other data structure; the computer allocating primary destinations to the buckets, wherein a number, the number identifying the bucket destinations, of each primary',
+    '1. A hydraulic control system, comprising: a hydraulic circuit; a pump configured to supply pressurized fluid to the hydraulic circuit; a first fluid actuator fluidly connected to receive pressurized fluid from the hydraulic circuit; a first valve arrangement movable to control a flow of fluid to the first fluid actuator; a second fluid actuator fluidly connected to receive pressurized fluid from the hydraulic circuit; a second valve arrangement movable to control a flow of fluid to the second fluid actuato',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+* Size: 2,000 training samples
+* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                          | sentence_1                                                                          | label                                                          |
+  |:--------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                              | float                                                          |
+  | details | <ul><li>min: 17 tokens</li><li>mean: 98.38 tokens</li><li>max: 313 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 98.92 tokens</li><li>max: 313 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.52</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence_0                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    | sentence_1                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    | label            |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------|
+  | <code>1. A cell capacity adjusting device for reducing fluctuations in state of charge (SOC) among cells of a battery pack, which is formed by connecting a plurality of cells in series, during suspension of operation of electrically-powered equipment whose main power source is the battery pack, the cell capacity adjusting device comprising: cell capacity target value setting means for setting a cell capacity adjustment target voltage; cell selection means for detecting an open-circuit voltage of each of the cells</code> | <code>1. A semiconductor package comprising: an encapsulant comprising: a semiconductor substrate in the encapsulant, the substrate comprising: a plurality of electrically conductive interconnects extending to the lower side of the encapsulant for electrically connecting the die contacts of the substrate to the surface; and a heat spreader in thermal contact with the backside of the semiconductor substrate for aiding thermal connection to the surface.</code>                                                                | <code>0.0</code> |
+  | <code>1. A method comprising: receiving a request from a user of a mobile device to track the mobile device; generating, in response to the request, a control signal to remotely activate an application on the mobile device for controlling an audio interface or an imaging interface of the mobile device to capture a signal from the audio interface or the imaging interface; receiving one or more signals captured from the audio interface or the imaging interface of the mobile device; determining to present the receiv</code> | <code>1. A method for monitoring the condition of an article comprising the steps of: a. affixing a covering made of a substrate that is coated with a layer of an electrically conductive material and forming a single electrically conductive surface that extends over the entire covering and has an electrical resistance, said covering being configured to at least partially encapsulate the article such that the article cannot be tampered with, without modifying the electrical resistance of said covering; b. producin</code> | <code>1.0</code> |
+  | <code>1. A system to store and to transmit electrical power, comprising a storage system comprising a central storage system used to store electrical power of at least one power source, an HVDC power transmission system to which the central storage system is connected, a first bidirectional converter connected at one side to the HVDC power transmission system, at least one an AC network connected to another side of the first bidirectional converter, a first load connected to the AC network and adapted to both, re</code> | <code>1. An elliptically polarized dielectric block antenna comprising: a linearly polarized dielectric block antenna; and a wave polarizer integrated with the linearly polarized dielectric block antenna, wherein the wave polarizer converts the linearly polarized wave of the linearly polarized dielectric block antenna into an elliptically polarized wave; wherein the wave polarizer is integrated with the dielectric block of the linearly polarized dielectric block antenna; and wherein the wave polarizer comprises o</code> | <code>0.0</code> |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: no
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1
+- `num_train_epochs`: 3
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `eval_use_gather_object`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Framework Versions
+- Python: 3.12.10
+- Sentence Transformers: 3.4.1
+- Transformers: 4.44.2
+- PyTorch: 2.4.1+cpu
+- Accelerate: 1.12.0
+- Datasets: 4.3.0
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

patentsberta_finetuned_final/config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "AI-Growth-Lab/PatentSBERTa",
+  "architectures": [
+    "MPNetModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "vocab_size": 30527
+}

patentsberta_finetuned_final/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.44.2",
+    "pytorch": "2.4.1+cpu"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

patentsberta_finetuned_final/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e28202556120966b12e1eb36376e58ead315bebb63ca3d735aaf7521e16a279c
+size 437967672

patentsberta_finetuned_final/modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

patentsberta_finetuned_final/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

patentsberta_finetuned_final/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

patentsberta_finetuned_final/tokenizer_config.json

@@ -0,0 +1,72 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

qlora_outputs.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98255cf9b1ea80fbf3b0d372f3627a10553ffea700a986a0d4c1b8dcb55a3bef
+size 891140146