Instructions to use its-zion-18/projfinetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use its-zion-18/projfinetuned with sentence-transformers:

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("its-zion-18/projfinetuned")

sentences = [
    "VFX Artist (CONTRACT)",
    "Software Engineer Google Write clean, well-documented, and efficient code.\nParticipate in code reviews and provide constructive feedback.\nCollaborate with cross-functional teams to define and deliver features.\nTroubleshoot and debug production issues. Bachelor's or Master's degree in Computer Science or a related field.\n5+ years of experience in software development.\nProficiency with one or more programming languages (e.g., C++, Java, Python).\nExperience with large-scale distributed systems. Design, develop, and maintain software applications and systems. You will be responsible for writing clean, efficient code, collaborating with a team of engineers, and ensuring the reliability and scalability of products. This is a hands-on role that requires strong technical skills.",
    "VFX Artist (CONTRACT)  Creates, designs, and implements real-time particle effects using both static and animating 2D/3D elements\nPlacing of visual FX across all areas of the game, including environmental and gameplay FX, and cinematics\ncreate FX textures (color, normal, specular, ambient occlusion, height, and incandescent maps.)\nPossesses at least an intermediate ability to navigate and use DCC software such as Maya, Houdini, or equivalent\nCreates FX shaders with node-based shader networks\nCreates simple geometry and UV sets\nPossesses an intermediate foundation in computer graphics fundamentals and artistic analysis\nOptimizes FX for framerate and memory\nCollaborates with other development departments to ensure that FX are implemented appropriately in the game engine\nUnderstand and adds to the overall art style of game\nOrchestrates FX events involving layering and timing of different FX to create a believable scene\nKnowledge of other visual effects software is a plus Demonstrated professionalism in attendance, communication, reading comprehension, receiving feedback and working in a production setting\nAbility to define problems, collect data, establish facts, and draw valid conclusions\nAbility to interpret an extensive variety of technical instructions in mathematical or diagram form and deal with several abstract and concrete variables\nProficient in Maya, competent working with joints and locators, keyframing, rigid body simulations, hard surface modeling, and UV mapping\nProficient in Photoshop for painting and editing textures\nProficient with node-based shader networks\nGood team skills, collaborative attitude, and good observation skills and ability to use reference materials\nAbility to work independently\nSolid traditional arts background a plus\nAt SIE, working with our partners, we consider several factors when setting each role’s base pay range, including the competitive benchmarking data for the market and geographic location. Please note that the individual base pay range may vary based on job-related factors which may include knowledge, skills, experience, and location. In addition, this role is eligible for benefit offerings that include medical, dental, and vision. Click here to learn more.\nThe estimated base pay range for this role is listed below, this is an hourly rate.\n$75 - $90 USD\nAccepted file types: pdf, doc, docx, txt, rtf Insomniac Games is looking for a VFX Artist. In this role, the VFX Artist is responsible for creating VFX to work and assist in gameplay, environment, and cinematics of a game.",
    "Data Center Facilities Technician, Controls Google Inspect, maintain, and repair various data center systems such as servers, network equipment, Programmable Logic Controllers (PLCs), system administration, access control, alarm investigation, and Supervisory Control and Data Acquisition (SCADA) management.\nProvide daily assistance to technicians as you read blueprints/schematics/ladder logic/sequence of operations, conduct tours of systems, and assess their working order.\nControl, monitoring, logging, and alarming systems.\nOperate, monitor, maintain, and respond to abnormal conditions in the data center facilities systems and equipment.\nSupport startup, commissioning, and integration of new controls equipment and systems into facilities infrastructure. Associate's degree, trade school certification, or other certified training in a related technical field, or equivalent practical experience.\n2 years of experience in Controls/Automation in an industrial or commercial environment.\nAbility to participate in material handling tasks such as lifting, carrying or moving up to 50 lbs of equipment, the required use of OSHA standard safety equipment such as limited weight bearing work platforms, ladders, step stools and Personal Protective Equipment (PPE) like safety harnesses.\nAbility to work non-standard hours and differing work rotations/shifts.\nIndustry standard certifications related to system administration (e.g., CompTIA A+, CompTIA Network+, CompTIA Security+, Certified Windows or Linux system administrator).\n2 years of experience in controls/automation, or construction/technical environment or a related field.\nExperience in data centers, hospitals, power plants, or laboratories.\nKnowledge of meters, devices, sensors, relays and troubleshooting utilizing standard hand tools, digital metering, or calibration/diagnostic equipment.\nProficiency in Scripting language.\nAbility to communicate with contractors who perform maintenance or upgrade work on the data center systems.\nGoogle is a global company and, in order to facilitate efficient collaboration and communication globally, English proficiency is a requirement for all roles unless stated otherwise in the job posting. The Data Center team designs and operates some of the most sophisticated electrical engineering, mechanical engineering and HVAC systems in the world. Facilities Technicians at Google data centers operate, monitor and support physical facilities conditions. Some of these duties will include heating and cooling of air and water, power supply, generators, UPS systems, electrical distribution and control and monitoring systems. You regularly help inspect, maintain and repair various data center systems such as piping and non-critical electrical or mechanical system components). You provide daily assistance to senior technicians as you read blueprints/schematics, conduct tours of systems and assess their working order. As an advocate for best practices, you develop creative approaches to reducing operational costs while improving overall data center efficiency. You ensure that environmental and safety standards are consistently met, identifying problems and making repairs quickly. In emergency situations or abnormal conditions, you manage data center performance issues and outages to minimize the recovery time from failures.\nAs a Facilities Technician, you will operate, monitor, and support physical facilities conditions for our data centers.\nTo all recruitment agencies: Google does not accept agency resumes. Please do not forward resumes to our jobs alias, Google employees, or any other organization location. Google is not responsible for any fees related to unsolicited resumes."
]
embeddings = model.encode(sentences)

similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [4, 4]

Notebooks
Google Colab
Kaggle

SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2. It maps sentences & paragraphs to a 384-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: sentence-transformers/all-MiniLM-L6-v2
Maximum Sequence Length: 256 tokens
Output Dimensionality: 384 dimensions
Similarity Function: Cosine Similarity

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Normalize()
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("its-zion-18/projfinetuned")
# Run inference
sentences = [
    'Manager, Social Sales & Newsletters',
    'Manager, Social Sales & Newsletters  Collaborate with the sales team to drive revenue and sales for social advertising business, ensuring revenue goals are hit quarterly and annually.\nManage day-to-day sales requests providing targeting information and inventory requests to sales planners & reps to assist in their pre-sale initiatives\nCollaborate with the sales team to drive revenue and sales for newsletter partnerships, ensuring revenue goals are hit quarterly and annually.\nAttend live events and partner with stakeholders to ensure contracted social elements for clients are operating smoothly when necessary\nManage communications and organization from pre-sale to post-sale including managing tracker of programs, working on brainstorms in pre-sale, joining kick off calls in post-sale, looping in social activation and newsletter teams and providing campaign details\nStrong understanding of social media best practices, trends and advertising on social platforms\nWe are holding ourselves accountable and ensuring that all decisions are made with equity top of mind. Bachelor’s Degree in Business, Marketing, Communications or a related field\n3-5 years of relevant experience\nCreative storyteller\nCreator economy experience a must\nStrong proficiency in Excel, Google Drive\nAbility to multi-task, efficiently manage time and prioritize deliverables\nForbes has estimated the compensation range set forth above in good faith.\xa0 The compensation range is what we believe we will offer, and ultimately pay, a successful candidate.\xa0 In determining this range, we consider the experience, level of education (if applicable to the role), knowledge, skills, and abilities required to be had by a successful candidate as well as the budget and the company’s pay rates, generally. This said, we may have to make changes to our compensation estimates and job descriptions from time to time and we expressly reserve the right to do so.\xa0 Should we make any such changes, this advertisement will be revised to reflect such revisions.\xa0 We encourage you to occasionally re-visit this advertisement to ensure that you are abreast of any changes.\xa0 Thank you for your interest in joining Forbes!\nForbes aims to offer employees the flexibility they need in order to be successful. Some positions may require candidates to be based in a specific location for consideration while some roles may be fully remote (within the U.S.) if it aligns with the needs of the position. This position is only open to candidates residing in California, Colorado, Connecticut, District of Columbia, Florida, Georgia, Maine, Maryland, Massachusetts, New Jersey, New York, North Carolina, Pennsylvania, South Carolina, Tennessee, Texas, & Washington. Due to business operations and compliance requirements, we are unable to consider applicants based outside these states at this time.\nCreate a Job Alert\nInterested in building your career at Forbes? Get future opportunities sent straight to your email.\nAccepted file types: pdf, doc, docx, txt, rtf Forbes is an iconic global media brand that has symbolized success for over a century. Fueled by journalism that informs and inspires, Forbes spotlights the doers and doings shaping industries, achieving success and making an impact on the world. Forbes connects and convenes the most influential communities ranging from billionaires, business leaders and rising entrepreneurs to creators and innovators. The Forbes brand reaches more than 140 million people monthly worldwide through its trusted journalism, signature ForbesLive events and 49 licensed local editions in 81 countries.\nForbes Media is hiring a Manager, Social Sales & Newsletters to join our AI & Strategic Platforms team. This role will focus on driving revenue, strategic business development and representing the social and newsletter products at Forbes. This includes collaborating with key stakeholders at Forbes to drive sales, develop creative strategy for social activations, create new products and work with clients on bringing social advertising to life. This role will report into the Senior Director, Client Activation & Paid Social.\nOur office operates as a remote and hybrid workforce, with in-person collaboration expected for certain roles. Based on the responsibilities of this position, a hybrid work schedule with a minimum of one in-person collaboration day per week at our Jersey City, NJ headquarters is expected.\nParticipating in client-facing conversations as a social media and newsletter expert on behalf of Forbes when needed\nBrainstorm and ideate social & newsletter packages attached to Forbes’ products including editorial, live partnerships, content and social only\nBrainstorm and bring to market new social activations and opportunities for Forbes Live Event advertisers\nLiaison with key Forbes stakeholders including sales reps, account managers, sales planners, editorial social, live programming, integrated marketing, video producers, etc.\nPartner with external partners including LinkedIn, Meta, TikTok, influencer talent agencies, etc.\nForbes is committed to diversity, equity and inclusion and uses our various platforms to help the world build back with equity at its core. As the leading business media brand, we have a responsibility to ensure our content and experiences reflect the diverse audiences we serve. We have the unique ability to do good, leveraging our considerable editorial voice to highlight inequities and challenge systems.',
    'Firmware Engineer  Evaluate, benchmark, and select SoC/MCU platforms suitable for vision workloads and potential cloud integration.\nPrototype and deploy vision pipelines: capture raw image frames, perform preprocessing (ISP, color conversions), and manage AI inference models either locally or via cloud services.\nCollaborate with hardware teams to select optimal image sensors, lenses, and camera modules for object detection and classification tasks.\nImplement low-level drivers (I²C/SPI, GPIO, PWM) and incorporate them into device trees and board-support packages.\nWork with other team members to define and implement inter-processor communication protocols (SPI/UART/I²C) for sensor data exchange and system telemetry.\nEnsure coexistence of camera subsystems with other embedded peripherals (touchscreen, motors, sensors, connectivity modules) without performance degradation.\nExperience with OTA firmware updates for MCUs (bootloaders) and SoCs (partition management). Bachelor’s or Master’s degree in Computer Science, Electrical Engineering, or related discipline, or equivalent experience.\n5+ years experience in embedded firmware engineering, including at least 3 years focused on camera or vision applications.\nStrong proficiency in C/C++ (Linux kernel drivers or RTOS firmware), with knowledge of memory management, DMA, interrupts, and real-time system constraints.\nHands-on experience with camera interfaces: MIPI-CSI-2, USB Video Class (UVC), or parallel RGB; comfortable working with image sensor datasheets, register programming, and sensor configuration.\nFamiliarity with vision frameworks (OpenCV, TensorRT, TensorFlow Lite, Edge TPU) or cloud-based AI processing platforms (AWS, Azure, Google Cloud); capable of prototyping object detection or segmentation pipelines, profiling performance, and suggesting optimizations.\nSolid understanding of I²C, SPI, UART, and GPIO interfaces.\nProven prototyping ability—quickly translating high-level performance targets into functional prototypes and effectively evaluating hardware-software tradeoffs.\nSkilled in using logic analyzers, oscilloscopes, and debugging tools (JTAG, GDB) to troubleshoot camera issues.\nExcellent communication skills, capable of producing clear documentation, architecture diagrams, and engaging in effective cross-team collaboration.\nExperience with camera calibration techniques, including lens distortion correction and color-space conversions.\nExperience with integrating touchscreen panels (LVDS/DSI/HDMI) and touch controllers (I²C/SPI), and developing responsive user interfaces.\nDevelop and optimize embedded UI frameworks (e.g., Qt Embedded, LVGL).\nFamiliarity with Linux system architectures, cross-compilation, build systems, and kernel module integration.\nPrevious experience in startups or rapid prototyping environments.\nFamiliarity with Agile methodologies, version control (GitHub), CI/CD pipelines, and project management tools (JIRA).\nInterested in building your career at Mill? Get future opportunities sent straight to your email.\nAccepted file types: pdf, doc, docx, txt, rtf Mill is all about answering a simple question: how can we prevent waste? Less waste can save time, money, energy, maybe even our planet. And there’s no better place to start than food. Food waste is one of the most solvable climate problems facing us today. Plus, our trash really stinks. It’s gross, heavy, and our least favorite chore. At Mill we are striving to build a better environment for all, as we take on climate and kitchen change.\nWe are seeking an extraordinary Firmware Engineer to lead the vision system development for our next-generation product. You will evaluate SoC and MCU platforms, and develop camera-based AI applications for object detection (either on-device or cloud-based). Collaborating closely with hardware designers, connectivity experts, and system engineers, your work will be crucial in turning innovative concepts into functional prototypes and products.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[     1.0000,      0.7013,     -0.0001],
#         [     0.7013,      1.0000,      0.1803],
#         [    -0.0001,      0.1803,      1.0000]])

Training Details

Training Dataset

Unnamed Dataset

Size: 391 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 391 samples:
sentence_0 sentence_1
type string string
details
min: 2 tokens
mean: 7.03 tokens
max: 30 tokens

min: 2 tokens
mean: 240.47 tokens
max: 256 tokens

	sentence_0	sentence_1
type	string	string
details	min: 2 tokens mean: 7.03 tokens max: 30 tokens	min: 2 tokens mean: 240.47 tokens max: 256 tokens

Samples:

sentence_0	sentence_1
`Electronics Engineer`	Electronics Engineer National Telecommunications and Information Administration Perform basic or applied research or engineering in such areas as propagation theory, scattering and diffraction, antenna design and optimization, radiated electromagnetic interference, and microwave systems. Oversee and conduct lab and field measurements and/or develop, refine, and validate state-of-the-art theoretical and empirical radio propagation, spectrum, or wireless system models. Develop software tools that use measurement findings and simulations to evaluate wireless system performance, predict technology behavior under various deployment conditions, and recommend more efficient uses of the radio spectrum. Apply digital signal processing methods-including techniques for noise reduction, sampling, spectral estimation, filtering, and real-time detection and estimation-in software and hardware to analyze wireless signals. Develop research proposals and present plans, progress, financials, and finding...
`Procurement Agent`	Procurement Agent Boeing Communicate performance expectations and metrics to the supplier Travel to suppliers and conduct assessments to ensure the supplier’s ongoing capability to support Boeing Provide oversight and management of the supply and demand of parts, schedules, and supplier quality and delivery Analyze and track Key Performance Indicators (KPIs) (things like on-time delivery) and using those indicators to predict risks; assist suppliers to develop new predictive indicators as needed Mitigate discovered risks and initiate and implement supplier recovery plans and improvement activities Lead Root Cause/Corrective Action initiatives to improve systemic issues Facilitate cross-functional discussions regarding technical approaches, the resolution of quality issues, and the improvement of products and processes Perform some level of system transactions and data entry to maintain Enterprise Resource Planning (ERP) and/or SAP fidelity, support metric generation, and maintain stake...
`Digital Design Developer, Opinion`	Digital Design Developer, Opinion The New York Times Company Office: New York, NY Department: Editing Develop templates for recurring editorial features. Optimize projects to load and perform across browsers and devices. You will report to Deputy Editor Design. Familiarity with Git and collaborative coding workflows 5+ years of digital design experience Visual and interactive design skills — a clear grasp of typography, layout, color, motion, and behavior Experience in client-side Web development, including JavaScript, HTML and CSS required Experience working with video, audio, graphics Experience or familiarity with Svelte Ability to work in a fast-paced news environment with a willingness to work a flexible, news-driven schedule that may occasionally include nights or weekends The mission of The New York Times is to seek the truth and help people understand the world. That means independent journalism is at the heart of all we do as a company. It’s why we have a world-renowned news...

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "gather_across_devices": false
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 1
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: no
prediction_loss_only: True
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
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: 1
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}
parallelism_config: None
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch_fused
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: None
hub_always_push: False
hub_revision: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
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
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
use_liger_kernel: False
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin
router_mapping: {}
learning_rate_mapping: {}

Framework Versions

Python: 3.12.11
Sentence Transformers: 5.1.1
Transformers: 4.56.2
PyTorch: 2.8.0+cu126
Accelerate: 1.10.1
Datasets: 4.0.0
Tokenizers: 0.22.1

Citation

BibTeX

Sentence Transformers

@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",
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}