Views
No views yet
SentenceTransformer(
(0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: 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()
)pip install -U sentence-transformers1from sentence_transformers import SentenceTransformer
2
3# Download from the 🤗 Hub
4model = SentenceTransformer("sentence_transformers_model_id")
5# Run inference
6sentences = [
7 "[PC] [2000s] Western themed kids game with blue main character?\n\nI'm re-visiting a bunch of games from my childhood, and I cannot for the life of me remember what this game is called. It was a western themed game in a cartoony style, and I'm pretty sure that the main character was a little blue monster, possibly with a bandana? \n\n\nI'm pretty sure it was an educational game, since my parents didn't really buy me non-educational CD-ROMs as a kid. If I remember correctly, you were in a town, and could go to various other places around the town with other characters. I know there's a Fisher Price game that's western themed with a town, but it wasn't that one.",
8 'kid phonics 2',
9 'the scruffs',
10]
11embeddings = model.encode(sentences)
12print(embeddings.shape)
13# [3, 384]
14
15# Get the similarity scores for the embeddings
16similarities = model.similarity(embeddings, embeddings)
17print(similarities.shape)
18# [3, 3]sentence_0 and sentence_1| sentence_0 | sentence_1 | |
|---|---|---|
| type | string | string |
| details |
|
|
| sentence_0 | sentence_1 |
|---|---|
[PC BROWSER] [LATE 2000] Old flash, creepy, mystery, puzzle game[object Object][object Object]I can hardly remember it but I think it had something to do with a point and click sort of puzzle where you would visit different planets. One planet had an old man sleeping, his nose/mouth was making bubbles and you could pop them. [object Object][object Object]You sort of interacted with the world until you figured something out in the correct order. It was possibly in black and white? [object Object][object Object]It had a creepy, weird sort of art style maybe. | [PC] [Unknown] Game about a child on the moon[object Object][object Object]Hello, I was recently thinking back to some of my years in primary school and remembered small bits and pieces of one of the few games we were allowed to play back then; Something about a character (probably a child) in an astronaut costume on the moon (I think we were accompanied by a dog too), I don't know what exactly this kind of game is called but it was set up terraria, where the world is almost 2D in appearance. The character models were 3D, but you could only see the side views (I believe anyways, I also remember getting stuck playing this game really easily so maybe I just never got to a point where you could see the rest of the model) [object Object]I remember having played this around 2016-2017 (I'd be 8 or 9) because my school only let people use the allocated computers when they reach the grade I was in at that time, but I suspect the game is older than that. Seeing as that was 7-8 years ago (wow), I don't remember very much about it, but ... |
[PC][early 2000s] Kid’s game with pirate mice[object Object][object Object]Platform: PC[object Object][object Object]Estimated year of release: I believe I played in early to mid 2000s[object Object][object Object]Genre: Children’s Learning Game[object Object][object Object]Graphics/art style: cartoonish [object Object][object Object]Notable characters: from what I remember — villainous pirate mice, hero mice, one was a bigger, goofy mouse (I think he was a pirate) [object Object][object Object]Notable gameplay mechanics: I think the goal was to thwart the pirate mice from stealing/hoarding cheese[object Object][object Object]Other details: I remember a pretty fleshed out storyline; good voice acting; a mouse on the hero side with blonde hair I think. It’s also possible all the mice were pirates and that there were just good and bad mice pirates. I also think I remember a flying ship. Thanks! | [PC] [late 1990s-early 2000s] educational children's game with female mouse who sails on a ship[object Object][object Object]I'm specifically trying to find either what I think is either an opening or ending cutscene. There's a female mouse (or some other kind of rodent) on a ship at sunset, singing a song about sailing on the open sea. I think she has a male mouse companion, and possibly other animals. I believe the game is mostly math problems. Something like a Jumpstart or Reader Rabbit game, but I haven't been able to find this cutscene in any playthroughs that I've scene on Youtube. |
All I know is there was a shark scene[object Object][object Object]All I can remember about this game is that at some point you're at a movie studio type area (maybe?) and you recreate the scene in jaws where the ship sinks and you have to climb up the mast of the fishing boat. Its killing me please someone put me out of my misery. | universal studios theme park adventure for gamecube |
MultipleNegativesRankingLoss with these parameters:
1{
2 "scale": 20.0,
3 "similarity_fct": "cos_sim"
4}per_device_train_batch_size: 128per_device_eval_batch_size: 128multi_dataset_batch_sampler: round_robinoverwrite_output_dir: Falsedo_predict: Falseeval_strategy: noprediction_loss_only: Trueper_device_train_batch_size: 128per_device_eval_batch_size: 128per_gpu_train_batch_size: Noneper_gpu_eval_batch_size: Nonegradient_accumulation_steps: 1eval_accumulation_steps: Nonetorch_empty_cache_steps: Nonelearning_rate: 5e-05weight_decay: 0.0adam_beta1: 0.9adam_beta2: 0.999adam_epsilon: 1e-08max_grad_norm: 1num_train_epochs: 3max_steps: -1lr_scheduler_type: linearlr_scheduler_kwargs: Nonewarmup_ratio: 0.0warmup_steps: 0log_level: passivelog_level_replica: warninglog_on_each_node: Truelogging_nan_inf_filter: Truesave_safetensors: Truesave_on_each_node: Falsesave_only_model: Falserestore_callback_states_from_checkpoint: Falseno_cuda: Falseuse_cpu: Falseuse_mps_device: Falseseed: 42data_seed: Nonejit_mode_eval: Falsebf16: Falsefp16: Falsefp16_opt_level: O1half_precision_backend: autobf16_full_eval: Falsefp16_full_eval: Falsetf32: Nonelocal_rank: 0ddp_backend: Nonetpu_num_cores: Nonetpu_metrics_debug: Falsedebug: []dataloader_drop_last: Falsedataloader_num_workers: 0dataloader_prefetch_factor: Nonepast_index: -1disable_tqdm: Falseremove_unused_columns: Truelabel_names: Noneload_best_model_at_end: Falseignore_data_skip: Falsefsdp: []fsdp_min_num_params: 0fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}fsdp_transformer_layer_cls_to_wrap: Noneaccelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}parallelism_config: Nonedeepspeed: Nonelabel_smoothing_factor: 0.0optim: adamw_torchoptim_args: Noneadafactor: Falsegroup_by_length: Falselength_column_name: lengthproject: huggingfacetrackio_space_id: trackioddp_find_unused_parameters: Noneddp_bucket_cap_mb: Noneddp_broadcast_buffers: Falsedataloader_pin_memory: Truedataloader_persistent_workers: Falseskip_memory_metrics: Trueuse_legacy_prediction_loop: Falsepush_to_hub: Falseresume_from_checkpoint: Nonehub_model_id: Nonehub_strategy: every_savehub_private_repo: Nonehub_always_push: Falsehub_revision: Nonegradient_checkpointing: Falsegradient_checkpointing_kwargs: Noneinclude_inputs_for_metrics: Falseinclude_for_metrics: []eval_do_concat_batches: Truefp16_backend: autopush_to_hub_model_id: Nonepush_to_hub_organization: Nonemp_parameters:auto_find_batch_size: Falsefull_determinism: Falsetorchdynamo: Noneray_scope: lastddp_timeout: 1800torch_compile: Falsetorch_compile_backend: Nonetorch_compile_mode: Noneinclude_tokens_per_second: Falseinclude_num_input_tokens_seen: noneftune_noise_alpha: Noneoptim_target_modules: Nonebatch_eval_metrics: Falseeval_on_start: Falseuse_liger_kernel: Falseliger_kernel_config: Noneeval_use_gather_object: Falseaverage_tokens_across_devices: Trueprompts: Nonebatch_sampler: batch_samplermulti_dataset_batch_sampler: round_robin| Epoch | Step | Training Loss |
|---|---|---|
| 0.2308 | 500 | 3.4998 |
| 0.4617 | 1000 | 2.8783 |
| 0.6925 | 1500 | 2.6795 |
| 0.9234 | 2000 | 2.5377 |
| 1.1542 | 2500 | 2.3956 |
| 1.3850 | 3000 | 2.3053 |
| 1.6159 | 3500 | 2.2521 |
| 1.8467 | 4000 | 2.2323 |
| 2.0776 | 4500 | 2.163 |
| 2.3084 | 5000 | 2.1002 |
| 2.5392 | 5500 | 2.0794 |
| 2.7701 | 6000 | 2.0712 |
1@inproceedings{reimers-2019-sentence-bert,
2 title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
3 author = "Reimers, Nils and Gurevych, Iryna",
4 booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
5 month = "11",
6 year = "2019",
7 publisher = "Association for Computational Linguistics",
8 url = "https://arxiv.org/abs/1908.10084",
9}1@misc{henderson2017efficient,
2 title={Efficient Natural Language Response Suggestion for Smart Reply},
3 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},
4 year={2017},
5 eprint={1705.00652},
6 archivePrefix={arXiv},
7 primaryClass={cs.CL}
8}