Views
No views yet
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 1024, '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})
(2): Normalize()
)pip install -U sentence-transformers1from sentence_transformers import SentenceTransformer
2
3# Download from the 🤗 Hub
4model = SentenceTransformer("afulara/legal-ft-527ef5e4-666a-47eb-870a-04fce17590e1")
5# Run inference
6sentences = [
7 'What is the most important factor in determining the quality of a trained model according to the context?',
8 'Intuitively, one would expect that systems this powerful would take millions of lines of complex code. Instead, it turns out a few hundred lines of Python is genuinely enough to train a basic version!\nWhat matters most is the training data. You need a lot of data to make these things work, and the quantity and quality of the training data appears to be the most important factor in how good the resulting model is.\nIf you can gather the right data, and afford to pay for the GPUs to train it, you can build an LLM.',
9 'So training an LLM still isn’t something a hobbyist can afford, but it’s no longer the sole domain of the super-rich. I like to compare the difficulty of training an LLM to that of building a suspension bridge—not trivial, but hundreds of countries around the world have figured out how to do it. (Correction: Wikipedia’s Suspension bridges by country category lists 44 countries).\nYou can run LLMs on your own devices\nIn January of this year, I thought it would be years before I could run a useful LLM on my own computer. GPT-3 and 3.5 were pretty much the only games in town, and I thought that even if the model weights were available it would take a $10,000+ server to run them.',
10]
11embeddings = model.encode(sentences)
12print(embeddings.shape)
13# [3, 1024]
14
15# Get the similarity scores for the embeddings
16similarities = model.similarity(embeddings, embeddings)
17print(similarities.shape)
18# [3, 3]InformationRetrievalEvaluator| Metric | Value |
|---|---|
| cosine_accuracy@1 | 0.875 |
| cosine_accuracy@3 | 1.0 |
| cosine_accuracy@5 | 1.0 |
| cosine_accuracy@10 | 1.0 |
| cosine_precision@1 | 0.875 |
| cosine_precision@3 | 0.3333 |
| cosine_precision@5 | 0.2 |
| cosine_precision@10 | 0.1 |
| cosine_recall@1 | 0.875 |
| cosine_recall@3 | 1.0 |
| cosine_recall@5 | 1.0 |
| cosine_recall@10 | 1.0 |
| cosine_ndcg@10 | 0.9539 |
| cosine_mrr@10 | 0.9375 |
| cosine_map@100 | 0.9375 |
sentence_0 and sentence_1| sentence_0 | sentence_1 | |
|---|---|---|
| type | string | string |
| details |
|
|
| sentence_0 | sentence_1 |
|---|---|
What is the new way to scale a model mentioned in the context? | The biggest innovation here is that it opens up a new way to scale a model: instead of improving model performance purely through additional compute at training time, models can now take on harder problems by spending more compute on inference.[object Object]The sequel to o1, o3 (they skipped “o2” for European trademark reasons) was announced on 20th December with an impressive result against the ARC-AGI benchmark, albeit one that likely involved more than $1,000,000 of compute time expense![object Object]o3 is expected to ship in January. I doubt many people have real-world problems that would benefit from that level of compute expenditure—I certainly don’t!—but it appears to be a genuine next step in LLM architecture for taking on much harder problems. |
Why was the sequel named o3 instead of o2? | The biggest innovation here is that it opens up a new way to scale a model: instead of improving model performance purely through additional compute at training time, models can now take on harder problems by spending more compute on inference.[object Object]The sequel to o1, o3 (they skipped “o2” for European trademark reasons) was announced on 20th December with an impressive result against the ARC-AGI benchmark, albeit one that likely involved more than $1,000,000 of compute time expense![object Object]o3 is expected to ship in January. I doubt many people have real-world problems that would benefit from that level of compute expenditure—I certainly don’t!—but it appears to be a genuine next step in LLM architecture for taking on much harder problems. |
What are some companies mentioned that have developed multi-modal audio models? | Your browser does not support the audio element.[object Object][object Object]OpenAI aren’t the only group with a multi-modal audio model. Google’s Gemini also accepts audio input, and the Google Gemini apps can speak in a similar way to ChatGPT now. Amazon also pre-announced voice mode for Amazon Nova, but that’s meant to roll out in Q1 of 2025.[object Object]Google’s NotebookLM, released in September, took audio output to a new level by producing spookily realistic conversations between two “podcast hosts” about anything you fed into their tool. They later added custom instructions, so naturally I turned them into pelicans:[object Object][object Object][object Object]Your browser does not support the audio element. |
MatryoshkaLoss with these parameters:
1{
2 "loss": "MultipleNegativesRankingLoss",
3 "matryoshka_dims": [
4 768,
5 512,
6 256,
7 128,
8 64
9 ],
10 "matryoshka_weights": [
11 1,
12 1,
13 1,
14 1,
15 1
16 ],
17 "n_dims_per_step": -1
18}eval_strategy: stepsper_device_train_batch_size: 10per_device_eval_batch_size: 10num_train_epochs: 10multi_dataset_batch_sampler: round_robinoverwrite_output_dir: Falsedo_predict: Falseeval_strategy: stepsprediction_loss_only: Trueper_device_train_batch_size: 10per_device_eval_batch_size: 10per_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: 10max_steps: -1lr_scheduler_type: linearlr_scheduler_kwargs: {}warmup_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: Falseuse_ipex: 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}tp_size: 0fsdp_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}deepspeed: Nonelabel_smoothing_factor: 0.0optim: adamw_torchoptim_args: Noneadafactor: Falsegroup_by_length: Falselength_column_name: lengthddp_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: Falsegradient_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: Falseneftune_noise_alpha: Noneoptim_target_modules: Nonebatch_eval_metrics: Falseeval_on_start: Falseuse_liger_kernel: Falseeval_use_gather_object: Falseaverage_tokens_across_devices: Falseprompts: Nonebatch_sampler: batch_samplermulti_dataset_batch_sampler: round_robin| Epoch | Step | cosine_ndcg@10 |
|---|---|---|
| 1.0 | 16 | 0.9638 |
| 2.0 | 32 | 0.9484 |
| 3.0 | 48 | 0.9539 |
| 3.125 | 50 | 0.9539 |
| 4.0 | 64 | 0.9692 |
| 5.0 | 80 | 0.9539 |
| 6.0 | 96 | 0.9539 |
| 6.25 | 100 | 0.9539 |
| 7.0 | 112 | 0.9539 |
| 8.0 | 128 | 0.9539 |
| 9.0 | 144 | 0.9539 |
| 9.375 | 150 | 0.9539 |
| 10.0 | 160 | 0.9539 |
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{kusupati2024matryoshka,
2 title={Matryoshka Representation Learning},
3 author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
4 year={2024},
5 eprint={2205.13147},
6 archivePrefix={arXiv},
7 primaryClass={cs.LG}
8}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}