Downloads · 30 days
4
3% of all-time downloads
mwalker22/AIE6-S09-b99b3324-c1e6-4624-bf18-42f7d114c011
AIE6-S09-b99b3324-c1e6-4624-bf18-42f7d114c011 is a sentence similarity model from mwalker22. Use it when you need a score for how close two texts are. It is set up for sentence-transformers.
This is a sentence-transformers model finetuned from Snowflake/snowflake-arctic-embed-l. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semanti…
Downloads · 30 days
4
3% of all-time downloads
All-time downloads
115
Public
Parameters
334M
1.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.3 GB · 100%
From the Hugging Face model README
This is a sentence-transformers model finetuned from Snowflake/snowflake-arctic-embed-l. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
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()
)
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("mwalker22/AIE6-S09-b99b3324-c1e6-4624-bf18-42f7d114c011")
# Run inference
sentences = [
'What licensing model does Qwen25-Coder-32B use?',
'Qwen2.5-Coder-32B is an LLM that can code well that runs on my Mac talks about Qwen2.5-Coder-32B in November—an Apache 2.0 licensed model!\n\nI can now run a GPT-4 class model on my laptop talks about running Meta’s Llama 3.3 70B (released in December)',
'The GPT-4 barrier was comprehensively broken\nSome of those GPT-4 models run on my laptop\nLLM prices crashed, thanks to competition and increased efficiency\nMultimodal vision is common, audio and video are starting to emerge\nVoice and live camera mode are science fiction come to life\nPrompt driven app generation is a commodity already\nUniversal access to the best models lasted for just a few short months\n“Agents” still haven’t really happened yet\nEvals really matter\nApple Intelligence is bad, Apple’s MLX library is excellent\nThe rise of inference-scaling “reasoning” models\nWas the best currently available LLM trained in China for less than $6m?\nThe environmental impact got better\nThe environmental impact got much, much worse',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]
# 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.*
-->
| Metric | Value |
|---|---|
| cosine_accuracy@1 | 0.9167 |
| cosine_accuracy@3 | 1.0 |
| cosine_accuracy@5 | 1.0 |
| cosine_accuracy@10 | 1.0 |
| cosine_precision@1 | 0.9167 |
| cosine_precision@3 | 0.3333 |
| cosine_precision@5 | 0.2 |
| cosine_precision@10 | 0.1 |
| cosine_recall@1 | 0.9167 |
| cosine_recall@3 | 1.0 |
| cosine_recall@5 | 1.0 |
| cosine_recall@10 | 1.0 |
| cosine_ndcg@10 | 0.9692 |
| cosine_mrr@10 | 0.9583 |
| cosine_map@100 | 0.9583 |
| sentence_0 | sentence_1 | |
|---|---|---|
| type | string | string |
| details | <ul><li>min: 2 tokens</li><li>mean: 20.74 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>min: 43 tokens</li><li>mean: 135.42 tokens</li><li>max: 214 tokens</li></ul> |
| sentence_0 | sentence_1 |
|---|---|
| <code>When did Meta release the original Llama model?</code> | <code>Then in February, Meta released Llama. And a few weeks later in March, Georgi Gerganov released code that got it working on a MacBook.<br>I wrote about how Large language models are having their Stable Diffusion moment, and with hindsight that was a very good call!<br>This unleashed a whirlwind of innovation, which was accelerated further in July when Meta released Llama 2—an improved version which, crucially, included permission for commercial use.<br>Today there are literally thousands of LLMs that can be run locally, on all manner of different devices.</code> |
| <code>What was significant about the release of Llama 2 in July?</code> | <code>Then in February, Meta released Llama. And a few weeks later in March, Georgi Gerganov released code that got it working on a MacBook.<br>I wrote about how Large language models are having their Stable Diffusion moment, and with hindsight that was a very good call!<br>This unleashed a whirlwind of innovation, which was accelerated further in July when Meta released Llama 2—an improved version which, crucially, included permission for commercial use.<br>Today there are literally thousands of LLMs that can be run locally, on all manner of different devices.</code> |
| <code>What is the new way to scale a model mentioned in the context?</code> | <code>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.<br>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!<br>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.</code> |
{
"loss": "MultipleNegativesRankingLoss",
"matryoshka_dims": [
768,
512,
256,
128,
64
],
"matryoshka_weights": [
1,
1,
1,
1,
1
],
"n_dims_per_step": -1
}
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 | 0.9583 |
| 2.0 | 32 | 0.9484 |
| 3.0 | 48 | 0.9539 |
| 3.125 | 50 | 0.9539 |
| 4.0 | 64 | 0.9692 |
| 5.0 | 80 | 0.9692 |
| 6.0 | 96 | 0.9692 |
| 6.25 | 100 | 0.9692 |
| 7.0 | 112 | 0.9692 |
| 8.0 | 128 | 0.9692 |
| 9.0 | 144 | 0.9692 |
| 9.375 | 150 | 0.9692 |
| 10.0 | 160 | 0.9692 |
@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",
}
@misc{kusupati2024matryoshka,
title={Matryoshka Representation Learning},
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},
year={2024},
eprint={2205.13147},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
@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}
}
<!--
## 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.*
-->