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 retrieval.

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
Supported Modality: Text

Model Sources

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

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'})
  (1): Pooling({'embedding_dimension': 384, 'pooling_mode': 'mean', '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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("ronit01/rag_tuned_minilm_mnr_10")
# Run inference
sentences = [
    "What is the difference between distributive and algebraic metrics in RapidFire AI's online aggregation for evals?",
    'Types of Metrics\n-----------------------\n\nWe support 2 types of metrics based on their aggregation semantics: \n\n* **Distributive Metrics:** These are purely additive over a given set of data points. \n  \n  Examples: *count* of number of correct predictions; *sum* of output token lengths across queries.\n\n* **Algebraic Metrics:** These are averages or proportions over a given set of data points. They can be decomposed into components that are individually distributive. \n  \n  Examples: *precision*, which counts number of correct predictions and total number of data points separately and then divides them; *mean rouge-1*, which averages per-example rouge-1 values that assesses overlap of tokens between generated text and ground truth text.\n\nWhen you define an eval metric via :func:`evals.compute_metrics_fn()` and :func:`evals.accumulate_metrics_fn()`, \nyou must specify their type (algebraic or distributive) and value range as illustrated below. \nFor metrics without a type defined, they will be displayed *as is*, i.e., without projected \nestimates or confidence intervals.',
    'RapidFire AI offers a browser-based dashboard to automatically visualize all ML metrics and lets \nyou control runs on the fly from there. \nOur current default dashboard is a fork of the popular OSS tool `MLflow <https://mlflow.org/>`__, \nand it inherits much of MLflow\'s native features.\nThe dashboard URI is printed when the rapidfireai server is started; open it in a browser. \n\nAs of this writing, apart from MLflow, RapidFire AI also supports \n`TensorBoard  <https://www.tensorflow.org/tensorboard>`__\nand `Trackio <https://huggingface.co/docs/trackio/en/index>`__\nfor logging metrics plots. \nSpecify any one, two, or all three dashboards to use with the following server start argument. \n\n.. code-block:: bash\n\n   rapidfireai start --tracking-backends [mlflow | tensorboard | trackio]\n\nAlternatively, set the dashboard using its environment variable as below in your python code/notebook:\n\n.. code-block:: python\n\n   os.environ["RF_MLFLOW_ENABLED"] = "true"\n   os.environ["RF_TENSORBOARD_ENABLED"] = "true"\n   os.environ["RF_TRACKIO_ENABLED"] = "true"\n\nSupport for other popular dashboards such as Weights & Biases and CometML is coming soon. \nThe rest of this section explains the new features of our MLflow-fork dashboard.\nNote that these new features are not yet available on the other dashboards.',
]
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, 0.6788, 0.1914],
#         [0.6788, 1.0000, 0.2678],
#         [0.1914, 0.2678, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

Size: 52 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 52 samples:
sentence_0 sentence_1
type string string
details
min: 11 tokens
mean: 24.87 tokens
max: 34 tokens
min: 31 tokens
mean: 216.15 tokens
max: 256 tokens

Samples:

sentence_0	sentence_1
`Why does RapidFire AI argue that simply downsampling the evaluation data is insufficient compared to its online aggregation approach?`	Why Not Just Downsample?[object Object]------------------------[object Object][object Object]One might wonder why downsampling the eval set does not suffice here. [object Object]:doc:[object Object], downsampling alone has [object Object]significant disadvantages compared to the approach offered by RapidFire AI. [object Object][object Object]First, you have to decide a downsample size upfront, which is not trivial if your[object Object]eval metrics have high variance across examples. Point estimates without confidence [object Object]intervals can give false confidence in a sample. You can resample manually [object Object]over and over, but that adds manual grunt work of juggling separate samples/files. [object Object]Finally, downsampling alone does not offer you the power of IC Ops and automated [object Object]parallelization to try new configs on the fly--you'd have reimplement those manually.[object Object][object Object]RapidFire AI's online aggregation approach with IC Ops avoids all the above issues,[object Object]while also being [object Object] to downsampling, i.e., you can use both in [object Object]conjunction for even lower runtimes/costs.
`What is online aggregation in the context of RapidFire AI evals, and what three confidence interval strategies does it support?`	`RapidFire AI transforms the status quo by adapting the powerful idea of [object Object]`
from database systems research to LLM evals.
Our adaptive execution engine, :doc:`as described on this page</difference>`, automatically
shards the data and processes multiple configs in parallel, one shard at a time, with
efficient swapping techniques.

This means you get running metric estimates with confidence intervals in real time. So, you can confidently stop poor configs earlier, clone better configs on the fly, and perform more informed exploration to reach much better eval metrics in much less time.

Example: Traditional Batch Evals vs. RapidFire AI

For instance, suppose you have an evals set with 400 queries. You decide to compare, say, 4 RAG configs in one go with RapidFire AI with number of shards set to 8. The illustration below contrasts traditional batch evals vs. RapidFire AI's approach for a simple eval metric.

.. list-table:: :widths: 50 50 :class... | | `What arguments does the RFModelConfig class accept for defining a model configuration in RapidFire AI?` | `RFModelConfig`


[object Object]
[object Object]
[object Object]
[object Object]

:param model_name: Model identifier for use with Hugging Face's :code:[object Object]. Can be a Hugging Face model hub name (e.g., ``"Qwen/Qwen2.5-7B-Instruct...

Loss: MultipleNegativesRankingLoss with these parameters:

json
1{ 2 "scale": 20.0, 3 "similarity_fct": "cos_sim", 4 "gather_across_devices": false, 5 "directions": [ 6 "query_to_doc" 7 ], 8 "partition_mode": "joint", 9 "hardness_mode": null, 10 "hardness_strength": 0.0 11}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 10
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

do_predict: False
prediction_loss_only: True
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
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: 10
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_ratio: None
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
enable_jit_checkpoint: False
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
use_cpu: False
seed: 42
data_seed: None
bf16: False
fp16: False
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: -1
ddp_backend: None
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
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
group_by_length: False
length_column_name: length
project: huggingface
trackio_space_id: trackio
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
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_for_metrics: []
eval_do_concat_batches: True
auto_find_batch_size: False
full_determinism: False
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
include_num_input_tokens_seen: no
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: True
use_cache: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin
router_mapping: {}
learning_rate_mapping: {}

Training Time

Training: 6.1 seconds

Framework Versions

Python: 3.12.13
Sentence Transformers: 5.4.1
Transformers: 5.0.0
PyTorch: 2.10.0+cu128
Accelerate: 1.13.0
Datasets: 4.0.0
Tokenizers: 0.22.2

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",
}

MultipleNegativesRankingLoss