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/golden_rag_tuned_minilm_mnr_100")
# Run inference
sentences = [
    'How do you define and wire together the accumulate_metrics_fn for algebraic metrics in a RAG evals pipeline, and what happens if you omit it?',
    '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.\n\n.. code-block:: python\n\n    # Based on GSM8K tutorial use case\n    metrics = {\n        "Total": {"value": total},\n        "Correct": {\n            "value": correct,\n            "is_distributive": True,\n            "value_range": (0, 1),\n        },\n        "Accuracy": {\n            "value": accuracy,\n            "is_algebraic": True,\n            "value_range": (0, 1),\n        },\n    }',
    'Postprocess Function\n--------------------\n\nOptional user-provided function to postprocess a batch of examples and their respective generated outputs, \nwhich is injected into this function by the system. \nThis is useful for, say, extracting structured information from generations, adding ground truth data, \nor performing any transformations needed before computing metrics.\n\nIt is invoked for each batch during the evaluation process after generation and before metric computation.\nPass it directly to the :code:`postprocess_fn` key in your eval config dictionary.\n',
]
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, 0.6599, 0.2692],
#         [0.6599, 1.0000, 0.2501],
#         [0.2692, 0.2501, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

Size: 111 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 111 samples:
sentence_0 sentence_1
type string string
details
min: 15 tokens
mean: 41.97 tokens
max: 70 tokens
min: 36 tokens
mean: 227.35 tokens
max: 256 tokens

Samples:

sentence_0	sentence_1
`How does the num_shards parameter in run_evals() relate to the online aggregation confidence interval computation, and what is the end-to-end flow from setting num_shards to seeing narrowing confidence intervals on eval metrics?`
.. py:function:: run_evals(self, config_group: Any, dataset: Dataset, num_shards: int=4, num_actors: int, seed: int=42) -> dict[int, tuple[dict, dict]]:

:param config_group: Single evals config knob dictionary, a generated config group, or a :code:list of configs or config groups :type config_group: Evals config-group or list as described in :doc:the Multi-Config Specification page</configs>

:param dataset: Evaluation dataset to measure eval metrics :type dataset: Dataset

:param num_shards: Number of logical splits of data to control degree of concurrency for multi-config execution (recommended: at least 4) :type num_shards: int

:param num_actors: Number of parallel worker processes per machine to control degree of concurrency; (default: number of GPUs); (recommended max 16, if machine has no GPUs) :type num_actors: int, optional

:param seed: Seed to control randomness for online aggregation (default: 42) :type seed: int, optional

:return: Dictionary with a key be... | |

What is the default value of the text_key metadata field name used to store raw text content in Pinecone vector store configurations?

          - :code:[object Object]: The metadata field name used to store the original raw text content associated with a vector in Pinecone. Optional; default is :code:[object Object]. Applicable to all modes. This is useful when the Pinecone index was populated by an external tool that stored text under a non-default metadata field name (e.g., :code:[object Object], :code:[object Object]).
- :code:[object Object]: Vector type for the index. Accepts a :code:[object Object] value or string. Optional for Create mode; default is :code:[object Object]. N/A for Read/Update mode.
- :code:[object Object]: Arbitrary string key-value tags to attach to the index. Optional for Create mode; default is :code:[object Object]. N/A for Read/Update mode.
- :code:[object Object]: Timeout in seconds for index operations. Optional for Create mode; default is :code:[object Object]. N/A for Read/Update mode.
- :code:[object Object]: Whether deletion protection is enabled. Accepts a :code:[object Object] ...

| |

How do FAISS, Pinecone, and PGVector compare as vector store options in RapidFire AI in terms of supported modes, persistence, configuration requirements, and GPU support?

    :param vector_store_cfg: The vector store type and args to store and possibly index embedding vectors for retrieval, provided as a single dictionary.


[object Object]


[object Object]


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















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

	sentence_0	sentence_1
type	string	string
details	min: 15 tokens mean: 41.97 tokens max: 70 tokens	min: 36 tokens mean: 227.35 tokens max: 256 tokens