embedding_gemma_ft_v1 / README.md

deebak14

Add new SentenceTransformer model

178a831 verified 2 months ago

preview code

raw

history blame

37.3 kB

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:15565
  - loss:MultipleNegativesRankingLoss
base_model: google/embeddinggemma-300m
widget:
  - source_sentence: >-
      I need to lock an object in my model so I can work on other parts without
      accidentally selecting it. How can I do that?
    sentences:
      - >-
        You cannot use the following methods IsObjectLocked, LockObjects,
        UnlockObject, SelectObject, SelectObjects, UnlockObjects,
        IsObjectSelectable, ShowObject, IsObjectNormal
      - object
      - "You can use the following methods to complete the task.\nmethod: LockObject\ndescription: Locks a single object. Locked objects are visible, and they can be\r\n    snapped to. But, they cannot be selected.\nsyntax: LockObject(object_id)\nparameters: object_id (guid): The identifier of an object\nreturns: bool: True or False indicating success or failure\n\nFollowing is the code that uses this method to complete the task as per user query.\n\n```python\nimport rhinoscriptsyntax as rs\n\n# Lock an object in the model to prevent accidental selection\nid = rs.GetObject(\"Select object to lock\")\nif id:\n    rs.LockObject(id)\n    print(\"Object locked successfully.\")\nelse:\n    print(\"No object selected.\")\n```"
  - source_sentence: >-
      I want to create a cloud of points in my Rhino model. Can you show me how
      to do that?
    sentences:
      - "You can use the following methods to complete the task.\nmethod: AddPointCloud\ndescription: Adds point cloud object to the document\nsyntax: AddPointCloud(points, colors=None)\nparameters: \npoints ([point, ....]): list of values where every multiple of three represents a point\r\ncolors ([color, ...]): list of colors to apply to each point\n\nreturns: \nguid: identifier of point cloud on success\n\n\nFollowing is the code that uses this method to complete the task as per user query.\n\n```python\nimport rhinoscriptsyntax as rs\n\n# Create a cloud of points in Rhino\npoints = [(0, 0, 0), (1, 1, 1), (2, 2, 2), (3, 3, 3)]  # Define points\nrs.AddPointCloud(points)  # Add the point cloud to the model\n```"
      - geometry
      - >-
        You cannot use the following methods PointCloudPoints, AddPoints,
        CreatePoint, PointCloudCount, AddPoint, AddLine, PointCloudHidePoints,
        CreateVector, PointCoordinates
  - source_sentence: >-
      I need to find out which vertices make up each face of my mesh. Can you
      help me with that?
    sentences:
      - >-
        You can use the following methods to complete the task.

        method: MeshFaces

        description: Returns face vertices of a mesh

        syntax: MeshFaces(object_id, face_type=True)

        parameters: object_id (guid): identifier of a mesh object

        face_type (bool, optional): The face type to be returned. True = both
        triangles and quads. False = only triangles

        returns: list([point, point, point, point], ...): 3D points that define
        the face vertices of the mesh. If face_type is True, then faces are
        returned as both quads and triangles (4 3D points). For triangles, the
        third and fourth vertex will be identical. If face_type is False, then
        faces are returned as only triangles(3 3D points). Quads will be
        converted to triangles.


        Following is the code that uses this method to complete the task as per
        user query.


        ```python

        import rhinoscriptsyntax as rs

        # Get the mesh object from the user

        obj = rs.GetObject("Select mesh", rs.filter.mesh)

        # Retrieve the vertex indices for each face of the mesh

        faces = rs.MeshFaces(obj, True)

        if faces:
            rs.EnableRedraw(False)
            i = 0
            while i < len(faces):
                # Each face can be a triangle or a quad
                face = faces[i:i+4] if len(faces) > i + 3 else faces[i:i+3]
                print("Face vertices:", face)
                i += 3 if len(face) == 3 else 4
            rs.EnableRedraw(True)
        ```
      - >-
        You cannot use the following methods MeshVertexFaces, MeshFaceVertices,
        MeshVertices, MeshVertexCount, MeshFaceCenters, MeshTriangleCount,
        MeshQuadCount, MeshFaceCount, MeshNakedEdgePoints
      - mesh
  - source_sentence: >-
      Can you show me how to check if two transformation matrices are the same
      in Rhino?
    sentences:
      - "You can use the following methods to complete the task.\nmethod: XformChangeBasis2\ndescription: Returns a change of basis transformation matrix of None on error\nsyntax: XformChangeBasis2(x0,y0,z0,x1,y1,z1)\nparameters: \nx0,y0,z0 (vector): initial basis\r\nx1,y1,z1 (vector): final basis\n\nreturns: \ntransform: The 4x4 transformation matrix if successful\r\nNone: if not successful\n\n\nFollowing is the code that uses this method to complete the task as per user query.\n\n```python\nimport rhinoscriptsyntax as rs\n\n# Function to check if two transformation matrices are the same\n# Parameters: mat1, mat2 - transformation matrices to compare\n# Returns: True if they are the same, False otherwise\ndef are_matrices_equal(mat1, mat2):\n    return rs.XformCompare(mat1, mat2) == 0\n\n# Example usage\nmatrix1 = rs.XformChangeBasis2(1, 0, 0, 0, 1, 0)\nmatrix2 = rs.XformChangeBasis2(1, 0, 0, 0, 1, 0)\nresult = are_matrices_equal(matrix1, matrix2)\nprint(\"Matrices are equal:\" , result)\n```"
      - >-
        You cannot use the following methods XformCompare, IsXformSimilarity,
        IsXformIdentity, IsXformZero, CompareGeometry, CreateXform,
        VectorTransform, XformTranslation, TransformObject, XformDeterminant
      - transformation
  - source_sentence: >-
      I need to find where a flat surface meets a sphere. How can I do that in
      Rhino?
    sentences:
      - plane
      - >-
        You cannot use the following methods LineSphereIntersection, IsSphere,
        AddSphere, LinePlaneIntersection, Angle, CircleCenterPoint,
        CurveCurveIntersection, CurveSurfaceIntersection, AddCircle3Pt
      - >-
        You can use the following methods to complete the task.

        method: PlaneSphereIntersection

        description: Calculates the intersection of a plane and a sphere.

        syntax: PlaneSphereIntersection(plane, sphere_plane, sphere_radius)

        parameters: plane (plane): The plane to intersect; sphere_plane (plane):
        Equatorial plane of the sphere (origin is center); sphere_radius
        (float): Radius of the sphere.

        returns: list: [type, point/plane, radius] where type=0 for point, 1 for
        circle. None on error.


        Following is the code that uses this method to complete the task as per
        user query.


        ```python

        import rhinoscriptsyntax as rs


        # Define a flat surface as a plane

        plane = rs.WorldXYPlane()

        # Define the radius of the sphere

        radius = 10

        # Calculate the intersection between the plane and the sphere

        results = rs.PlaneSphereIntersection(plane, plane, radius)


        # Check if there are results and handle them accordingly

        if results:
            if results[0] == 0:
                # If the intersection is a point, add it to the document
                rs.AddPoint(results[1])
            else:
                # If the intersection is a circle, add it to the document
                rs.AddCircle(results[1], results[2])
        ```
datasets:
  - deebak14/embedding_tuple_data_v1
  - deebak14/embedding_triplet_data_v1
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy
model-index:
  - name: SentenceTransformer based on google/embeddinggemma-300m
    results:
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: base eval
          type: base-eval
        metrics:
          - type: cosine_accuracy
            value: 1
            name: Cosine Accuracy

SentenceTransformer based on google/embeddinggemma-300m

This is a sentence-transformers model finetuned from google/embeddinggemma-300m on the embedding_tuple_data_v1 dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: google/embeddinggemma-300m
Maximum Sequence Length: 2048 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- embedding_tuple_data_v1

Model Sources

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

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 2048, 'do_lower_case': False, 'architecture': 'Gemma3TextModel'})
  (1): Pooling({'word_embedding_dimension': 768, '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): Dense({'in_features': 768, 'out_features': 3072, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
  (3): Dense({'in_features': 3072, 'out_features': 768, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
  (4): 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.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("deebak14/embedding_gemma_ft_v1")
# Run inference
queries = [
    "I need to find where a flat surface meets a sphere. How can I do that in Rhino?",
]
documents = [
    'You can use the following methods to complete the task.\nmethod: PlaneSphereIntersection\ndescription: Calculates the intersection of a plane and a sphere.\nsyntax: PlaneSphereIntersection(plane, sphere_plane, sphere_radius)\nparameters: plane (plane): The plane to intersect; sphere_plane (plane): Equatorial plane of the sphere (origin is center); sphere_radius (float): Radius of the sphere.\nreturns: list: [type, point/plane, radius] where type=0 for point, 1 for circle. None on error.\n\nFollowing is the code that uses this method to complete the task as per user query.\n\n```python\nimport rhinoscriptsyntax as rs\n\n# Define a flat surface as a plane\nplane = rs.WorldXYPlane()\n# Define the radius of the sphere\nradius = 10\n# Calculate the intersection between the plane and the sphere\nresults = rs.PlaneSphereIntersection(plane, plane, radius)\n\n# Check if there are results and handle them accordingly\nif results:\n    if results[0] == 0:\n        # If the intersection is a point, add it to the document\n        rs.AddPoint(results[1])\n    else:\n        # If the intersection is a circle, add it to the document\n        rs.AddCircle(results[1], results[2])\n```',
    'You cannot use the following methods LineSphereIntersection, IsSphere, AddSphere, LinePlaneIntersection, Angle, CircleCenterPoint, CurveCurveIntersection, CurveSurfaceIntersection, AddCircle3Pt',
    'plane',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 768] [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[ 0.6658,  0.4819, -0.1617]])

Evaluation

Metrics

Triplet

Dataset: base-eval
Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	1.0

Training Details

Training Dataset

embedding_tuple_data_v1

Dataset: embedding_tuple_data_v1 at b592a1a
Size: 15,565 training samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 9 tokens
mean: 15.98 tokens
max: 50 tokens

min: 42 tokens
mean: 177.53 tokens
max: 810 tokens

	anchor	positive
type	string	string
details	min: 9 tokens mean: 15.98 tokens max: 50 tokens	min: 42 tokens mean: 177.53 tokens max: 810 tokens

Samples:

anchor	positive
`Provide an example of using AddRectangle.`	`import rhinoscriptsyntax as rs plane = rs.WorldXYPlane() plane = rs.RotatePlane(plane, 45.0, [0,0,1]) rs.AddRectangle(plane, 5.0, 15.0) Metadata: Name: AddRectangle Category: curve Function Signature: rs.AddRectangle(plane: plane, width: number, height: number) -> guid Description: Add a rectangular curve to the document`
`How do I search for the total number of linetypes in my document?`	`You can use the following method: Name: LinetypeCount Category: linetype Function Signature: rs.LinetypeCount() -> int Description: Description: Returns the number of linetypes in the document. Parameters: None Returns: int: The number of linetypes in the document.`
`How do I maintain the shape of a curve while fitting it?`	You can use the following method: Name: FitCurve Category: curve Function Signature: rs.FitCurve(curve_id: guid, degree: int = 3, distance_tolerance: float = -1, angle_tolerance: float = -1) -> guid Description: Description: Reduces the number of control points of a curve while maintaining its general shape. This function is useful for replacing curves with many control points. For more information, see the Rhino help for the FitCrv command. Parameters: curve_id (guid): Identifier of the curve object to be fitted. eg: '3D4F5A6B-7C8D-9E0F-1A2B-3C4D5E6F7A8B' degree (int, optional): The degree of the curve, which must be greater than 1. The default is 3. eg: 3 distance_tolerance (float, optional): The fitting tolerance. If not specified or <= 0.0, the document absolute tolerance is used. eg: 0.01 angle_tolerance (float, optional): The kink smoothing tolerance in degrees. If 0.0, all kinks are smoothed. If > 0.0, kinks smaller than this value are smoothed. If ...

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "gather_across_devices": false
}

Evaluation Dataset

embedding_triplet_data_v1

Dataset: embedding_triplet_data_v1 at 71ea1de
Size: 476 evaluation samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 476 samples:

	anchor	positive	negative
type	string	string	string
details	min: 15 tokens mean: 23.13 tokens max: 38 tokens	min: 111 tokens mean: 252.44 tokens max: 1015 tokens	min: 32 tokens mean: 42.48 tokens max: 55 tokens

Samples:

anchor	positive	negative
`I need to flatten a curved surface for laser cutting. How can I do that?`	`You can use the following methods to complete the task. method: UnrollSurface description: Flattens a developable surface or polysurface syntax: UnrollSurface(surface_id, explode=False, following_geometry=None, absolute_tolerance=None, relative_tolerance=None) parameters: surface_id (guid): the surface's identifier`
explode (bool, optional): If True, the resulting surfaces ar not joined
following_geometry ({guid, ...]): List of curves, dots, and points which
should be unrolled with the surface returns: list(guid, ...): of unrolled surface ids
tuple((guid, ...),(guid, ...)): if following_geometry is not None, a tuple
[1] is the list of unrolled surface ids
[2] is the list of unrolled following geometry Following is the code that uses this method to complete the task as per user query. ```python import rhinoscriptsyntax as rs # Flatten a curved surface for laser cutting surface = rs.GetObject("Select curved surface to flatten", rs.filter.surface) if surface: # Unrol...	`You cannot use the following methods ConvertCurveToPolyline, MeshOutline, PullCurveToMesh, ExplodeText, MeshToNurb, IsCurvePlanar, Angle, AddFilletCurve, MeshVolume`
`Can you show me how to rotate a plane by 30 degrees around its normal axis?`	You can use the following methods to complete the task. method: PlaneTransform description: Transforms a plane. syntax: PlaneTransform(plane, xform) parameters: plane (plane): Plane to transform; xform (transform): Transformation to apply. returns: plane: Resulting plane if successful, otherwise None. Following is the code that uses this method to complete the task as per user query. python<br>import rhinoscriptsyntax as rs<br><br># Get the current construction plane<br>plane = rs.ViewCPlane()<br><br># Create a rotation transformation of 30 degrees around the normal axis (Z-axis)<br>xform = rs.XformRotation(30.0, plane.ZAxis, plane.Origin)<br><br># Apply the transformation to the plane<br>plane = rs.PlaneTransform(plane, xform)<br><br># Set the new construction plane<br>rs.ViewCPlane(None, plane)<br>	`You cannot use the following methods RotatePlane, XformRotation1, PlaneFromNormal, VectorRotate, Angle, PlaneFromFrame, LinePlane, MovePlane, CreatePlane`
`I want to change the height of a text dot I just created. How can I do that?`	`You can use the following methods to complete the task. method: TextDotHeight description: Returns or modified the font height of a text dot syntax: TextDotHeight(object_id, height=None) parameters: object_id (guid): identifier of a text dot object`
height (number, optional) new font height returns: number: If height is not specified, the current text dot height
number: If height is specified, the previous text dot height
None: on error Following is the code that uses this method to complete the task as per user query. `python<br>import rhinoscriptsyntax as rs<br># Change the height of a text dot<br>obj = rs.GetObject("Select text dot")<br>if rs.IsTextDot(obj):<br> previous_height = rs.TextDotHeight(obj, 15.0) # Set new height to 15.0<br> print(f"Previous height was: {previous_height}")<br>`	`You cannot use the following methods TextDotPoint, TextDotFont, TextDotText, TextObjectHeight, IsTextDot, AddTextDot, TextObjectFont, PointCoordinates, ExplodeText`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "gather_across_devices": false
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
learning_rate: 2e-05
warmup_ratio: 0.1
bf16: True
prompts: task: sentence similarity | query:
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 2e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 3
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.1
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: True
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
no_cuda: False
use_cpu: False
use_mps_device: False
seed: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: True
fp16: False
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: 0
ddp_backend: None
tpu_num_cores: None
tpu_metrics_debug: False
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
fsdp_transformer_layer_cls_to_wrap: None
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
adafactor: False
group_by_length: False
length_column_name: length
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
use_legacy_prediction_loop: False
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_inputs_for_metrics: False
include_for_metrics: []
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
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: False
prompts: task: sentence similarity | query:
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss	base-eval_cosine_accuracy
-1	-1	-	-	0.0147
0.1028	100	0.1601	-	-
0.2055	200	0.0474	0.2296	0.8971
0.3083	300	0.0749	-	-
0.4111	400	0.1037	0.1457	0.9265
0.5139	500	0.0564	-	-
0.6166	600	0.0706	0.3362	0.9475
0.7194	700	0.0549	-	-
0.8222	800	0.0427	0.2154	0.9538
0.9250	900	0.0599	-	-
1.0277	1000	0.0656	0.2439	0.9706
1.1305	1100	0.0409	-	-
1.2333	1200	0.0283	0.2422	0.9727
1.3361	1300	0.0336	-	-
1.4388	1400	0.0338	0.2397	0.9664
1.5416	1500	0.0384	-	-
1.6444	1600	0.0271	0.1048	0.9832
1.7472	1700	0.0305	-	-
1.8499	1800	0.024	0.1172	0.9916
1.9527	1900	0.014	-	-
2.0555	2000	0.018	0.0898	0.9958
2.1583	2100	0.0091	-	-
2.2610	2200	0.0154	0.0721	0.9916
2.3638	2300	0.0123	-	-
2.4666	2400	0.0119	0.0876	0.9937
2.5694	2500	0.0173	-	-
2.6721	2600	0.0091	0.0482	1.0
2.7749	2700	0.0211	-	-
2.8777	2800	0.0146	0.0550	1.0
2.9805	2900	0.0101	-	-
-1	-1	-	-	1.0

Framework Versions

Python: 3.12.11
Sentence Transformers: 5.1.0
Transformers: 4.56.1
PyTorch: 2.8.0+cu126
Accelerate: 1.10.1
Datasets: 4.0.0
Tokenizers: 0.22.0

Citation

BibTeX

Sentence Transformers

@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

@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}
}