Add new SentenceTransformer model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "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
+}

README.md

@@ -0,0 +1,1032 @@
+---
+base_model: BAAI/bge-base-en-v1.5
+language:
+- en
+library_name: sentence-transformers
+license: apache-2.0
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:3078
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: '[ q_{\text{ut}} = \frac{1}{2} \rho g B N_{\gamma} + c N_{c} +
+    (p_{q} + \rho g D_{f}) N_{q} \quad \text{[SI]} \quad (36.1a) ] [ q_{\text{ut}}
+    = \frac{1}{2} \gamma B N_{\gamma} + c N_{c} + (p_{q} + \gamma D_{f}) N_{q} \quad
+    \text{[U.S.]} \quad (36.1b) ]
+
+
+    Various researchers have made improvements on the theory supporting this equation,
+    leading to somewhat different terms and sophistication in evaluating (N_0), (N_c),
+    and (N_g). The approaches differ in the assumptions made of the shape of the failure
+    zone beneath the footing. However, the general form of the equation is the same
+    in most cases.
+
+
+    Figure 36.2 and Table 36.2 can be used to evaluate the capacity factors (N_0),
+    (N_c), and (N_g) in Equation 36.1. Alternatively, Table 36.3 can be used. The
+    bearing capacity factors in Table 36.2 are based on Terzaghi''s 1943 studies.
+    The values in Table 36.3 are based on Meyerhof''s 1955 studies and others, and
+    have been widely used. Other values are also in use.
+
+
+    Equation 36.1 is appropriate for a foundation in a continuous wall footing. Corrections,
+    called shape factors, for various footing geometries are presented in Table 36.4
+    and Table 36.5 using the parameters identified in Figure 36.3. The bearing capacity
+    factors (N_c) and (N_0) are multiplied by the appropriate shape factors when they
+    are used in Equation 36.1.
+
+
+    Several researchers have recommended corrections to (N_0) to account for footing
+    depth. (Corrections to (N_0) for footing depth have also been suggested. No corrections
+    to (N_c) for footing depth have been suggested.) There is considerable variation
+    in the method of calculating this correction if it is used at all. A multiplicative
+    correction factor, (d_c), which is used most often, has the form:
+
+
+    [ d_{c} = 1 + \frac{K D_{f}}{B} ]
+
+
+    (K) is a constant for which values of 0.2 and 0.4 have been proposed. The depth
+    factor correction is applied to (N_0) along with the shape factor correction in
+    Equation 36.1. Once the ultimate bearing capacity is determined, it is corrected
+    by the overburden, giving the net bearing capacity. This is the net pressure the
+    soil can support beyond the pressure applied by the existing overburden.
+
+
+    [ q_{\text{net}} = q_{\text{ult}} - \rho g D_{f} \quad \text{[SI]} \quad (36.3a)
+    ] [ q_{\text{net}} = q_{\text{ut}} - \gamma D_{f} \quad \text{[U.S.]} \quad (36.3b)
+    ]
+
+
+    [ \begin{array}{r l}{{\mathrm{[U.S.]}}}&{{}36.3(b)}\end{array} ]
+
+
+    [ q_{\text{net}} = q_{\text{ult}} - \gamma D_{f} ]
+
+
+    Figure 36.2: Terzaghi Bearing Capacity Factors'
+  sentences:
+  - What does the net bearing capacity represent in foundation engineering?
+  - Can anyone explain the difference between ductility and percent elongation?
+  - How do you compute the inverse of a 3x3 matrix?
+- source_sentence: 'Backwashing with filtered water pumped back through the filter
+    from the bottom to the top expands the sand layer by 30-50%, which dislodges trapped
+    material. Backwashing for 3-5 minutes at a rate of 8-15 gpm/ft² (5.4-10 L/s-m²)
+    is a typical specification. The head loss is reduced to approximately 1 ft (0.3
+    m) after washing. Experience has shown that supplementary agitation of the filter
+    media is necessary to prevent "caking" and "mudballs" in almost all installations.
+    Prior to backwashing, the filter material may be expanded by an air prewash volume
+    of 1-8 (2-5 typical) times the sand filter volume per minute for 2-10 minutes
+    (3-5 minutes typical). Alternatively, turbulence in the filter material may be
+    encouraged during backwashing with an air wash or with rotating hydraulic surface
+    jets.
+
+
+    During backwashing, the water in the filter housing will rise at a rate of 1-3
+    ft/min (0.5-1.5 cm/s). This rise should not exceed the settling velocity of the
+    smallest particle that is to be retained in the filter. The wash water, which
+    is collected in troughs for disposal, constitutes approximately 1-5% of the total
+    processed water. The total water used is approximately 75-100 gal/ft² (3-4 kL/m²).
+    The actual amount of backwash water is given by the equation:
+
+
+    $$ V = A_{\text{filter}} \cdot (\text{rate of rise}) \cdot t_{\text{backwash}}
+    $$
+
+
+    The temperature of the water used in backwashing is important since viscosity
+    changes with temperature (the effect of temperature on water density is negligible).
+    Water at 40°F (4°C) is more viscous than water at 70°F (21°C). Therefore, media
+    particles may be expanded to the same extent using lower upflow rates at lower
+    backwash temperatures. ```markdown
+
+
+    26. Other Filtration Methods
+
+
+    Pressure (sand) filters for water supply treatment operate similarly to rapid
+    sand filters except that incoming water is typically pressurized to 25-75 psig
+    (170-520 kPa gage). Single media filter rates are typically 4-5 gpm/ft² (1.4-14
+    L/s-m²), with 2-10 gpm/ft² (2.7-3.4 L/s-m² typical), while dual media filters
+    run at 1.5 to 2.0 times these rates. Pressure filters are not used in large installations.
+
+
+    Ultrafilters are membranes that act as sieves to retain turbidity, microorganisms,
+    and large organic molecules that are THM precursors, while allowing water, salts,
+    and small molecules to pass through. Ultrafiltration is effective in removing
+    particles ranging in size of 0.001 to 10 µm. A pressure of 15-75 psig (100-500
+    kPa) is required to drive the water through the membrane.
+
+
+    Biofilm filtration (biofilm process) uses microorganisms to remove selected contaminants
+    (e.g., aromatics and other hydrocarbons). The operation of biofilters is similar
+    to trickling filters used in wastewater processing. Sand filter facilities are
+    relatively easy to modify—sand is replaced with gravel in the 4-14 mm size range,
+    application rates are decreased, and exposure to chlorine from incoming and backwash
+    water is eliminated. While the maximum may never be used, a maximum backwash rate
+    of 20 gpm/ft² (14 L/s-m²) should be provided for. A µm is the same as a micron.'
+  sentences:
+  - How do I calculate the total water used for backwashing?
+  - How do I calculate flow rate if the water depth is 5 ft and channel width is 8
+    ft?
+  - What is the formula for estimating the percent time spent following on highways?
+- source_sentence: 'Here is the LaTeX representation of the angles and the radius
+    of the circle:
+
+
+    \begin{align} \alpha &= \angle PQR \ \beta &= \angle QNR \ \gamma &= \angle RPN
+    \ \end{align}
+
+
+    \begin{align} a &= \text{radius of the circle} \ I &= \text{line segment} \ \end{align}
+
+
+    The figure also includes a dashed line representing a chord and a tangent line
+    from point P to the circle, with a point of tangency labeled ''T''. The tangent
+    line is perpendicular to the radius of the circle at point T.
+
+
+    Figure 79.5 Tangent and Chord Offset Geometry
+
+
+    The short chord distance is
+
+
+    [ \mathrm{NQ} = C = 2R \sin \alpha ] [ \mathrm{NP} = (2R \sin \alpha) \cos \alpha
+    = C \cos \alpha ] [ \mathrm{PQ} = (2R \sin \alpha) \sin \alpha = 2R \sin^2 \alpha
+    ]
+
+
+    \tag{79.23} \tag{79.24} \tag{79.25} ```
+
+
+    7. Curve Layout By Chord Offset
+
+
+    The chord offset method is a third method for laying out horizontal curves. This
+    method is also suitable for short curves. The method is named for the way in which
+    the measurements are made, which is by measuring distances along the main chord
+    from the instrument location at PC.
+
+
+    [ \mathrm{NR} = \mathrm{chord~distance} = \mathrm{NQ}\cos\left({\frac{I}{2}} -
+    \alpha\right) ]
+
+
+    [ \sqrt{2} = (2R\sin\alpha)\cos\left(\frac{I}{2} - \alpha\right) = C\cos\left(\frac{I}{2}
+    - \alpha\right) = (I - \alpha)^{2} ]
+
+
+    [ \mathrm{RQ} = \mathrm{chord~offset} = \mathrm{NQ}~\sin\left({\frac{I}{2}} -
+    \alpha\right) ]
+
+
+    [ = (2R\sin\alpha)\sin\left({\frac{I}{2}} - \alpha\right) = C\sin\left({\frac{I}{2}}
+    - \alpha\right) ]
+
+
+    [ 79.27 ]
+
+
+    8. Horizontal Curves Through Points
+
+
+    Occasionally, it is necessary to design a horizontal curve to pass through a specific
+    point. The following procedure can be used. (Refer to Fig. 79.6.)
+
+
+    Step 1: Calculate ( \alpha ) and ( m ) from ( x ) and ( y ). (If ( x ) and ( m
+    ) are known, skip this step.) [ \alpha = \arctan\left(\frac{y}{x}\right) ] [ m
+    = \sqrt{x^{2} + y^{2}} ]
+
+
+    Step 2: Calculate ( y ). Since ( 90^\circ + \frac{I}{2} + \alpha = 180^\circ ),
+    [ \gamma = 90^\circ - \frac{I}{2} - \alpha ]
+
+
+    Step 3: Calculate ( \phi ). [ \phi = 180^\circ - \arcsin\left(\frac{\sin\gamma}{\cos\left(\frac{I}{2}\right)}\right)
+    ] [ = 180^\circ - \gamma - \phi ]
+
+
+    Step 4: Calculate ( O ). (Refer to Eq. 79.32)'
+  sentences:
+  - What's the difference between horizontal and vertical parabolas in their equations?
+  - What does the distance of 50 ft represent in the wave illustration?
+  - What is the relationship between tangent lines and radius in circular geometry?
+- source_sentence: 'Description: The image provided is not clear enough to discern
+    any specific details, text, or formulas. It appears to be a blurred image with
+    no distinguishable content. Therefore, I cannot extract any formulas or provide
+    a description of the image content.
+
+
+    Unfortunately, it is extremely difficult to prove compensatory fraud (i.e., fraud
+    for which damages are available). Proving fraud requires showing beyond a reasonable
+    doubt (a) a reckless or intentional misstatement of a material fact, (b) an intention
+    to deceive, (c) it resulted in misleading the innocent party to contract, and
+    (d) it was to the innocent party''s detriment. For example, if an engineer claims
+    to have experience in designing steel buildings but actually has none, the court
+    might consider the misrepresentation a fraudulent action. If, however, the engineer
+    has some experience, but an insufficient amount to do an adequate job, the engineer
+    probably will not be considered to have acted fraudulently.
+
+
+    Torts
+
+
+    A tort is a civil wrong committed by one person causing lamage to another person
+    or person''s property, emoional well-being, or reputation.11 It is a breach of
+    the ights of an individual to be secure in person or propxty. In order to correct
+    the wrong, a civil lawsuit (tort iction or civil complaint) is brought by the
+    alleged njured party (the plaintiff) against the defendant. To be a valid tort
+    action (i.e., lawsuit), there must have been injury (i.e., damage). Generally,
+    there will be no contract between the two parties, so the tort action annot claim
+    a breach of contract. 12 Cort law is concerned with compensation for the injury,
+    not punishment. Therefore, tort awards usually consist
+
+
+    f general, compensatory, and special damages and arely include punitive and exemplary
+    damages. (See Damages" for definitions of these damages.)
+
+
+    Strict Liability In Tort
+
+
+    itrict liability in tort means that the injured party wins f the injury can be
+    proven. It is not necessary to prove egligence, breach of explicit or implicit
+    warranty, or he existence of a contract (privity of contract). Strict ability
+    in tort is most commonly encountered in prodct liability cases. A defect in a
+    product, regardless of ow the defect got there, is sufficient to create strict
+    ability in tort.
+
+
+    lase law surrounding defective products has developed nd refined the following
+    requirements for winning a trict liability in tort case. The following points
+    must e proved.
+
+
+    The difference between a civil tort (lausuit) and a criminal lausuit is ie alleged
+    injured party. A crime is a wrong against society. A iminal lawsuit is brought
+    by the state against a defendant.
+
+
+    It is possible for an injury to be both a breach of contract and a tort.
+
+
+    ippose an owner has an agreement with a contractor to construct a ilding, and
+    the contract requires the contractor to comply with all ate and federal safety
+    regulations. If the owner is subsequently jured on a stairway because there was
+    no guardrail, the injury could · recoverable both as a tort and as a breach of
+    contract. If a third irty unrelated to the contract was injured, however, that
+    party could cover only through a tort action. · The product was defective in manufacture,
+    design, labeling, and so on.
+
+
+    The product was defective when used.
+
+
+    The defect rendered the product unreasonably dangerous.
+
+
+    The defect caused the injury. .
+
+
+    The specific use of the product that caused the damage was reasonably foreseeable.
+
+
+    Manufacturing And Design Liability'
+  sentences:
+  - What factors influence the instantaneous center of rotation in welded structures?
+  - How do you establish if fraud has occurred in a contract?
+  - How do you calculate the probability of multiple events happening?
+- source_sentence: '9. Area
+
+
+    Equation 9.35 calculates the area, ( A ), bounded by ( x = a ), ( x = b ), ( f_1(x)
+    ) above, and ( f_2(x) ) below. (Note: ( f_2(x) = 0 ) if the area is bounded by
+    the x-axis.) This is illustrated in Fig. 9.1. [ A = \int_{a}^{b} \left( f_{1}(x)
+    - f_{2}(x) \right) \, dx \qquad \qquad (9.35) ] Figure 9.1 Area Between Two Curves
+
+
+    Description: The image shows a graph with two curves labeled f1(x) and f2(x).
+    The graph is plotted on a Cartesian coordinate system with an x-axis and a y-axis.
+    There are two vertical dashed lines intersecting the x-axis at points labeled
+    ''a'' and ''b''. The curve f1(x) is above the line y = 0 and the curve f2(x) is
+    below the line y = 0. The area between the two curves from x = a to x = b is shaded,
+    indicating a region of interest or calculation.
+
+
+    The LaTeX representation of the curves is not provided in the image, so I cannot
+    write them in LaTeX form. However, if the curves were described by functions,
+    they could be represented as follows:
+
+
+    f1(x) could be represented as ( f_1(x) = ax^2 + bx + c ) for some constants a,
+    b, and c.
+
+
+    f2(x) could be represented as ( f_2(x) = -ax^2 - bx - c ) for some constants a,
+    b, and c.
+
+
+    The area between the curves from x = a to x = b could be calculated using the
+    integral of the difference between the two functions over the interval [a, b].
+
+
+    Description: The image provided is not clear enough to describe in detail or to
+    extract any formulas. The text is not legible, and no other discernible features
+    can be identified.
+
+
+    Find the area between the x-axis and the parabola ( y = x^2 ) in the interval
+    ([0, 4]).
+
+
+    Description: The image shows a graph with a curve that represents a function y
+    = x^2. There is a vertical dashed line at x = 4, indicating a point of interest
+    or a specific value on the x-axis. The graph is plotted on a Cartesian coordinate
+    system with the x-axis labeled ''x'' and the y-axis labeled ''y''. The curve is
+    a parabola that opens upwards, showing that as x increases, y increases at an
+    increasing rate. The point where x = 4 is marked on the x-axis, and the corresponding
+    y-value on the curve is not explicitly shown but can be inferred from the equation
+    y = x^2.
+
+
+    Solution: Referring to Eq. 9.35, [ f_{1}(x) = x^{2} \quad \text{and} \quad f_{2}(x)
+    = 0 ] Thus, [ A = \int_{a}^{b} \left( f_1(x) - f_2(x) \right) dx = \int_{0}^{4}
+    x^2 \, dx = \left[ \frac{x^3}{3} \right]_{0}^{4} = \frac{64}{3} ] ...
+
+
+    10. Arc Length'
+  sentences:
+  - Can you show me how to find the area using the integral of the difference of two
+    functions?
+  - Can you explain how to calculate the force BC using trigonometric components?
+  - What is the minimum requirement for steel area in slab reinforcement according
+    to ACI guidelines?
+model-index:
+- name: deep learning project
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.2543859649122807
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.5789473684210527
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.7017543859649122
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.7982456140350878
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.2543859649122807
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.19298245614035087
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.14035087719298245
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.07982456140350876
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.2543859649122807
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.5789473684210527
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.7017543859649122
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.7982456140350878
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.5289463979794752
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.4422630650700826
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.45071327302764325
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.2631578947368421
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.5760233918128655
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.695906432748538
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.783625730994152
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.2631578947368421
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.19200779727095513
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.13918128654970757
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0783625730994152
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.2631578947368421
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.5760233918128655
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.695906432748538
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.783625730994152
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.525405284677311
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.4422096908939014
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.45077185641932777
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.260233918128655
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.5526315789473685
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.6754385964912281
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.7573099415204678
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.260233918128655
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.18421052631578946
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1350877192982456
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.07573099415204677
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.260233918128655
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.5526315789473685
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.6754385964912281
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.7573099415204678
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.5082788808907895
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.4281189083820665
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.4372871346521922
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.2134502923976608
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.5116959064327485
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.6403508771929824
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.7368421052631579
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.2134502923976608
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.1705653021442495
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.12807017543859647
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.07368421052631578
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.2134502923976608
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.5116959064327485
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.6403508771929824
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.7368421052631579
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.4726924534205871
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.3880070546737214
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.39701781193586744
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.1871345029239766
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.47076023391812866
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.5789473684210527
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.6695906432748538
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.1871345029239766
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.15692007797270952
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.11578947368421051
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.06695906432748537
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.1871345029239766
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.47076023391812866
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.5789473684210527
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.6695906432748538
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.42447214920635656
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.3461802654785111
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.3562882551304709
+      name: Cosine Map@100
+---
+
+# deep learning project
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) on the json 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:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - json
+- **Language:** en
+- **License:** apache-2.0
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 768, '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()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+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("bbmb/deep-learning-for-embedding-model-ssilwal-qpham6")
+# Run inference
+sentences = [
+    "9. Area\n\nEquation 9.35 calculates the area, ( A ), bounded by ( x = a ), ( x = b ), ( f_1(x) ) above, and ( f_2(x) ) below. (Note: ( f_2(x) = 0 ) if the area is bounded by the x-axis.) This is illustrated in Fig. 9.1. [ A = \\int_{a}^{b} \\left( f_{1}(x) - f_{2}(x) \\right) \\, dx \\qquad \\qquad (9.35) ] Figure 9.1 Area Between Two Curves\n\nDescription: The image shows a graph with two curves labeled f1(x) and f2(x). The graph is plotted on a Cartesian coordinate system with an x-axis and a y-axis. There are two vertical dashed lines intersecting the x-axis at points labeled 'a' and 'b'. The curve f1(x) is above the line y = 0 and the curve f2(x) is below the line y = 0. The area between the two curves from x = a to x = b is shaded, indicating a region of interest or calculation.\n\nThe LaTeX representation of the curves is not provided in the image, so I cannot write them in LaTeX form. However, if the curves were described by functions, they could be represented as follows:\n\nf1(x) could be represented as ( f_1(x) = ax^2 + bx + c ) for some constants a, b, and c.\n\nf2(x) could be represented as ( f_2(x) = -ax^2 - bx - c ) for some constants a, b, and c.\n\nThe area between the curves from x = a to x = b could be calculated using the integral of the difference between the two functions over the interval [a, b].\n\nDescription: The image provided is not clear enough to describe in detail or to extract any formulas. The text is not legible, and no other discernible features can be identified.\n\nFind the area between the x-axis and the parabola ( y = x^2 ) in the interval ([0, 4]).\n\nDescription: The image shows a graph with a curve that represents a function y = x^2. There is a vertical dashed line at x = 4, indicating a point of interest or a specific value on the x-axis. The graph is plotted on a Cartesian coordinate system with the x-axis labeled 'x' and the y-axis labeled 'y'. The curve is a parabola that opens upwards, showing that as x increases, y increases at an increasing rate. The point where x = 4 is marked on the x-axis, and the corresponding y-value on the curve is not explicitly shown but can be inferred from the equation y = x^2.\n\nSolution: Referring to Eq. 9.35, [ f_{1}(x) = x^{2} \\quad \\text{and} \\quad f_{2}(x) = 0 ] Thus, [ A = \\int_{a}^{b} \\left( f_1(x) - f_2(x) \\right) dx = \\int_{0}^{4} x^2 \\, dx = \\left[ \\frac{x^3}{3} \\right]_{0}^{4} = \\frac{64}{3} ] ...\n\n10. Arc Length",
+    'Can you show me how to find the area using the integral of the difference of two functions?',
+    'What is the minimum requirement for steel area in slab reinforcement according to ACI guidelines?',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# 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.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+
+* Datasets: `dim_768`, `dim_512`, `dim_256`, `dim_128` and `dim_64`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | dim_768    | dim_512    | dim_256    | dim_128    | dim_64     |
+|:--------------------|:-----------|:-----------|:-----------|:-----------|:-----------|
+| cosine_accuracy@1   | 0.2544     | 0.2632     | 0.2602     | 0.2135     | 0.1871     |
+| cosine_accuracy@3   | 0.5789     | 0.576      | 0.5526     | 0.5117     | 0.4708     |
+| cosine_accuracy@5   | 0.7018     | 0.6959     | 0.6754     | 0.6404     | 0.5789     |
+| cosine_accuracy@10  | 0.7982     | 0.7836     | 0.7573     | 0.7368     | 0.6696     |
+| cosine_precision@1  | 0.2544     | 0.2632     | 0.2602     | 0.2135     | 0.1871     |
+| cosine_precision@3  | 0.193      | 0.192      | 0.1842     | 0.1706     | 0.1569     |
+| cosine_precision@5  | 0.1404     | 0.1392     | 0.1351     | 0.1281     | 0.1158     |
+| cosine_precision@10 | 0.0798     | 0.0784     | 0.0757     | 0.0737     | 0.067      |
+| cosine_recall@1     | 0.2544     | 0.2632     | 0.2602     | 0.2135     | 0.1871     |
+| cosine_recall@3     | 0.5789     | 0.576      | 0.5526     | 0.5117     | 0.4708     |
+| cosine_recall@5     | 0.7018     | 0.6959     | 0.6754     | 0.6404     | 0.5789     |
+| cosine_recall@10    | 0.7982     | 0.7836     | 0.7573     | 0.7368     | 0.6696     |
+| **cosine_ndcg@10**  | **0.5289** | **0.5254** | **0.5083** | **0.4727** | **0.4245** |
+| cosine_mrr@10       | 0.4423     | 0.4422     | 0.4281     | 0.388      | 0.3462     |
+| cosine_map@100      | 0.4507     | 0.4508     | 0.4373     | 0.397      | 0.3563     |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### json
+
+* Dataset: json
+* Size: 3,078 training samples
+* Columns: <code>positive</code> and <code>anchor</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | positive                                                                             | anchor                                                                            |
+  |:--------|:-------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                               | string                                                                            |
+  | details | <ul><li>min: 117 tokens</li><li>mean: 508.1 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 15.93 tokens</li><li>max: 28 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         | anchor                                                                                        |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------|
+  | <code>The PHF is used to convert hourly volumes to flow rates and represents the hourly variation in traffic flow. If the demand volume is measured in 15 min increments, it is unnecessary to use the PHF to convert to flow rates.<br><br>Therefore, since two-lane highway analysis is based on demand flow rates for a peak 15 min period within the analysis hour (usually the peak hour), the PHF in Equation 73.22 and Equation 73.23 is given a value of 1.00.<br><br>The average travel speed in the analysis direction, ( ATS_d ), is estimated from the FFS, the demand flow rate, the opposing flow rate, and the adjustment factor for the percentage of no-passing zones in the analysis direction, ( f_{np} ), as given in HCM Exh. 15-15. Equation 73.24 only applies to Class I and Class III two-lane highways.<br><br>[ \mathrm{ATS}{d} = \mathrm{FFS} - 0.0076(v{d,s} + v_{o,s}) - f_{\mathrm{np},s} \quad (73.24) ]<br><br>If the PTSF methodology is used, the formula for the demand flow rate, ( v_{i, \text{ATS}} ), is the same, although di...</code> | <code>What is the formula for estimating the percent time spent following on highways?</code> |
+  | <code>However, if the initial point on the limb is close to the critical point (i.e., the nose of the curve), then a small change in the specific energy (such as might be caused by a small variation in the channel floor) will cause a large change in depth. That is why severe turbulence commonly occurs near points of critical flow. Given that ( 4 \, \text{ft/sec} ) (or ( 1.2 \, \text{m/s} )) of water flows in a ( 7 \, \text{ft} ) (or ( 2.1 \, \text{m} )) wide, ( 6 \, \text{ft} ) (or ( 1.8 \, \text{m} )) deep open channel, the flow encounters a ( 1.0 \, \text{ft} ) (or ( 0.3 \, \text{m} )) step in the channel bottom. What is the depth of flow above the step? Actually, specific energy curves are typically plotted for flow per unit width, ( q = \frac{Q}{w} ). If that is the case, a jump from one limb to the other could take place if the width were allowed to change as well as the depth. A rise in the channel bottom does not always produce a drop in the water surface. Only if the flow is initiall...</code>                         | <code>What happens to the water depth when it encounters a step in a channel?</code>          |
+  | <code>The shear strength, ( S ) or ( S_{ys} ), of a material is the maximum shear stress that the material can support without yielding in shear. (The ultimate shear strength, ( S_{us} ), is rarely encountered.) For ductile materials, maximum shear stress theory predicts the shear strength as one-half of the tensile yield strength. A more accurate relationship is derived from the distortion energy theory (also known as von Mises theory).<br><br>Figure 43.16: Uniform Bar in Torsion<br><br>Description: The image shows a diagram of a mechanical system with a cylindrical object, a rod, and a spring. There are two forces acting on the system: one is the weight of the rod, labeled 'L', acting downwards, and the other is the spring force, labeled 'T', acting upwards. The rod is shown to be in equilibrium, with the spring force balancing the weight of the rod. The distance from the pivot point to the center of mass of the rod is labeled 'r'. There is also a variable 'y' indicating the vertical displacement of t...</code>             | <code>Can you explain what maximum shear stress theory is?</code>                             |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 4
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `tf32`: True
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 16
+- `eval_accumulation_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`: 4
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `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`: True
+- `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`: True
+- `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}
+- `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`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `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
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch      | Step   | Training Loss | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 |
+|:----------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
+| 0.9897     | 6      | -             | 0.5417                 | 0.5428                 | 0.5145                 | 0.4630                 | 0.3945                |
+| 1.6495     | 10     | 3.7867        | -                      | -                      | -                      | -                      | -                     |
+| 1.9794     | 12     | -             | 0.5269                 | 0.5206                 | 0.4992                 | 0.4751                 | 0.4082                |
+| **2.9691** | **18** | **-**         | **0.5298**             | **0.5238**             | **0.5107**             | **0.4761**             | **0.4268**            |
+| 3.2990     | 20     | 1.9199        | -                      | -                      | -                      | -                      | -                     |
+| 3.9588     | 24     | -             | 0.5289                 | 0.5254                 | 0.5083                 | 0.4727                 | 0.4245                |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.3.1
+- Transformers: 4.41.2
+- PyTorch: 2.1.2+cu121
+- Accelerate: 0.34.2
+- Datasets: 2.19.1
+- Tokenizers: 0.19.1
+
+## 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",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@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}
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@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.*
+-->

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "BAAI/bge-base-en-v1.5",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.1.2+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7de8f53df682a86cc9d75b689b3ab609fe702597f2738029baee6dea93791ca
+size 437951328

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": true
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}