Model save

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "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
+}

README.md

@@ -0,0 +1,633 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:57126
+- loss:MultipleNegativesRankingLoss
+base_model: sentence-transformers/all-MiniLM-L6-v2
+widget:
+- source_sentence: '##inemia a the the upper limit of normal concentra - b success
+    was defined or at least success menstrual cycles without of cycle. the most from
+    the trial were dizziness, reproduced, comparison bromocriptine the hyperpro n
+    j med ; 904. )'
+  sentences:
+  - the yearly inci - dence of symptomatic gallstones is about 1 %. cardiac effects
+    include sinus bradycardia ( 25 % ) and conduction disturbances ( 10 % ). pain
+    at the site of injection is common, especially with the long - acting octreotide
+    suspension. vitamin b 12 deficiency may occur with long - term use of octreotide.
+    a long - acting formulation of lanreotide, another octapeptide somatostatin analog,
+    was approved by the fda in 2007 for treat - ment of acromegaly. lanreotide appears
+    to have effects comparable to those of octreotide on reducing gh levels and normalizing
+    igf - i concentrations. pegvisomant pegvisomant is a gh receptor antagonist used
+    to treat acromegaly. it is the polyethylene glycol ( peg ) derivative of a mutant
+    gh, b2036. like native gh, pegvisomant has two gh receptor bind - ing sites. however,
+    one of the pegvisomant gh receptor binding sites has increased affinity for the
+    gh receptor, whereas its second gh receptor binding site has reduced affinity.
+    this differential receptor affinity allows the initial step ( gh receptor dime
+  - '##inemia and anovulation. a : the dotted line indicates the upper limit of normal
+    serum prolactin concentra - tions. b : complete success was defined as pregnancy
+    or at least two consecutive menses with evidence of ovulation at least once. partial
+    success was two menstrual cycles without evidence of ovulation or just one ovulatory
+    cycle. the most common reasons for withdrawal from the trial were nausea, headache,
+    dizziness, abdominal pain, and fatigue. ( modified and reproduced, with permission,
+    from webster j et al : a comparison of cabergoline and bromocriptine in the treatment
+    of hyperpro - lactinemic amenorrhea. n engl j med 1994 ; 331 : 904. )'
+  - compounds are shown in figure 38 – 5. the thiocarbamide group is essential for
+    antithyroid activity. pharmacokinetics methimazole is completely absorbed but
+    at variable rates. it is readily accumulated by the thyroid gland and has a volume
+    of distribution similar to that of propylthiouracil. excretion is slower than
+    with propylthiouracil ; 65 – 70 % of a dose is recovered in the urine in 48 hours.
+    in contrast, propylthiouracil is rapidly absorbed, reaching peak serum levels
+    after 1 hour. the bioavailability of 50 – 80 % may be due to incomplete absorption
+    or a large first - pass effect in the liver. the volume of distribution approximates
+    total body water with accumulation in the thyroid gland. most of an ingested dose
+    of propylthiouracil is excreted by the kidney as the inactive glucuronide within
+    24 hours. the short plasma half - life of these agents ( 1. 5 hours for propyl
+    - thiouracil and 6 hours for methimazole ) has little influence on the duration
+    of the antithyroid action or the dosing interval because both agents are accumulated
+    by the thyroid gland. for propyl -
+- source_sentence: '##sis. serious hypertension, diabetes. disorder surgical irradiation
+    of the pituitary tumor, or tion of both adrenals. patients large of cortisol during
+    and doses to mg soluble hydrocortisone as - ous intravenous day of surgery. the
+    dose reduced replacement levels, reduction in produce symptoms, including fever
+    and if adrenalectomy - term main - tenance that outlined for c. primary chrousos
+    syndrome — this or usually mutations the glucocorticoid - tor attempt to for hypo
+    pituitary ) axis hyperfunctioning'
+  sentences:
+  - '##sis. other serious disturbances include mental disorders, hypertension, and
+    diabetes. this disorder is treated by surgical removal of the tumor produc - ing
+    acth or cortisol, irradiation of the pituitary tumor, or resec - tion of one or
+    both adrenals. these patients must receive large doses of cortisol during and
+    after the surgical procedure. doses of up to 300 mg of soluble hydrocortisone
+    may be given as a continu - ous intravenous infusion on the day of surgery. the
+    dose must be reduced slowly to normal replacement levels, since rapid reduction
+    in dose may produce withdrawal symptoms, including fever and joint pain. if adrenalectomy
+    has been performed, long - term main - tenance is similar to that outlined above
+    for adrenal insufficiency. c. primary generalized glucocorticoid resistance (
+    chrousos ) syndrome — this rare sporadic or familial genetic condition is usually
+    due to inactivating mutations of the glucocorticoid recep - tor gene. in its attempt
+    to compensate for the defect, the hypo - thalamic - pituitary - adrenal ( hpa
+    ) axis is hyperfunctioning'
+  - 'oral : 200, 220, 250, 375, 500 mg tablets ; 375, 550 mg controlled - release
+    tablets ; 375, 500 mg delayed - release tablets ; 125 mg / 5 ml suspension oxaprozin
+    ( generic, daypro ) oral : 600 mg tablets, capsules piroxicam ( generic, feldene
+    ) oral : 10, 20 mg capsules salsalate, salicylsalicylic acid ( generic, disalcid
+    ) oral : 500, 750 mg tablets ; 500 mg capsules sodium salicylate ( generic ) oral
+    : 325, 650 mg enteric - coated tablets sodium thiosalicylate ( generic, rexolate
+    ) parenteral : 50 mg / ml for im injection sulindac ( generic, clinoril ) oral
+    : 150, 200 mg tablets suprofen ( profenal ) topical : 1 % ophthalmic solution
+    tolmetin ( generic, tolectin ) oral : 200, 600 mg tablets ; 400 mg capsules disease
+    - modifying antirheumatic drugs abatacept ( orencia ) parenteral : 250 mg / vial
+    lyophilized, for reconstitution for iv injection adalimumab ( humira ) parenteral
+    : 40 mg /'
+  - a half - life of about 10 hours. lutropin has only been approved for use in combination
+    with follitropin alfa for stimulation of follicular development in infertile women
+    with profound lh deficiency. it has not been approved for use with the other preparations
+    of fsh nor for simulating the endogenous lh surge that is needed to complete follicular
+    development and pre - cipitate ovulation. d. human chorionic gonadotropin hcg
+    is produced by the human placenta and excreted into the urine, whence it can be
+    extracted and purified. it is a glycoprotein consisting of a 92 - amino - acid
+    α chain virtually identical to that of fsh, lh, and tsh, and a β chain of 145
+    amino acids that resembles that of lh except for the presence of a carboxyl terminal
+    sequence of 30 amino acids not present in lh. choriogonadotropin alfa ( rhcg )
+    is a recombinant form of hcg. because of its greater consistency in biologic activity,
+    rhcg is packaged and dosed on the basis of weight rather than units of activity.
+    all of the other gonadotropins
+- source_sentence: five origin. action is inhibits activation of ( chapter a has an
+    ( ), produced cd28 on cell or on apc, leading - abatacept which contains the -
+    4 ) 86, inhibiting to pharmacokinetics abatacept infusion “ ” ( day 4 monthly
+    infusions. is weight patients weighing less than kg mg, 100 receiving 750 and
+    more than 100 kg 1000 regimens in adult group can if - 16
+  sentences:
+  - '##l 2005 ; 75 : 406. tan kr et al : neural basis for addictive properties of
+    benzodiazepines. nature 2010 ; 463 : 769. c a s e s t u d y a n s w e r the patient
+    was diagnosed with pathologic gambling sec - ondary to the dopamine agonist prescription.
+    compulsive behavior including gambling, binge eating, or hypersexu - ality is
+    observed in about 15 % of patients who receive dopamine agonist treatment. the
+    condition is not related to parkinson ’ s disease, as compulsive behaviors also
+    occur in patients with restless legs syndrome who are treated with the same medication.
+    the incidence with levodopa is lower, and compulsive behavior is sometimes preceded
+    by dose escalation.'
+  - α - blocking agents ( five drugs ). these dmards and biologics are discussed alphabetically,
+    independent of origin. abatacept mechanism of action abatacept is a co - stimulation
+    modulator biologic that inhibits the activation of t cells ( see also chapter
+    55 ). after a t cell has engaged an antigen - presenting cell ( apc ), a second
+    signal is produced by cd28 on the t cell that interacts with cd80 or cd86 on the
+    apc, leading to t - cell activation. abatacept ( which contains the endogenous
+    ligand ctla - 4 ) binds to cd80 and 86, thereby inhibiting the binding to cd28
+    and preventing the activation of t cells. pharmacokinetics abatacept is given
+    as three intravenous infusion “ induction ” doses ( day 0, week 2, and week 4
+    ), followed by monthly infusions. the dose is based on body weight ; patients
+    weighing less than 60 kg receiving 500 mg, those 60 – 100 kg receiving 750 mg,
+    and those more than 100 kg receiving 1000 mg. dosing regimens in any adult group
+    can be increased if needed. the terminal serum half - life is 13 – 16 days. co
+  - chapter 33 agents used in anemias ; hematopoietic growth factors 587 groups. in
+    particular, the depletion of tetrahydrofolate prevents synthesis of adequate supplies
+    of the deoxythymidylate ( dtmp ) and purines required for dna synthesis in rapidly
+    dividing cells, as shown in figure 33 – 3, section 2. the accumulation of folate
+    as n 5 - methyltetrahydrofolate and the associated depletion of tetra - hydrofolate
+    cofactors in vitamin b 12 deficiency have been referred to as the “ methylfolate
+    trap. ” this is the biochemical step whereby vitamin b 12 and folic acid metabolism
+    are linked, and it explains why the megaloblastic anemia of vitamin b 12 deficiency
+    can be partially corrected by ingestion of large amounts of folic acid. folic
+    acid can be reduced to dihydrofolate by the enzyme dihydro - folate reductase
+    ( figure 33 – 3, section 3 ) and thereby serve as a source of the tetrahydrofolate
+    required for synthesis of the purines and dtmp required for dna synthesis. vitamin
+    b 12 deficiency causes the accumulation of homo - cysteine due to reduced formation
+- source_sentence: 'in after a successful when, definition, no longer dependent. the
+    level : understand the long term changes by of initial molecular cellular targets
+    must be a com approaches animals and functional revealed target this the teg area
+    vta a tiny structure tip brainstem, which amygdala, hippocampus, drugs of abuse
+    christian retired and and parkinson ’ disease age at time, neurologist prescribed
+    restore dopamine levels. symptoms start fluctuate and dopamine role later, he
+    devel oped a interest gambling, buying lottery and visiting casino he'
+  sentences:
+  - 'common in addicts after a successful withdrawal when, by definition, they are
+    no longer dependent. addictive drugs increase the level of dopamine : reinforcement
+    to understand the long - term changes induced by drugs of abuse, their initial
+    molecular and cellular targets must be identified. a com - bination of approaches
+    in animals and humans, including functional imaging, has revealed the mesolimbic
+    dopamine system as the prime target of addictive drugs. this system originates
+    in the ventral teg - mental area ( vta ), a tiny structure at the tip of the brainstem,
+    which projects to the nucleus accumbens, the amygdala, the hippocampus, 32 drugs
+    of abuse christian luscher, md a retired accountant developed a tremor and slowing
+    of movements and was diagnosed with parkinson ’ s disease at age 67. at that time,
+    his neurologist prescribed levodopa to restore dopamine levels. two years later,
+    motor symptoms start to fluctuate and the dopamine receptor agonist ropini - role
+    is added to his treatment. ∗ a few months later, he devel - oped a strong interest
+    in gambling, first buying lottery tickets and then visiting a casino almost every
+    day. he concealed his gambling activity until'
+  - bleeding in over - the - counter use is low but still double that of over - the
+    - counter ibuprofen ( perhaps due to a dose effect ). rare cases of allergic pneumonitis,
+    leukocy - toclastic vasculitis, and pseudoporphyria as well as the common nsaid
+    - associated adverse effects have been noted. oxaprozin oxaprozin is another propionic
+    acid derivative nsaid. as noted in table 36 – 1, its major difference from the
+    other members of this subgroup is a very long half - life ( 50 – 60 hours ), although
+    oxapro - zin does not undergo enterohepatic circulation. it is mildly urico -
+    suric, making it potentially more useful in gout than some other nsaids. otherwise,
+    the drug has the same benefits and risks that are associated with other nsaids.
+    piroxicam piroxicam, an oxicam ( figure 36 – 1 ), is a nonselective cox inhib
+    - itor that at high concentrations also inhibits polymorphonuclear leukocyte migration,
+    decreases oxygen radical production, and inhibits lymphocyte function. its long
+    half - life
+  - 4 ). recombinant human g - csf ( rhug - csf ; filgrastim ) is produced in a bacterial
+    expression system. it is a nonglycosylated peptide of 175 amino acids, with a
+    molecular weight of 18 kda. recombinant human gm - csf ( rhugm - csf ; sargramostim
+    ) is produced in a yeast expression system. it is a partially glycosylated peptide
+    of 127 amino acids, with three molecular species with molecular weights of 15,
+    500 ; 15, 800 ; and 19, 500. these preparations have serum half - lives of 2 –
+    7 hours after intravenous or subcutaneous administration. pegfilgrastim, a covalent
+    conjugation product of filgrastim and a form of polyethylene glycol, has a much
+    longer serum half - life than recombinant g - csf, and it can be injected once
+    per myelo - suppressive chemotherapy cycle instead of daily for several days.
+    lenograstim, used widely in europe, is a glycosylated form of recombinant g -
+    csf. pharmacodynamics the myeloid growth
+- source_sentence: chapter drugs of 571 genetic by comparing relatively modest for
+    very high of the relative liability of a drug – its heritability, that basis of
+    common all is being genomic indicates that only perhaps even allele in combination
+    phenotype. involved remains elusive. some substance - have identified ( dehydrogenase
+    ), future will also focus on the mechanisms all drugs of abuse some not for substances
+    without reward such the and the dissocia anesthetics ( drugs, primarily
+  sentences:
+  - chapter 33 agents used in anemias ; hematopoietic growth factors 589 catalyzed
+    by the enzyme dihydrofolate reductase ( “ folate reductase ” ), to give dihydrofolic
+    acid ( figure 33 – 3, section 3 ). tetrahydrofolate is subsequently transformed
+    to folate cofactors possessing one - car - bon units attached to the 5 - nitrogen,
+    to the 10 - nitrogen, or to both positions ( figure 33 – 3 ). folate cofactors
+    are interconvertible by various enzymatic reactions and serve the important biochemical
+    function of donating one - carbon units at various levels of oxida - tion. in
+    most of these, tetrahydrofolate is regenerated and becomes available for reutilization.
+    pharmacokinetics the average american diet contains 500 – 700 mcg of folates daily,
+    50 – 200 mcg of which is usually absorbed, depending on metabolic requirements.
+    pregnant women may absorb as much as 300 – 400 mcg of folic acid daily. various
+    forms of folic acid are present in a wide variety of plant and animal tissues
+    ; the richest sources are yeast, liver, kidney, and green vegetables
+  - 602 section vi drugs used to treat diseases of the blood, inflammation, & gout
+    amputation or organ failure. venous clots tend to be more fibrin - rich, contain
+    large numbers of trapped red blood cells, and are recognized pathologically as
+    red thrombi. venous thrombi can cause severe swelling and pain of the affected
+    extremity, but the most feared consequence is pulmonary embolism. this occurs
+    when part or all of the clot breaks off from its location in the deep venous system
+    and travels as an embolus through the right side of the heart and into the pulmonary
+    arterial circulation. sudden occlusion of a large pulmonary artery can cause acute
+    right heart failure and sudden death. in addition lung ischemia or infarction
+    will occur distal to the occluded pulmonary arterial segment. such emboli usually
+    arise from the deep venous system of the proximal lower extremities or pelvis.
+    although all thrombi are mixed, the platelet nidus dominates the arterial thrombus
+    and the fibrin tail dominates the venous thrombus. blood coagulation cascade blood
+    coagulates due to the transformation of soluble fibrinogen into insoluble fi
+  - chapter 32 drugs of abuse 571 of environmental and genetic factors. heritability
+    of addiction, as determined by comparing monozygotic with dizygotic twins, is
+    relatively modest for cannabinoids but very high for cocaine. it is of interest
+    that the relative risk for addiction ( addiction liability ) of a drug ( table
+    32 – 1 ) correlates with its heritability, suggesting that the neurobiologic basis
+    of addiction common to all drugs is what is being inherited. further genomic analysis
+    indicates that only a few alleles ( or perhaps even a single recessive allele
+    ) need to function in combination to produce the phenotype. however, identification
+    of the genes involved remains elusive. although some substance - specific candidate
+    genes have been identified ( eg, alcohol dehydrogenase ), future research will
+    also focus on genes implicated in the neurobiologic mechanisms common to all addictive
+    drugs. nonaddictive drugs of abuse some drugs of abuse do not lead to addiction.
+    this is the case for substances that alter perception without causing sensations
+    of reward and euphoria, such as the hallucinogens and the dissocia - tive anesthetics
+    ( table 32 – 1 ). unlike addictive drugs, which primarily
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). It maps sentences & paragraphs to a 384-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:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision c9745ed1d9f207416be6d2e6f8de32d1f16199bf -->
+- **Maximum Sequence Length:** 256 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### 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': 256, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, '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): 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("RikoteMaster/retriever_pdf_and_books")
+# Run inference
+sentences = [
+    'chapter drugs of 571 genetic by comparing relatively modest for very high of the relative liability of a drug – its heritability, that basis of common all is being genomic indicates that only perhaps even allele in combination phenotype. involved remains elusive. some substance - have identified ( dehydrogenase ), future will also focus on the mechanisms all drugs of abuse some not for substances without reward such the and the dissocia anesthetics ( drugs, primarily',
+    'chapter 32 drugs of abuse 571 of environmental and genetic factors. heritability of addiction, as determined by comparing monozygotic with dizygotic twins, is relatively modest for cannabinoids but very high for cocaine. it is of interest that the relative risk for addiction ( addiction liability ) of a drug ( table 32 – 1 ) correlates with its heritability, suggesting that the neurobiologic basis of addiction common to all drugs is what is being inherited. further genomic analysis indicates that only a few alleles ( or perhaps even a single recessive allele ) need to function in combination to produce the phenotype. however, identification of the genes involved remains elusive. although some substance - specific candidate genes have been identified ( eg, alcohol dehydrogenase ), future research will also focus on genes implicated in the neurobiologic mechanisms common to all addictive drugs. nonaddictive drugs of abuse some drugs of abuse do not lead to addiction. this is the case for substances that alter perception without causing sensations of reward and euphoria, such as the hallucinogens and the dissocia - tive anesthetics ( table 32 – 1 ). unlike addictive drugs, which primarily',
+    '602 section vi drugs used to treat diseases of the blood, inflammation, & gout amputation or organ failure. venous clots tend to be more fibrin - rich, contain large numbers of trapped red blood cells, and are recognized pathologically as red thrombi. venous thrombi can cause severe swelling and pain of the affected extremity, but the most feared consequence is pulmonary embolism. this occurs when part or all of the clot breaks off from its location in the deep venous system and travels as an embolus through the right side of the heart and into the pulmonary arterial circulation. sudden occlusion of a large pulmonary artery can cause acute right heart failure and sudden death. in addition lung ischemia or infarction will occur distal to the occluded pulmonary arterial segment. such emboli usually arise from the deep venous system of the proximal lower extremities or pelvis. although all thrombi are mixed, the platelet nidus dominates the arterial thrombus and the fibrin tail dominates the venous thrombus. blood coagulation cascade blood coagulates due to the transformation of soluble fibrinogen into insoluble fi',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# 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.*
+-->
+
+<!--
+## 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
+
+#### Unnamed Dataset
+
+* Size: 57,126 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                             | positive                                                                             |
+  |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                               |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 58.68 tokens</li><li>max: 133 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 143.97 tokens</li><li>max: 256 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                                                                                                                                                                                                                                                                                                    | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>advanced march lecture : lps weights ola svensson1 this lecture do the : we ( actually hedge method. solve lps. fast very solving lps approximately. version 11 of topics in tcs, ” were simon rodriguez the by that used in the last lecture. recall last the lecture, saw how fairly follow the of recall that game t and n experts was : for : i ∈ n gives up or ) based the expert, up 3. with the expert advice ’ decides the up / down</code> | <code>advanced algorithms march 22, 2022 lecture 9 : solving lps using multiplicative weights notes by ola svensson1 in this lecture we do the following : • we describe the multiplicative weight update ( actually hedge ) method. • we then use this method to solve covering lps. • this is a very fast and simple ( i. e., very attractive ) method for solving these lps approximately. these lecture notes are partly based on an updated version of “ lecture 11 of topics in tcs, 2015 ” that were written by vincent eggerling and simon rodriguez and on the lecture notes by shiva kaul that we used in the last lecture. 1 recall last lecture in the previous lecture, we saw how to use the weighted majority method in order to fairly smartly follow the advice of experts. recall that the general game - setting with t days and n experts was as follows : for t = 1,..., t : 1. each expert i ∈ [ n ] gives some advice : up or down 2. aggregator ( you ) predicts, based on the advice of the expert, up or down. 3. ad...</code> |
+  | <code>or down predicts, up down. adversary, of expert the the / down 4. aggregator the parameterized > 0 “ rate now as : • expert i ( 1. ( experts are in begin - at each t • predict / based weighted vote w = w t w n observing the set ( t i = w ( i · ( 1−ε i ] was ( trustworthiness experts. lecture the when / 2. the sequence of outcomes, t, and expert ∈ [ n ], of wm mistakes ≤2</code>                                                        | <code>up or down 2. aggregator ( you ) predicts, based on the advice of the expert, up or down. 3. adversary, with knowledge of the expert advice and the aggregator ’ s decision, decides the up / down outcome. 4. aggregator observes the outcome and [UNK] if his prediction was incorrect. the weighted majority algorithm, parameterized by [UNK] > 0 ( the “ learning rate ” ), now works as follows : • assign each expert i a weight w ( 1 ) i initialized to 1. ( all experts are equally trustworthy in the begin - ning. ) at each time t : • predict up / down based on a weighted majority vote per w ( t ) = ( w ( t ) 1,..., w ( t ) n ). • after observing the cost vector, set w ( t + 1 ) i = w ( t ) i · ( 1−ε ) for every expert i ∈ [ n ] whose prediction was wrong. ( discount the trustworthiness of erroneous experts. ) last lecture we analyzed the case when [UNK] = 1 / 2. the same proof gives the following theorem 1 for any sequence of outcomes, duration t, and expert i ∈ [ n ], # of wm mistakes ≤2</code>         |
+  | <code>) last lecture analyzed [UNK] = 1 / 2. the following theorem sequence outcomes, duration t, and n wm ≤2 [UNK] ( ’ + o ( ( ). notes as for lecturer. have not inconsistent omit citations 1</code>                                                                                                                                                                                                                                                   | <code>##roneous experts. ) last lecture we analyzed the case when [UNK] = 1 / 2. the same proof gives the following theorem 1 for any sequence of outcomes, duration t, and expert i ∈ [ n ], # of wm mistakes ≤2 ( 1 + [UNK] ) · ( # of i ’ s mistakes ) + o ( log ( n ) / [UNK] ). 1disclaimer : these notes were written as notes for the lecturer. they have not been peer - reviewed and may contain inconsistent notation, typos, and omit citations of relevant works. 1</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+* Size: 6,348 evaluation samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                              | positive                                                                             |
+  |:--------|:------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                               |
+  | details | <ul><li>min: 14 tokens</li><li>mean: 97.31 tokens</li><li>max: 142 tokens</li></ul> | <ul><li>min: 53 tokens</li><li>mean: 238.84 tokens</li><li>max: 256 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                                                                                                                                                                                                                                                                                                                     | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>more at gesic doses. be predominantly however, it also the μ agonist weak or partial nist it mixed available. it used orally however, its injection miscellaneous tramadol is on blockade has been norepinephrine function. because it partially is μ agonist. the recommended mg orally times daily. association with ; drug contraindicated in history of epilepsy with that lower the serious risk the development sero toni</code>                               | <code>##phine but appears to produce more sedation at equianal - gesic doses. butorphanol is considered to be predominantly a κ agonist. however, it may also act as a partial agonist or antagonist at the μ receptor. benzomorphans pentazocine is a κ agonist with weak μ - antagonist or partial ago - nist properties. it is the oldest mixed agent available. it may be used orally or parenterally. however, because of its irritant properties, the injection of pentazocine subcutaneously is not recommended. miscellaneous tramadol is a centrally acting analgesic whose mechanism of action is predominantly based on blockade of serotonin reuptake. tramadol has also been found to inhibit norepinephrine transporter function. because it is only partially antagonized by naloxone, it is believed to be only a weak μ - receptor agonist. the recommended dosage is 50 – 100 mg orally four times daily. toxicity includes association with seizures ; the drug is relatively contraindicated in patients with a history of...</code> |
+  | <code>##ly four times daily. toxicity includes relatively in a of the serious is the of - inhibitor ( ). typically abate after several days of is no clinically respiration or tem thus far given that action of tramadol largely - serve as an adjunct pure opioid treatment of chronic is newer with modest μ significant norepinephrine - inhibiting models, its effects moderately by naloxone but reduced adrenoceptor antagonist. furthermore, norepinephrine</code> | <code>##ly four times daily. toxicity includes association with seizures ; the drug is relatively contraindicated in patients with a history of epilepsy and for use with other drugs that lower the seizure threshold. another serious risk is the development of sero - tonin syndrome, especially if selective serotonin reuptake inhibitor ( ssri ) antidepressants are being administered ( see chapter 16 ). other side effects include nausea and dizziness, but these symptoms typically abate after several days of therapy. it is surprising that no clinically significant effects on respiration or the cardiovascular sys - tem have thus far been reported. given the fact that the analgesic action of tramadol is largely independent of μ - receptor action, tra - madol may serve as an adjunct with pure opioid agonists in the treatment of chronic neuropathic pain. tapentadol is a newer analgesic with modest μ - opioid receptor affinity and significant norepinephrine reuptake - inhibiting action. in animal mode...</code> |
+  | <code>- action. in its analgesic effects were moderately by strongly adrenoceptor antagonist. porter ( 6 was than of its the transporter ( of tapentadol 2008 been shown to as oxycodone the to gastrointesti complaints nausea. carries risk for for is how in cal to tramadol mechanism based opioid antitussives the effective drugs suppression of this is analgesia. in effect</code>                                                                                 | <code>- inhibiting action. in animal models, its analgesic effects were only moderately reduced by naloxone but strongly reduced by an α 2 - adrenoceptor antagonist. furthermore, its binding to the norepinephrine trans - porter ( net, see chapter 6 ) was stronger than that of tramadol, whereas its binding to the serotonin transporter ( sert ) was less than that of tramadol. tapentadol was approved in 2008 and has been shown to be as effective as oxycodone in the treatment of moderate to severe pain but with a reduced profile of gastrointesti - nal complaints such as nausea. tapentadol carries risk for seizures in patients with seizure disorders and for the development of sero - tonin syndrome. it is unknown how tapentadol compares in clini - cal utility to tramadol or other analgesics whose mechanism of action is not based primarily on opioid receptor pharmacology. antitussives the opioid analgesics are among the most effective drugs available for the suppression of cough. this effect is oft...</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 128
+- `per_device_eval_batch_size`: 128
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 5
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `dataloader_drop_last`: True
+- `dataloader_num_workers`: 2
+- `load_best_model_at_end`: True
+- `push_to_hub`: True
+- `hub_model_id`: RikoteMaster/retriever_pdf_and_books
+- `hub_strategy`: end
+- `hub_private_repo`: False
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 128
+- `per_device_eval_batch_size`: 128
+- `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`: 5
+- `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`: False
+- `fp16`: True
+- `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`: True
+- `dataloader_num_workers`: 2
+- `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
+- `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`: True
+- `resume_from_checkpoint`: None
+- `hub_model_id`: RikoteMaster/retriever_pdf_and_books
+- `hub_strategy`: end
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `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
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch      | Step     | Training Loss | Validation Loss |
+|:----------:|:--------:|:-------------:|:---------------:|
+| 0.1121     | 50       | 0.0343        | -               |
+| 0.2242     | 100      | 0.0199        | -               |
+| 0.3363     | 150      | 0.0184        | -               |
+| 0.4484     | 200      | 0.0188        | 0.0069          |
+| 0.5605     | 250      | 0.019         | -               |
+| 0.6726     | 300      | 0.0155        | -               |
+| 0.7848     | 350      | 0.0128        | -               |
+| 0.8969     | 400      | 0.0139        | 0.0048          |
+| 1.0090     | 450      | 0.0151        | -               |
+| 1.1211     | 500      | 0.012         | -               |
+| 1.2332     | 550      | 0.0144        | -               |
+| 1.3453     | 600      | 0.0117        | 0.0037          |
+| 1.4574     | 650      | 0.0164        | -               |
+| 1.5695     | 700      | 0.0099        | -               |
+| 1.6816     | 750      | 0.0128        | -               |
+| 1.7937     | 800      | 0.0076        | 0.0035          |
+| 1.9058     | 850      | 0.0098        | -               |
+| 2.0179     | 900      | 0.0147        | -               |
+| 2.1300     | 950      | 0.0087        | -               |
+| 2.2422     | 1000     | 0.012         | 0.0033          |
+| 2.3543     | 1050     | 0.0106        | -               |
+| 2.4664     | 1100     | 0.0176        | -               |
+| 2.5785     | 1150     | 0.0123        | -               |
+| 2.6906     | 1200     | 0.0122        | 0.0032          |
+| 2.8027     | 1250     | 0.0126        | -               |
+| 2.9148     | 1300     | 0.013         | -               |
+| 3.0269     | 1350     | 0.011         | -               |
+| 3.1390     | 1400     | 0.0139        | 0.0031          |
+| 3.2511     | 1450     | 0.01          | -               |
+| 3.3632     | 1500     | 0.0122        | -               |
+| 3.4753     | 1550     | 0.0094        | -               |
+| 3.5874     | 1600     | 0.0122        | 0.0030          |
+| 3.6996     | 1650     | 0.0147        | -               |
+| 3.8117     | 1700     | 0.0126        | -               |
+| 3.9238     | 1750     | 0.0125        | -               |
+| 4.0359     | 1800     | 0.0138        | 0.0030          |
+| 4.1480     | 1850     | 0.0105        | -               |
+| 4.2601     | 1900     | 0.0107        | -               |
+| 4.3722     | 1950     | 0.0179        | -               |
+| 4.4843     | 2000     | 0.011         | 0.0029          |
+| 4.5964     | 2050     | 0.0126        | -               |
+| 4.7085     | 2100     | 0.0137        | -               |
+| 4.8206     | 2150     | 0.0084        | -               |
+| **4.9327** | **2200** | **0.012**     | **0.0029**      |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.17
+- Sentence Transformers: 4.1.0
+- Transformers: 4.52.3
+- PyTorch: 2.7.0+cu126
+- Accelerate: 1.7.0
+- Datasets: 3.6.0
+- Tokenizers: 0.21.1
+
+## 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",
+}
+```
+
+#### 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 +1,25 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.52.3",
+    "pytorch": "2.7.0+cu126"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:688b8d59b5e233387311edabe584f06754c255fd312258aabdeadbb79dc188da
+size 90864192

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": 256,
+  "do_lower_case": false
+}

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 +1,65 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 256,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8511ebcd4819c8c4cbd85612f91ffa256732ae19852f3129fdd07b78e6dd2b6a
+size 6161