constants.py

import os

CORPUS_BY_DESC = {
    'RedPajama (LLaMA tokenizer), 1.4T tokens': 'v3_rpj_llama_c4',
    'Pile-val (LLaMA tokenizer), 390M tokens': 'v3_pileval_llama',
    'Pile-val (GPT-2 tokenizer), 380M tokens': 'v3_pileval',
}
CORPUS_DESCS = list(CORPUS_BY_DESC.keys())
QUERY_TYPE_BY_DESC = {
    '1. Count an n-gram': 'count',
    '2. Compute the probability of the last token in an n-gram': 'compute_prob',
    '3. Compute the next-token distribution of an (n-1)-gram': 'get_next_token_distribution_approx',
    '4. Compute the ∞-gram probability of the last token': 'compute_infgram_prob',
    '5. Compute the ∞-gram next-token distribution': 'get_infgram_next_token_distribution_approx',
    # '6. Searching for document containing n-gram(s)': 'get_a_random_document_from_cnf_query_fast_approx',
    '6. Searching for documents containing n-gram(s)': 'get_random_documents_from_cnf_query_fast_approx',
    # '7. Analyze an (AI-generated) document using ∞-gram': 'analyze_document',
}
QUERY_DESC_BY_TYPE = {v: k for k, v in QUERY_TYPE_BY_DESC.items()}
QUERY_DESCS = list(QUERY_TYPE_BY_DESC.keys())

MAX_QUERY_CHARS = int(os.environ.get('MAX_QUERY_CHARS', 1000))
MAX_INPUT_DOC_TOKENS = int(os.environ.get('MAX_INPUT_DOC_TOKENS', 1000))
MAX_OUTPUT_DOC_TOKENS = int(os.environ.get('MAX_OUTPUT_DOC_TOKENS', 5000))
MAX_CNT_FOR_NTD = int(os.environ.get('MAX_CNT_FOR_NTD', 1000))
MAX_CLAUSE_FREQ = int(os.environ.get('MAX_CLAUSE_FREQ', 10000))
MAX_CLAUSE_FREQ_FAST = int(os.environ.get('MAX_CLAUSE_FREQ_FAST', 1000000))
MAX_CLAUSE_FREQ_FAST_APPROX_PER_SHARD = int(os.environ.get('MAX_CLAUSE_FREQ_FAST_APPROX_PER_SHARD', 50000))
MAX_DIFF_TOKENS = int(os.environ.get('MAX_DIFF_TOKENS', 100))
MAX_DIFF_BYTES = 2 * MAX_DIFF_TOKENS
MAX_CLAUSES_IN_CNF = int(os.environ.get('MAX_CLAUSES_IN_CNF', 4))
MAX_TERMS_IN_DISJ_CLAUSE = int(os.environ.get('MAX_TERMS_IN_DISJ_CLAUSE', 4))