[TEA19896446]

pip install gensim

import gensim.downloader as api

model=api.loade(glove-twitter-25)
......
model.most_similar(positive=[y,z], negative=[x], topn=1)
......

But only got htb and {, the follow chars seems not correct, any hints?

[trevor69000]

did anyone get this

[axcqwrq]

Your model is not correct.
```
vec1 = model[word1]
vec2 = model[word2]
vec_target = model[target]

analogy_vector = vec_target + (vec2 - vec1)

result = model.similar_by_vector(analogy_vector, topn=1)
```

[TEA19896446]

Your model is not correct.
```
            vec1 = model[word1]
            vec2 = model[word2]
            vec_target = model[target]

            analogy_vector = vec_target + (vec2 - vec1)

            result = model.similar_by_vector(analogy_vector, topn=1)
```

Yes! It works

[cavour13]

mine is working too thanks

[x1rx]

import gensim.downloader as api
import re
import string

# Load the GloVe model
model = api.load("glove-twitter-25")

# File path to the challenge file
file_path = "chal.txt"

flag = ""

# Mapping full-width characters to ASCII
full_width_map = {
    "０": "0",
    "１": "1",
    "２": "2",
    "３": "3",
    "４": "4",
    "５": "5",
    "６": "6",
    "７": "7",
    "８": "8",
    "９": "9",
}


# Helper function to keep only ASCII characters, digits, punctuation, and whitespace
def keep_ascii_and_digits(text):
    normalized_text = "".join(full_width_map.get(c, c) for c in text)
    return "".join(
        c
        for c in normalized_text
        if c
        in string.ascii_letters + string.digits + string.punctuation + string.whitespace
    )


# Regex pattern to capture the analogy components
pattern = re.compile(r"^Like ([^\s]+) is to ([^\s]+), ([^\s]+) is to\?$")

# Read each line from chall.txt and calculate the analogy
with open(file_path, "r") as file:
    for line in file:
        try:
            # Use regex to extract words from the line
            match = pattern.match(line.strip())
            if not match:
                print(f"Skipping line due to incorrect format: {line}")
                continue

            word1, word2_target, target = match.groups()

            vec1 = model[word1]
            vec2 = model[word2_target]
            vec_target = model[target]

            analogy_vector = vec_target + (vec2 - vec1)
            result = model.similar_by_vector(analogy_vector, topn=1)
            result_word = keep_ascii_and_digits(result[0][0])
            print(
                f"Target word for analogy '{target}' ({word2_target} - {word1} + {target}): {result_word}"
            )
            flag += result_word
        except KeyError as e:
            print(f"Word not found in model: {e}")

print(f"[+] Flag: {flag}")

[elena83]

wow, many thanks for the writeup

[nocapx]

dude you saved me

This forum account is currently banned. Ban Length: Permanent (N/A Remaining)
Ban Reason: Leeching | http://c66go4clkqodr7tdjfu76jztjs7w7d3fajdeypxn73v4ju3dt7g5yyyd.onion/Forum-Ban-Appeals if you feel this is incorrect.

[8i9egw9n0]

THANK YOU! I can't believe how close and also NOT close I was <3

[potato_moose]

WOW, thanks for the writeup, dude!
That's great!