LLM
Collection
2 items
β’
Updated
ko-gemma-2-9b-it-fn-merged is a merge of the following models using mergekit:
λκ΅¬κ° μλ κ²½μ°:
<start_of_turn>user
You are a helpful assistant with access to the following functions. Use them if required -
{
"name": "search_books",
"description": "Search for books based on title, author, or genre",
"parameters": {
"type": "object",
"properties": {
"title": {
"type": "string",
"description": "The title of the book"
},
"author": {
"type": "string",
"description": "The author of the book"
},
"genre": {
"type": "string",
"description": "The genre of the book"
}
},
"required": []
}
}
To use these functions respond with:
<functioncall> {"name": "function_name", "arguments": {"arg_1": "value_1", "arg_1": "value_1", ...}} </functioncall>
Edge cases you must handle:
- If there are no functions that match the user request, you will respond politely that you cannot help.
User Question:
μ±
μ μ°Ύκ³ μλλ° μ λͺ©μ κΈ°μ΅νμ§ λͺ»νλ€μ. μ μμ μ΄λ¦μ μ‘°μ§ μ€μ°μ
λλ€.<end_of_turn>
<start_of_turn>model
<functioncall> {"name": "search_books", "arguments": {"author": "George Orwell"}} </functioncall> <end_of_turn>
<start_of_turn>user
{"books": [{"title": "1984", "author": "George Orwell", "genre": "λμ€ν νΌμ"}, {"title": "λλ¬Όλμ₯", "author": "George Orwell", "genre": "μ μΉ νμ"}]} <end_of_turn>
<start_of_turn>model
μ‘°μ§ μ€μ°μ μ±
μ λ κΆ μ°Ύμμ΄μ. 첫 λ²μ§Έλ "1984"λΌλ λμ€ν νΌμ μμ€μ΄μμ. λ λ²μ§Έλ μ μΉ νμμΈ "λλ¬Όλμ₯"μ
λλ€. <end_of_turn>
<start_of_turn>user
μ€, λ§μμ, "λλ¬Όλμ₯"μ μ°Ύκ³ μμμ΄μ. κ°μ μ₯λ₯΄μ μ±
λ μ°Ύμμ€ μ μμκΉμ?<end_of_turn>
<start_of_turn>model
<functioncall> {"name": "search_books", "arguments": {"genre": "μ μΉ νμ"}} </functioncall> <end_of_turn>
<start_of_turn>user
{"books": [{"title": "Catch-22", "author": "Joseph Heller", "genre": "μ μΉ νμ"}, {"title": "Slaughterhouse-Five", "author": "Kurt Vonnegut", "genre": "μ μΉ νμ"}]} <end_of_turn>
<start_of_turn>model
λΉμ°νμ, μ μΉ νμ μ₯λ₯΄μ ν΄λΉνλ μ±
λ κΆ λ μλ €λ릴κ²μ. Joseph Hellerμ "Catch-22"μ Kurt Vonnegutμ "Slaughterhouse-Five"μ
λλ€. <end_of_turn>
λκ΅¬κ° μλ κ²½μ°:
<start_of_turn>user
You are a helpful assistant, with no access to external functions.
User Question:
μ£Όμ΄μ§ μ«μ μνμ€λ λ€μκ³Ό κ°μ΅λλ€: 2, 4, 6, 8, 10. κ° μ«μλ λ°λ€μ νλκ³Ό λ§μ°¬κ°μ§λ‘ μκ°μ μκ°μ λνλ
λλ€. μνμ€λ₯Ό κ³μνλ©΄ κ° μ«μ μ¬μ΄μ μ°¨μ΄κ° λμΌνλ€λ κ²μ μ μ μμ΅λλ€. λ§μΉ λ°λκ³Ό ν΄λ₯κ° λ°λ€μ νλμ νμ±νλ κ²μ²λΌ, 무μΈκ°κ° μ«μ μνμ€λ₯Ό νμ±νκ³ μμ΅λλ€. μνμ€μμ λ€μ μ«μλ 무μμ΄λ©°, μκ°κ³Όμ κ΄κ³μμ μ΄λ€ μλ―Έλ₯Ό κ°μ§λμ§ μλ €μ£ΌμΈμ.<end_of_turn>
<start_of_turn>model
κΈ°μ λ ν¨ν΄μ λ°λΌ, μνμ€μμ λ€μ μ«μλ 12μ
λλ€. μ΄λ μ«μ 10μΌλ‘ ννλ μ΄μ μκ°μ΄ 2κ°μ μκ° λ¨μ λ€λ₯Ό λνλ
λλ€. ν¨ν΄μ μνμ€μμ κ° νμ μ«μκ° μ΄μ μ«μ λ€μμ 2κ°μ μκ° λ¨μμΈ κ²μ μμ¬ν©λλ€. λ°λΌμ 12 λ€μ μ«μλ 14μ΄λ©°, κ·Έ λ€μμ 16μ΄ λ©λλ€. μ΄λ¬ν ν¨ν΄μ μΌμ ν μ°¨μ΄κ° μλ λ±μ°¨ μμ΄λ‘ μλ €μ Έ μμ΅λλ€. <end_of_turn>
<start_of_turn>user
ν¨ν΄μ κ΄ν΄ μ΄μΌκΈ°νμλ©΄, νΌλ³΄λμΉ μμ΄μ λν΄ κΆκΈν©λλ€. μ΄κ²μ 무μμ΄κ³ μ΄λ»κ² μλνλμ?<end_of_turn>
<start_of_turn>model
νΌλ³΄λμΉ μμ΄μ κ° μ«μκ° μ΄μ λ μ«μμ ν©μΌλ‘ μ΄λ£¨μ΄μ§ μμ΄μ
λλ€. μμμ 0κ³Ό 1λ‘λΆν° μμνμ¬ μ΄μ λ μ«μλ₯Ό λν΄ λ€μ μ«μλ₯Ό μ»λ λ°©μμΌλ‘ κ³μλ©λλ€. λ°λΌμ μμ΄μ 0, 1, 1, 2, 3, 5, 8, 13, 21 λ±μΌλ‘ μ΄μ΄μ§λλ€. μ΄μ λ μ«μλ₯Ό λνλ©΄μ λ€μ μ«μλ₯Ό ꡬνλ ν¨ν΄μ 무νν μ΄μ΄μ§κ² λ©λλ€. νΌλ³΄λμΉ μμ΄μ μ΄ν리μ μνμμΈ λ μ€λλ₯΄λ νΌλ³΄λμΉκ° μμμ μκ°ν κ²μμ μ΄λ¦μ λ°μμ΅λλ€. νΌλ³΄λμΉ μμ΄μ λ무μ κ°μ§ μΉκΈ°, μ€κΈ°μ μμ΄ λ°°μ΄λλ νν, λ¬ν½μ΄ κ»μ§μ λͺ¨μκ³Ό κ°μ΄ μμ°μμ λ§μ΄ λνλ©λλ€. <end_of_turn>
models:
- model: rtzr/ko-gemma-2-9b-it
- model: NeuroWhAI/ko-gemma-2-9b-it-fn
parameters:
density: 0.3
weight: 0.2
merge_method: dare_ties
base_model: rtzr/ko-gemma-2-9b-it
parameters:
int8_mask: true
dtype: bfloat16