β¨ Subscribe My YouTube Channel β¨
π μμ¬AI π
β¨ Ollama Repo : Q5_K_M β¨
π μμ¬AI π
π Shorts Tulu3+Korean Merge π
"Performance Disclaimer: This merged model has not undergone comprehensive validation testing. As such, its actual performance characteristics remain unverified. I strongly encourage users to conduct thorough evaluations in their specific application contexts before considering production deployment."
Llama-3.1-Sisaai-Ko-Tulu-DPO-Merge-8B
By merging it with a Korean language model, the following benefits arise:
Korean with logical reasoning, mathematical problem-solving, and reliability (TruthfulQA)
Merge Method
This model was merged using the DARE TIES merge method using NousResearch/Meta-Llama-3.1-8B-Instruct as a base.
Models Merged
The following models were included in the merge:
Modelfile
The following YAML configuration was used to produce this model:
FROM llama-3.1-sisaai-ko-tulu-dpo-merge-8b-Q5_K_M.gguf
TEMPLATE """{{ if .Messages }}
{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|>
{{- if .System }}
{{ .System }}
{{- end }}
{{- if .Tools }}
You are a helpful assistant with tool calling capabilities. When you receive a tool call response, use the output to format an answer to the original user question.
{{- end }}
{{- end }}<|eot_id|>
{{- range $i, $_ := .Messages }}
{{- $last := eq (len (slice $.Messages $i)) 1 }}
{{- if eq .Role "user" }}<|start_header_id|>user<|end_header_id|>
{{- if and $.Tools $last }}
Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.
Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables.
{{ $.Tools }}
{{- end }}
{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|>
{{ end }}
{{- else if eq .Role "assistant" }}<|start_header_id|>assistant<|end_header_id|>
{{- if .ToolCalls }}
{{- range .ToolCalls }}{"name": "{{ .Function.Name }}", "parameters": {{ .Function.Arguments }}}{{ end }}
{{- else }}
{{ .Content }}{{ if not $last }}<|eot_id|>{{ end }}
{{- end }}
{{- else if eq .Role "tool" }}<|start_header_id|>ipython<|end_header_id|>
{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|>
{{ end }}
{{- end }}
{{- end }}
{{- else }}
{{- if .System }}<|start_header_id|>system<|end_header_id|>
{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>
{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>
{{ end }}{{ .Response }}{{ if .Response }}<|eot_id|>{{ end }}"""
PARAMETER stop <|start_header_id|>
PARAMETER stop <|end_header_id|>
PARAMETER stop <|eot_id|>
PARAMETER temperature 0.6
νμ΄μ¬ μ½λ νΌλ³΄λμΉ μμ΄
νμ΄μ¬μμ νΌλ³΄λμΉ μμ΄μ κ³μ°νλ λ°©λ²μ μ¬λ¬ κ°μ§κ° μμ΅λλ€. κ°μ₯ κΈ°λ³Έμ μΈ λ°©λ²μ λ°λ³΅λ¬Έκ³Ό 리μ€νΈλ₯Ό μ¬μ©νλ κ²μ
λλ€.
def fibonacci(n):
fib = [0, 1]
while len(fib) < n:
fib.append(fib[-1] + fib[-2])
return fib[:n]
# μμ: νΌλ³΄λμΉ μμ΄μ 첫 10κ° μ«μ
print(fibonacci(10))
μ΄ μ½λμμλ fib 리μ€νΈλ₯Ό μ΄κΈ°ννκ³ , λ°λ³΅λ¬Έ λ΄μμ μ΄μ λ νμ λν΄ λ€μ νμ κ³μ°ν©λλ€. λ§μ§λ§μΌλ‘, νμν λ§νΌμ νΌλ³΄λμΉ μμ΄μ λ°νν©λλ€.
λν, νμ΄μ¬μ μ λλ μ΄ν° κΈ°λ₯μ μ¬μ©νμ¬ λ©λͺ¨λ¦¬λ₯Ό ν¨μ¨μ μΌλ‘ μ¬μ©ν μλ μμ΅λλ€.
def fibonacci(n):
a, b = 0, 1
for _ in range(n):
yield a
a, b = b, a + b
# μμ: νΌλ³΄λμΉ μμ΄μ 첫 10κ° μ«μ
print(list(fibonacci(10)))
μ΄ μ½λμμλ aμ b λ³μλ₯Ό μ΄κΈ°ννκ³ , μ λλ μ΄ν° ν¨μ λ΄μμ λ°λ³΅λ¬Έμ μ¬μ©νμ¬ λ€μ νμ κ³μ°ν©λλ€. λ§μ§λ§μΌλ‘, νμν λ§νΌμ νΌλ³΄λμΉ μμ΄μ λ°νν©λλ€.
λ§μ§λ§μΌλ‘, νμ΄μ¬ 3.8 μ΄μ λ²μ μμλ μ»΄ν리ν¨μ
μ μ¬μ©νμ¬ λ κ°κ²°νκ² μ½λλ₯Ό μμ±ν μλ μμ΅λλ€.
def fibonacci(n):
return [0, 1] + [a + b for a, b in zip([0, 1], [1, 0]) for _ in range(n - 2)]
# μμ: νΌλ³΄λμΉ μμ΄μ 첫 10κ° μ«μ
print(fibonacci(10))
μ΄ μ½λμμλ 리μ€νΈ μ»΄ν리ν¨μ
μ μ¬μ©νμ¬ νΌλ³΄λμΉ μμ΄μ μμ±ν©λλ€.
κ° λ°©λ²μ μμ μ μν©μ λ§λ κ²μ μ νν μ μμ΅λλ€.
λ΄μ μ¬ν μΌμ
λ΄μ μ¬νμ κ³ννκ³ μλ€λ©΄, λ€μν κ΄κ΄μ§μ νλμΌλ‘ μ±μμ§ λ©μ§ μΌμ λ§λ€ μ μμ κ²μ
λλ€. μ¬κΈ°μλ λ΄μμ λνμ μΈ λλλ§ν¬λΆν° μ§μ μμκ³Ό λ¬ΈνκΉμ§ λ€μν νμ΄ ν¬ν¨λμ΄ μμ΅λλ€.
1μΌμ°¨: 맨ν΄νΌ
μμΉ¨: λΈλ£¨ν΄λ¦° λΈλ¦¬μ§μ μλ¦λ€μ΄ μ κ²½μ μ¦κΈ°λ©° μμν©λλ€.
μ€μ : μΌνΈλ΄ νν¬λ₯Ό κ±ΈμΌλ©°, 벨뷰 λλ‘μ λ‘μ¦ κ°λ λ± μ¬λ¬ κ²½μΉλ₯Ό κ°μν©λλ€.
μ μ¬: λ΄μμμ κ°μ₯ μ λͺ
ν ν«λκ·Έ μλΉμΈ ν«λκ·Έ μ€ν λ (νμ΄λμ€ μ€νΈλ¦¬νΈ κ·Όμ²) μμ λ§μλ ν«λκ·Έλ₯Ό λ¨Ήμ΅λλ€.
μ€ν: μΈκ³μ μΈ λλλ§ν¬μΈ μμ μ μ¬μ μ (Statue of Liberty) λ°©λ¬Έ λ° Ellis Island νλ°©μ ν©λλ€. μ΄κ³³μ λ΄μμ λμ°©ν λ§μ μ΄λ―Όμλ€μ΄ μ²μμΌλ‘ λ°κΈΈμ μ¬λ¦° κ³³μ
λλ€.
μ λ
: 맨ν΄νΌμ μ€μ¬κ°μΈ νμμ€ μ€νμ΄μμ μνλ₯Ό 보거λ, μ λͺ
ν λ μ€ν λμμ μμ¬ν©λλ€.
2μΌμ°¨: λΈλ£¨ν΄λ¦°
μμΉ¨: λΈλ£¨ν΄λ¦° λΈλ¦¬μ§ κ·Όμ²μ μμΉν Smorgasburgμμ λ€μν μμμ μ μ°Ύμ보며 μμν©λλ€.
μ€μ : λΈλ£¨ν΄λ¦° λ°λ¬Όκ΄ (Brooklyn Museum)κ³Ό λ΄μ λ―Έμ κ΄ (New York Transit Museum)μ λ°©λ¬Ένμ¬ μλ¦λ€μ΄ μμ νμ κ°μν©λλ€.
μ μ¬: Brooklyn Heightsμ ν΄λ³κ°μ μμΉν λ μ€ν λμμ λ§μλ μμμ λ¨Ήμ΅λλ€.
μ€ν: μ λͺ
ν λΈλ£¨ν΄λ¦° 체μ΄μ¦ μ¨μ΄μ (Brooklyn Cheese Shop)μμ λ€μν μΉμ¦λ₯Ό μμνκ³ , Williamsburgμ λ
νΉν λ¬Ένλ₯Ό κ²½νν©λλ€.
3μΌμ°¨: νΈμ¦
μμΉ¨: λ΄μ μ§νμ² μ μ΄μ©νμ¬ νΈμ¦λ‘ μ΄λνλ©°, μ λͺ
ν Flushing Meadows-Corona Parkμ μμΉν λ΄μ μΈκ³ λ°λν (World's Fair)θ·‘μ§λ₯Ό λ°©λ¬Έν©λλ€.
μ€μ : μ λμ΄ν°λ μ€νλμ (MetLife Stadium)μ ν¬ν¨ν λ€μν μ€ν¬μΈ μ₯μλ₯Ό νλ°©ν©λλ€.
μ μ¬: νΈμ¦μ μ€κ΅μΈθ‘ (Chinatown)μμ λ§μλ μ€κ΅ μμμ λ¨Ήμ΅λλ€.
μ€ν: μ λͺ
ν λ΄μ μμΏ μ리μ (New York Aquarium)μμ λ€μν ν΄μ μλ¬Όμ λ³Ό μ μμ΅λλ€.
4μΌμ°¨: 맨ν΄νΌ
μμΉ¨: μΌνΈλ΄ νν¬ κ·Όμ²μ λ μ€ν λμμ μμΉ¨ μμ¬λ₯Ό ν©λλ€.
μ€μ : λ΄μ λ―Έμ κ΄ (The Metropolitan Museum of Art)μ λ°©λ¬Ένμ¬ μΈκ³μ μΈ μμ νμ κ°μν©λλ€.
μ μ¬: μ λͺ
ν λ μ€ν λμΈ Eleven Madison Parkμμ μμ¬ν©λλ€.
μ€ν: 맨ν΄νΌμ λ€λ₯Έ μ§μμΌλ‘ μ΄λνμ¬, λ΄μ μμ² (New York City Hall), νμμ€ μ€νμ΄, κ·Έλ¦¬κ³ λΈλ‘λμ¨μ΄ κ·Ήμ₯λ€μ λ°©λ¬Έν©λλ€.
5μΌμ°¨: λ²ν΄λ¦¬
μμΉ¨: λ²ν΄λ¦¬μ μ λͺ
ν λ μ€ν λμμ μμΉ¨ μμ¬λ₯Ό ν©λλ€.
μ€μ : λ΄μ 주립 λνκ΅ λ²ν΄λ¦¬ μΊ νΌμ€λ₯Ό νλ°©νλ©°, λ€μν λ¬Έν μμ€κ³Ό λ°λ¬Όκ΄μ λ°©λ¬Έν©λλ€.
μ μ¬: λ²ν΄λ¦¬μ λ
νΉν μμμ μμ μμ¬ν©λλ€.
μ€ν: λ²ν΄λ¦¬μ ν΄λ³κ°μ μμΉν λ μ€ν λμμ μ λ
μμ¬λ₯Ό ν©λλ€.
μ΄ μΌμ μ λ΄μ μ¬νμ μν κΈ°λ³Έμ μΈ κ³νμ
λλ€. κ° μ§μμ λ€μν κ΄κ΄μ§μ νλμ ν¬ν¨νμ¬, λ΄μμ λ¬Ένλ₯Ό μλ²½νκ² κ²½νν μ μμ΅λλ€. λν, κ°μΈμ μ·¨ν₯κ³Ό κ΄μ¬μ λ°λΌ μ΄ μΌμ μ λ§κ² μμ νκ±°λ μΆκ°ν μλ μμ΅λλ€.
μΌκ°ν¨μ μ€λͺ
μΌκ°ν¨μλ μΌκ°λ²μμ μ¬μ©λλ ν¨μλ‘, κ°λμ ν¬κΈ°μ λ°λΌ μλ‘ λ€λ₯Έ κ°λ€μ μΆλ ₯ν©λλ€. μ£Όλ‘ μ¬λΆλ©΄λ³λ‘ λΆλ₯λλ©°, λ€μκ³Ό κ°μ 6κ°μ§ ν¨μκ° μ‘΄μ¬ν©λλ€.
μ¬μΈν¨μ (sin): μ΄ ν¨μλ ν λ³μ κΈΈμ΄μ λ°λμͺ½ λ³μ κΈΈμ΄λ₯Ό μ΄μ©νμ¬ κ³μ°λ©λλ€. μ¬μΈν¨μμ κ²°κ³Όκ°μ -1μμ 1 μ¬μ΄μ κ°μ
λλ€.
sin(ΞΈ) = λ°λμͺ½ λ³ / κ°λ‘λ³
μ½μ¬μΈν¨μ (cos): μ΄ ν¨μλ ν λ³μ κΈΈμ΄μ κ°μ λ°©ν₯μ μλ λ€λ₯Έ λ³μ κΈΈμ΄λ₯Ό μ΄μ©νμ¬ κ³μ°λ©λλ€. μ½μ¬μΈν¨μμ κ²°κ³Όκ°μ -1μμ 1 μ¬μ΄μ κ°μ
λλ€.
cos(ΞΈ) = κ°μ λ°©ν₯μ λ³ / κ°λ‘λ³
νμ νΈν¨μ (tan): μ΄ ν¨μλ ν λ³μ κΈΈμ΄μ λ°λμͺ½ λ³μ κΈΈμ΄λ₯Ό μ΄μ©νμ¬ κ³μ°λ©λλ€. νμ νΈν¨μμ κ²°κ³Όκ°μ μ€μ κ°μ΄λ 무νλλ‘ λμ¬ μ μμ΅λλ€.
tan(ΞΈ) = λ°λμͺ½ λ³ / κ°μ λ°©ν₯μ λ³
μ ν¨μλ€μ κ°λ ΞΈμ λν΄ λ€μκ³Ό κ°μ΄ μ μλ©λλ€.
μ¬λΆλ©΄ 1 (0Β° β€ ΞΈ < 90Β°): sin(ΞΈ), cos(ΞΈ), tan(ΞΈ) λͺ¨λ μμμ
λλ€.
μ¬λΆλ©΄ 2 (90Β° β€ ΞΈ < 180Β°): sin(ΞΈ), tan(ΞΈ)λ μμ, cos(ΞΈ)λ μμμ
λλ€.
μ¬λΆλ©΄ 3 (180Β° β€ ΞΈ < 270Β°): sin(ΞΈ), cos(ΞΈ), tan(ΞΈ) λͺ¨λ μμμ
λλ€.
μ¬λΆλ©΄ 4 (270Β° β€ ΞΈ < 360Β°): sin(ΞΈ)μ cos(ΞΈ)λ μμ, tan(ΞΈ)λ μμμ
λλ€.
μΌκ°ν¨μμ κ°μ λ€μκ³Ό κ°μ 곡μμ μν΄ κ³μ°λ©λλ€.
sin(ΞΈ + Ο) = sin(ΞΈ)cos(Ο) + cos(ΞΈ)sin(Ο)
cos(ΞΈ + Ο) = cos(ΞΈ)cos(Ο) - sin(ΞΈ)sin(Ο)
tan(ΞΈ + Ο) = (tan(ΞΈ) + tan(Ο)) / (1 - tan(ΞΈ)tan(Ο))
μΌκ°ν¨μλ λ€μν λΆμΌμμ μ¬μ©λ©λλ€. μλ₯Ό λ€μ΄, 물리νμμλ μ΄λλκ³Ό κ°μλμ κ°μ κ°λ
μ κ³μ°ν λ μΌκ°ν¨μλ₯Ό μ¬μ©νκ³ , ν΅κ³νμμλ λ°μ΄ν° λΆν¬λ₯Ό λΆμν λ μΌκ°ν¨μλ₯Ό μ¬μ©ν©λλ€. λν, μ»΄ν¨ν° κ·Έλν½μ€μμλ μΌκ°ν¨μκ° μ€μν μν μ ν©λλ€.
- Downloads last month
- 116
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.