kishida/CompileError-Java-JP-cheerful
Viewer • Updated • 51.4k • 23 • 1
How to use kishida/java-error-explainer-jp-cheerful-ministral3-3b with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="kishida/java-error-explainer-jp-cheerful-ministral3-3b", filename="java-error-explainer-jp-cheerful-ministral3-3b.Q8_0.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
How to use kishida/java-error-explainer-jp-cheerful-ministral3-3b with llama.cpp:
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf kishida/java-error-explainer-jp-cheerful-ministral3-3b:Q8_0 # Run inference directly in the terminal: llama cli -hf kishida/java-error-explainer-jp-cheerful-ministral3-3b:Q8_0
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf kishida/java-error-explainer-jp-cheerful-ministral3-3b:Q8_0 # Run inference directly in the terminal: llama cli -hf kishida/java-error-explainer-jp-cheerful-ministral3-3b:Q8_0
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf kishida/java-error-explainer-jp-cheerful-ministral3-3b:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf kishida/java-error-explainer-jp-cheerful-ministral3-3b:Q8_0
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf kishida/java-error-explainer-jp-cheerful-ministral3-3b:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf kishida/java-error-explainer-jp-cheerful-ministral3-3b:Q8_0
docker model run hf.co/kishida/java-error-explainer-jp-cheerful-ministral3-3b:Q8_0
How to use kishida/java-error-explainer-jp-cheerful-ministral3-3b with Ollama:
ollama run hf.co/kishida/java-error-explainer-jp-cheerful-ministral3-3b:Q8_0
How to use kishida/java-error-explainer-jp-cheerful-ministral3-3b with Unsloth Studio:
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for kishida/java-error-explainer-jp-cheerful-ministral3-3b to start chatting
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for kishida/java-error-explainer-jp-cheerful-ministral3-3b to start chatting
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for kishida/java-error-explainer-jp-cheerful-ministral3-3b to start chatting
How to use kishida/java-error-explainer-jp-cheerful-ministral3-3b with Pi:
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf kishida/java-error-explainer-jp-cheerful-ministral3-3b:Q8_0
# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
"providers": {
"llama-cpp": {
"baseUrl": "http://localhost:8080/v1",
"api": "openai-completions",
"apiKey": "none",
"models": [
{
"id": "kishida/java-error-explainer-jp-cheerful-ministral3-3b:Q8_0"
}
]
}
}
}# Start Pi in your project directory: pi
How to use kishida/java-error-explainer-jp-cheerful-ministral3-3b with Hermes Agent:
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf kishida/java-error-explainer-jp-cheerful-ministral3-3b:Q8_0
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default kishida/java-error-explainer-jp-cheerful-ministral3-3b:Q8_0
hermes
How to use kishida/java-error-explainer-jp-cheerful-ministral3-3b with Docker Model Runner:
docker model run hf.co/kishida/java-error-explainer-jp-cheerful-ministral3-3b:Q8_0
How to use kishida/java-error-explainer-jp-cheerful-ministral3-3b with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull kishida/java-error-explainer-jp-cheerful-ministral3-3b:Q8_0
lemonade run user.java-error-explainer-jp-cheerful-ministral3-3b-Q8_0
lemonade list
llm.create_chat_completion(
messages = "No input example has been defined for this model task."
)Javaのコンパイルエラーを明るく解説します。
まだ壊れています。
from llama_cpp import Llama
# model load
base_model = "ministral3-3b"
quant = "Q8_0"
llm = Llama.from_pretrained(
repo_id=f"kishida/java-error-explainer-jp-cheerful-{base_model}",
filename=f"java-error-explainer-jp-cheerful-{base_model}.{quant}.gguf",
seed=1234,
)
# streaming
def chat(msg):
res = llm.create_chat_completion(
messages=[
{"role": "system", "content": "You are a Java compile error explainer."},
{"role": "user", "content": msg},
],
temperature=0.7,
)
return res["choices"][0]["message"]["content"]
source = """
void main() {
IO.println(LocalDateTime.now());
IO.println("Hello")
}
"""
error = """
HelloWithError.java:3: エラー: ';'がありません
IO.println("Hello")
^
エラー1個
"""
template = """
source:
{}
compile error:
{}
"""
print("source + error")
print(chat(template.format(source, error)))
"""
おっと、コードの行末にセミンカンのないからエラーになっちゃったね!Javaでは命令や文を終える時には「;」とせんせんなんか。この行のセミンは欠けてるから、コンパイダーさんが「;」って言ってるんだよ!行末にセニトンの付き忘れが大いな事!
"""
print("error only")
print(chat(error))
"""
おっと、コードの行末にセミンカンのないからエラーになっちゃったね!Javaでは命令や文を終える時には「;」とせんせんなんか。この行のセミンは欠けてるから、コンパイダーさんが「;」って言ってるんだよ!行末にセニトンの付き忘れが大いな事!
"""
# 壊れてる?
8-bit
Base model
mistralai/Ministral-3-3B-Base-2512
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="kishida/java-error-explainer-jp-cheerful-ministral3-3b", filename="java-error-explainer-jp-cheerful-ministral3-3b.Q8_0.gguf", )