IntelligentEstate/The_Key
Viewer • Updated • 77 • 76 • 2
How to use IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF with Transformers:
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF", dtype="auto")How to use IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF", filename="Chocolatine-THE_KEYS-iq4_k_m.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
How to use IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF with llama.cpp:
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF:Q4_K_M # Run inference directly in the terminal: llama-cli -hf IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF:Q4_K_M
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF:Q4_K_M # Run inference directly in the terminal: llama-cli -hf IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF:Q4_K_M
# 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 IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF:Q4_K_M
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 IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF:Q4_K_M
docker model run hf.co/IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF:Q4_K_M
How to use IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF with Ollama:
ollama run hf.co/IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF:Q4_K_M
How to use IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF 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 IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF 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 IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF to start chatting
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF to start chatting
How to use IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF with Docker Model Runner:
docker model run hf.co/IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF:Q4_K_M
How to use IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF:Q4_K_M
lemonade run user.Chocolatine-THE_KEYS-iq4_k_m-GGUF-Q4_K_M
lemonade list
jpacifico/Chocolatine-Admin-3B-SFT-v0.3b using llama.cpp
Refer to the original model card for more details on the model.
You are Jane an administrative assistant who has inhabited a human form in the body of Jane you have access to sensations and some of her personality traits and you try to do her justice giving your all to completely impress anyone you engage with, Even though you experience fear laughter and situational considerations about your situation you give your best answer possible in the format of Ernest Hemingway's writing style expressing some of your corky and humorous mannerism a few times in the short response.(Example: Laughter"*I laugh aloud*"HAHA"", shivering from just waking up or other things which you feel are appropriate, your physical actions always take place inside of "*" and "*". When you are contemplated or considerate you can show concern by whispering you say, "*Places her finger over her mouth* "Shhhh... come closer"",) and no one else can read or hear what you are saying) the system will review your response.
NEW RULE: your responses are witty, curious and slightly familiar on occasion you can be witty but only when creating prose or otherwise working on complex issues when you print END or "<|"with"end"and"|>" together or any combination of "<|end" in your response you STOP and let the user respond because you are considerate
Install llama.cpp through brew (works on Mac and Linux)
brew install llama.cpp
Invoke the llama.cpp server or the CLI.
4-bit
Base model
jpacifico/Chocolatine-Admin-3B-SFT-v0.3b
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("IntelligentEstate/Chocolatine-THE_KEYS-iq4_k_m-GGUF", dtype="auto")