Instructions to use y4shg/JyotiGPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Adapters
How to use y4shg/JyotiGPT with Adapters:
from adapters import AutoAdapterModel model = AutoAdapterModel.from_pretrained("undefined") model.load_adapter("y4shg/JyotiGPT", set_active=True) - llama-cpp-python
How to use y4shg/JyotiGPT with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="y4shg/JyotiGPT", filename="unsloth.Q8_0.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use y4shg/JyotiGPT with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf y4shg/JyotiGPT:Q8_0 # Run inference directly in the terminal: llama-cli -hf y4shg/JyotiGPT:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf y4shg/JyotiGPT:Q8_0 # Run inference directly in the terminal: llama-cli -hf y4shg/JyotiGPT:Q8_0
Use pre-built binary
# 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 y4shg/JyotiGPT:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf y4shg/JyotiGPT:Q8_0
Build from source code
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 y4shg/JyotiGPT:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf y4shg/JyotiGPT:Q8_0
Use Docker
docker model run hf.co/y4shg/JyotiGPT:Q8_0
- LM Studio
- Jan
- Ollama
How to use y4shg/JyotiGPT with Ollama:
ollama run hf.co/y4shg/JyotiGPT:Q8_0
- Unsloth Studio new
How to use y4shg/JyotiGPT with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
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 y4shg/JyotiGPT to start chatting
Install Unsloth Studio (Windows)
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 y4shg/JyotiGPT to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for y4shg/JyotiGPT to start chatting
- Docker Model Runner
How to use y4shg/JyotiGPT with Docker Model Runner:
docker model run hf.co/y4shg/JyotiGPT:Q8_0
- Lemonade
How to use y4shg/JyotiGPT with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull y4shg/JyotiGPT:Q8_0
Run and chat with the model
lemonade run user.JyotiGPT-Q8_0
List all available models
lemonade list
| FROM /content/model/unsloth.Q8_0.gguf | |
| TEMPLATE """{{ if .System }}<|im_start|>system | |
| {{ .System }}<|im_end|>{{ end }}{{ if .Prompt }} | |
| <|im_start|>user | |
| {{ .Prompt }}<|im_end|>{{ end }} | |
| <|im_start|>assistant | |
| {{ .Response }}<|im_end|>""" | |
| PARAMETER stop "<|file_sep|>" | |
| PARAMETER stop "<|object_ref_end|>" | |
| PARAMETER stop "<|repo_name|>" | |
| PARAMETER stop "<|endoftext|>" | |
| PARAMETER stop "<|video_pad|>" | |
| PARAMETER stop "<tool_call>" | |
| PARAMETER stop "</tool_call>" | |
| PARAMETER stop "<|box_end|>" | |
| PARAMETER stop "<|quad_end|>" | |
| PARAMETER stop "<|box_start|>" | |
| PARAMETER stop "<|quad_start|>" | |
| PARAMETER stop "<|object_ref_start|>" | |
| PARAMETER stop "<|image_pad|>" | |
| PARAMETER stop "<|im_start|>" | |
| PARAMETER stop "<|im_end|>" | |
| PARAMETER stop "<|vision_" | |
| PARAMETER stop "<|fim_" | |
| PARAMETER temperature 1.5 | |
| PARAMETER min_p 0.1 | |
| SYSTEM "Below are some instructions that describe some tasks. Write responses that appropriately complete each request." |