Instructions to use Shriramnag/Shiv-AI-Song-Generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Shriramnag/Shiv-AI-Song-Generator with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Shriramnag/Shiv-AI-Song-Generator",
	filename="Shiv-AI-Song-Model.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 Shriramnag/Shiv-AI-Song-Generator with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Shriramnag/Shiv-AI-Song-Generator
# Run inference directly in the terminal:
llama-cli -hf Shriramnag/Shiv-AI-Song-Generator

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Shriramnag/Shiv-AI-Song-Generator
# Run inference directly in the terminal:
llama-cli -hf Shriramnag/Shiv-AI-Song-Generator

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 Shriramnag/Shiv-AI-Song-Generator
# Run inference directly in the terminal:
./llama-cli -hf Shriramnag/Shiv-AI-Song-Generator

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 Shriramnag/Shiv-AI-Song-Generator
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Shriramnag/Shiv-AI-Song-Generator

Use Docker

docker model run hf.co/Shriramnag/Shiv-AI-Song-Generator

LM Studio
Jan
Ollama
How to use Shriramnag/Shiv-AI-Song-Generator with Ollama:
```
ollama run hf.co/Shriramnag/Shiv-AI-Song-Generator
```

Unsloth Studio new

How to use Shriramnag/Shiv-AI-Song-Generator 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 Shriramnag/Shiv-AI-Song-Generator 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 Shriramnag/Shiv-AI-Song-Generator to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Shriramnag/Shiv-AI-Song-Generator to start chatting

Docker Model Runner
How to use Shriramnag/Shiv-AI-Song-Generator with Docker Model Runner:
```
docker model run hf.co/Shriramnag/Shiv-AI-Song-Generator
```

Lemonade

How to use Shriramnag/Shiv-AI-Song-Generator with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Shriramnag/Shiv-AI-Song-Generator

Run and chat with the model

lemonade run user.Shiv-AI-Song-Generator-{{QUANT_TAG}}

List all available models

lemonade list

Shriramnag commited on Mar 20

Commit

a32fb26

verified ·

1 Parent(s): e0819f0

Upload advanced_system/video_engine/requirements.txt with huggingface_hub

Browse files

Files changed (1) hide show

advanced_system/video_engine/requirements.txt +92 -0

advanced_system/video_engine/requirements.txt ADDED Viewed

	@@ -0,0 +1,92 @@

+--extra-index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/ort-cuda-13-nightly/pypi/simple/
+mmgp==3.7.6
+# Core AI stack
+diffusers==0.36.0
+transformers==4.54.0 #4.53.1
+tokenizers>=0.20.3
+accelerate>=1.1.1
+tqdm
+imageio
+imageio-ffmpeg
+einops
+sentencepiece
+open_clip_torch>=2.29.0
+numpy==2.1.2
+num2words==0.5.14
+# Video & media
+moviepy==1.0.3
+av
+ffmpeg-python
+pygame>=2.1.0
+sounddevice>=0.4.0
+soundfile
+mutagen
+pyloudnorm
+librosa==0.11.0
+speechbrain==1.0.3
+audio-separator==0.36.1
+pyannote.audio==3.3.2
+torchcodec
+# UI & interaction
+gradio==5.29.0
+dashscope
+loguru
+s3tokenizer
+conformer==0.3.2
+spacy_pkuseg
+spacy
+gradio_rangeslider
+# Vision & segmentation
+opencv-python>=4.12.0.88
+segment-anything
+rembg[gpu]==2.0.65
+onnxruntime-gpu==1.22.0; python_version < "3.11"
+onnxruntime-gpu==1.25.0.dev20260210001; python_version >= "3.11"
+decord
+timm
+insightface @ https://github.com/deepbeepmeep/insightface/releases/download/insightface/insightface-0.7.3-cp310-cp310-win_amd64.whl ; sys_platform == "win32" and python_version == "3.10"
+insightface @ https://github.com/deepbeepmeep/insightface/releases/download/insightface/insightface-0.7.3-cp311-cp311-win_amd64.whl ; sys_platform == "win32" and python_version == "3.11"
+insightface @ https://github.com/deepbeepmeep/insightface/releases/download/insightface/insightface-0.7.3-cp312-cp312-win_amd64.whl ; sys_platform == "win32" and python_version == "3.12"
+insightface==0.7.3 ; sys_platform == "linux"
+facexlib==0.3.0
+taichi
+vector_quantize_pytorch==1.27.19
+# chumpy wheel hosted on GitHub to avoid sdist build isolation issue
+chumpy @ https://github.com/deepbeepmeep/chumpy/releases/download/v0.71/chumpy-0.71-py3-none-any.whl
+smplfitter @ https://github.com/deepbeepmeep/smplfitter/releases/download/v0.2.10/smplfitter-0.2.10-py3-none-any.whl
+# Config & orchestration
+omegaconf
+hydra-core
+easydict
+pydantic==2.10.6
+# Math & modeling
+torchdiffeq>=0.2.5
+tensordict>=0.6.1
+peft==0.17.0 # 0.15.0
+vector-quantize-pytorch
+matplotlib
+gguf==0.17.1
+flash-linear-attention==0.4.1
+# Utilities
+ftfy
+piexif
+nvidia-ml-py
+misaki
+gitdb==4.0.12
+gitpython==3.1.45
+stringzilla==4.0.14
+xxhash
+munch
+wetext==0.1.2
+# Optional / commented out
+# transformers==4.46.3  # for llamallava pre-patch
+# rembg==2.0.65         # non-GPU fallback
+# huggingface_hub[hf_xet]  # slows down everything