Instructions to use isfs/wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use isfs/wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="isfs/wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp",
	filename="Wan2.2-TI2V-5B-Q2_K.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use isfs/wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf isfs/wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp:Q2_K
# Run inference directly in the terminal:
llama-cli -hf isfs/wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf isfs/wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp:Q2_K
# Run inference directly in the terminal:
llama-cli -hf isfs/wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp:Q2_K

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 isfs/wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf isfs/wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp:Q2_K

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 isfs/wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf isfs/wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp:Q2_K

Use Docker

docker model run hf.co/isfs/wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp:Q2_K

LM Studio
Jan
Ollama
How to use isfs/wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp with Ollama:
```
ollama run hf.co/isfs/wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp:Q2_K
```

Unsloth Studio new

How to use isfs/wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp 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 isfs/wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp 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 isfs/wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for isfs/wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp to start chatting

Docker Model Runner
How to use isfs/wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp with Docker Model Runner:
```
docker model run hf.co/isfs/wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp:Q2_K
```

Lemonade

How to use isfs/wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull isfs/wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp:Q2_K

Run and chat with the model

lemonade run user.wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp-Q2_K

List all available models

lemonade list

wan-2.2-5b-ti2v-gguf-stable-diffusion-cpp / stable-diffusion-cpp-nvidia /CMakeFiles /3.31.10 /CompilerIdCUDA /tmp /a_dlink.fatbin.c

isfs

Upload folder using huggingface_hub

a1663c1 verified 2 months ago

raw

history blame contribute delete

3.19 kB

	#ifndef __SKIP_INTERNAL_FATBINARY_HEADERS
	#include "fatbinary_section.h"
	#endif
	#define __CUDAFATBINSECTION ".nvFatBinSegment"
	#define __CUDAFATBINDATASECTION ".nv_fatbin"
	asm(
	".section .nv_fatbin, \"a\"\n"
	".align 8\n"
	"fatbinData:\n"
	".quad 0x00100001ba55ed50,0x00000000000003a8,0x0000004001010002,0x0000000000000368\n"
	".quad 0x0000000000000000,0x0000003400010007,0x0000000000000000,0x0000000000000011\n"
	".quad 0x0000000000000000,0x0000000000000000,0x33010102464c457f,0x0000000000000007\n"
	".quad 0x0000007d00be0002,0x0000000000000000,0x00000000000002f8,0x0000000000000178\n"
	".quad 0x0038004000340534,0x0001000600400002,0x7472747368732e00,0x747274732e006261\n"
	".quad 0x746d79732e006261,0x746d79732e006261,0x78646e68735f6261,0x666e692e766e2e00\n"
	".quad 0x61632e766e2e006f,0x0068706172676c6c,0x746f72702e766e2e,0x6e2e00657079746f\n"
	".quad 0x63612e6c65722e76,0x732e00006e6f6974,0x0062617472747368,0x006261747274732e\n"
	".quad 0x006261746d79732e,0x5f6261746d79732e,0x6e2e0078646e6873,0x2e006f666e692e76\n"
	".quad 0x676c6c61632e766e,0x766e2e0068706172,0x79746f746f72702e,0x722e766e2e006570\n"
	".quad 0x6f697463612e6c65,0x000000000000006e,0x0000000000000000,0x0000000000000000\n"
	".quad 0x0000000000000000,0x0004000300000032,0x0000000000000000,0x0000000000000000\n"
	".quad 0x000500030000004e,0x0000000000000000,0x0000000000000000,0xffffffff00000000\n"
	".quad 0xfffffffe00000000,0xfffffffd00000000,0xfffffffc00000000,0x0000000000000073\n"
	".quad 0x3605002511000000,0x0000000000000000,0x0000000000000000,0x0000000000000000\n"
	".quad 0x0000000000000000,0x0000000000000000,0x0000000000000000,0x0000000000000000\n"
	".quad 0x0000000000000000,0x0000000300000001,0x0000000000000000,0x0000000000000000\n"
	".quad 0x0000000000000040,0x000000000000005d,0x0000000000000000,0x0000000000000001\n"
	".quad 0x0000000000000000,0x000000030000000b,0x0000000000000000,0x0000000000000000\n"
	".quad 0x000000000000009d,0x000000000000005d,0x0000000000000000,0x0000000000000001\n"
	".quad 0x0000000000000000,0x0000000200000013,0x0000000000000000,0x0000000000000000\n"
	".quad 0x0000000000000100,0x0000000000000048,0x0000000300000002,0x0000000000000008\n"
	".quad 0x0000000000000018,0x7000000100000032,0x0000000000000000,0x0000000000000000\n"
	".quad 0x0000000000000148,0x0000000000000020,0x0000000000000003,0x0000000000000004\n"
	".quad 0x0000000000000008,0x7000000b0000004e,0x0000000000000000,0x0000000000000000\n"
	".quad 0x0000000000000168,0x0000000000000010,0x0000000000000000,0x0000000000000008\n"
	".quad 0x0000000000000008,0x0000000500000006,0x00000000000002f8,0x0000000000000000\n"
	".quad 0x0000000000000000,0x0000000000000070,0x0000000000000070,0x0000000000000008\n"
	".quad 0x0000000500000001,0x00000000000002f8,0x0000000000000000,0x0000000000000000\n"
	".quad 0x0000000000000070, 0x0000000000000070, 0x0000000000000008\n"
	".text\n");
	#ifdef __cplusplus
	extern "C" {
	#endif
	extern const unsigned long long fatbinData[119];
	#ifdef __cplusplus
	}
	#endif
	#ifdef __cplusplus
	extern "C" {
	#endif
	static const __fatBinC_Wrapper_t __fatDeviceText __attribute__ ((aligned (8))) __attribute__ ((section (__CUDAFATBINSECTION)))=
	{ 0x466243b1, 2, fatbinData, (void**)__cudaPrelinkedFatbins };
	#ifdef __cplusplus
	}
	#endif