Instructions to use TobDeBer/myContainers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TobDeBer/myContainers with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TobDeBer/myContainers",
	filename="arco_BE8.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 TobDeBer/myContainers with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TobDeBer/myContainers
# Run inference directly in the terminal:
llama-cli -hf TobDeBer/myContainers

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TobDeBer/myContainers
# Run inference directly in the terminal:
llama-cli -hf TobDeBer/myContainers

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 TobDeBer/myContainers
# Run inference directly in the terminal:
./llama-cli -hf TobDeBer/myContainers

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 TobDeBer/myContainers
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TobDeBer/myContainers

Use Docker

docker model run hf.co/TobDeBer/myContainers

LM Studio
Jan
Ollama
How to use TobDeBer/myContainers with Ollama:
```
ollama run hf.co/TobDeBer/myContainers
```

Unsloth Studio new

How to use TobDeBer/myContainers 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 TobDeBer/myContainers 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 TobDeBer/myContainers to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TobDeBer/myContainers to start chatting

Docker Model Runner
How to use TobDeBer/myContainers with Docker Model Runner:
```
docker model run hf.co/TobDeBer/myContainers
```

Lemonade

How to use TobDeBer/myContainers with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TobDeBer/myContainers

Run and chat with the model

lemonade run user.myContainers-{{QUANT_TAG}}

List all available models

lemonade list

TobDeBer commited on Sep 1, 2024

Commit

19822a8

1 Parent(s): 52af04b

normal files

Browse files

Files changed (6) hide show

.gitattributes +3 -0
README.md +13 -0
build_diffusion.sh +5 -0
build_gguf.sh +5 -0
diffusion/Dockerfile +6 -0
gguf/Dockerfile +10 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+llama-cli filter=lfs diff=lfs merge=lfs -text
+llama-server filter=lfs diff=lfs merge=lfs -text
+sd_cuda filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,13 @@

+# Container Repository for CPU adaptations of Inference code
+## Variants
+### CPUdiffusion
+- inference diffusion models on CPU
+- include CUDAonCPU stack
+### CPUgguf
+- inference gguf models on CPU
+- include GUI libraries

build_diffusion.sh ADDED Viewed

	@@ -0,0 +1,5 @@

+podman build --squash-all --tag bookworm:diffusion diffusion
+podman image prune -f
+podman save localhost/bookworm:diffusion >test.tar
+#time xz -9e -T0 test.tar

build_gguf.sh ADDED Viewed

	@@ -0,0 +1,5 @@

+podman build --squash-all --tag bookworm:gguf gguf
+podman image prune -f
+podman save localhost/bookworm:gguf >gguf.tar
+time xz -6 -T0 gguf.tar

diffusion/Dockerfile ADDED Viewed

	@@ -0,0 +1,6 @@

+FROM debian:bookworm-slim
+RUN apt-get update && apt-get upgrade
+RUN apt-get install -y git git-lfs pip cmake python3
+CMD ["sleep", " infinity"]

gguf/Dockerfile ADDED Viewed

	@@ -0,0 +1,10 @@

+FROM debian:bookworm-slim
+RUN apt-get update && apt-get upgrade
+RUN apt-get install -y git git-lfs pip cmake python3
+RUN git clone https://github.com/ggerganov/llama.cpp.git
+RUN cd llama.cpp && make -j 32 llama-server
+RUN cp llama.cpp/llama-server .
+RUN rm -rf llama.cpp/
+CMD ["sleep", " infinity"]