Instructions to use tensorblock/zeta-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/zeta-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/zeta-GGUF",
	filename="zeta-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 tensorblock/zeta-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/zeta-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/zeta-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/zeta-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/zeta-GGUF: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 tensorblock/zeta-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/zeta-GGUF: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 tensorblock/zeta-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/zeta-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/zeta-GGUF:Q2_K

LM Studio
Jan
Ollama
How to use tensorblock/zeta-GGUF with Ollama:
```
ollama run hf.co/tensorblock/zeta-GGUF:Q2_K
```

Unsloth Studio new

How to use tensorblock/zeta-GGUF 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 tensorblock/zeta-GGUF 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 tensorblock/zeta-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tensorblock/zeta-GGUF to start chatting

Docker Model Runner
How to use tensorblock/zeta-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/zeta-GGUF:Q2_K
```

Lemonade

How to use tensorblock/zeta-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/zeta-GGUF:Q2_K

Run and chat with the model

lemonade run user.zeta-GGUF-Q2_K

List all available models

lemonade list

morriszms commited on Jan 27

Commit

5b4096d

verified ·

1 Parent(s): 65399a7

Keep Q2_K/Q3_K_M gguf only

Browse files

Files changed (10) hide show

zeta-Q3_K_L.gguf +0 -3
zeta-Q3_K_S.gguf +0 -3
zeta-Q4_0.gguf +0 -3
zeta-Q4_K_M.gguf +0 -3
zeta-Q4_K_S.gguf +0 -3
zeta-Q5_0.gguf +0 -3
zeta-Q5_K_M.gguf +0 -3
zeta-Q5_K_S.gguf +0 -3
zeta-Q6_K.gguf +0 -3
zeta-Q8_0.gguf +0 -3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:610941425ece5ef7b263e6ee55415ac4db225793dd5994bf904c55bdb474f15f
-size 4088456928

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:416d6604d9acf63db1b28b1b992c5824bb8b7048fdb8f253b43b4a41c842a0d7
-size 3492366048

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e8749ff6a4297fc3635cf380dd77f0a463400e87efa7dad8ae5f54f7ae5c1188
-size 4431388384

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c2b8f26a74cd369799ad4e8bca52b516f95fddccb7bad3070941061b42eac3d6
-size 4683071200

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6ca56e4779f1cdd4ef5111611e388daa1ea18b9a701ed8b06d9967942d56a869
-size 4457766624