Instructions to use venkycs/Zyte-1B-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use venkycs/Zyte-1B-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="venkycs/Zyte-1B-gguf",
	filename="zyte-1B-q8_0.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use venkycs/Zyte-1B-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf venkycs/Zyte-1B-gguf:Q8_0
# Run inference directly in the terminal:
llama-cli -hf venkycs/Zyte-1B-gguf:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf venkycs/Zyte-1B-gguf:Q8_0
# Run inference directly in the terminal:
llama-cli -hf venkycs/Zyte-1B-gguf: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 venkycs/Zyte-1B-gguf:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf venkycs/Zyte-1B-gguf: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 venkycs/Zyte-1B-gguf:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf venkycs/Zyte-1B-gguf:Q8_0

Use Docker

docker model run hf.co/venkycs/Zyte-1B-gguf:Q8_0

LM Studio
Jan
Ollama
How to use venkycs/Zyte-1B-gguf with Ollama:
```
ollama run hf.co/venkycs/Zyte-1B-gguf:Q8_0
```

Unsloth Studio

How to use venkycs/Zyte-1B-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 venkycs/Zyte-1B-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 venkycs/Zyte-1B-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for venkycs/Zyte-1B-gguf to start chatting

Docker Model Runner
How to use venkycs/Zyte-1B-gguf with Docker Model Runner:
```
docker model run hf.co/venkycs/Zyte-1B-gguf:Q8_0
```

Lemonade

How to use venkycs/Zyte-1B-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull venkycs/Zyte-1B-gguf:Q8_0

Run and chat with the model

lemonade run user.Zyte-1B-gguf-Q8_0

List all available models

lemonade list

Model Card for Model ID

Here is original model https://huggingface.co/aihub-app/zyte-1B

LM Studio - https://lmstudio.ai (Fully Supported, make sure you select Zypher template format for inference with model.)

We have chosen to upload our model exclusively in the Q8 format, taking into account its compact size. This decision strikes an optimal balance between speed, performance, and memory usage, ensuring efficient and effective utilization of resources.

Model Card Authors

Special thanks to Venkatesh Siddi for his invaluable support in the conversion of the model to the GGUF format. His expertise and assistance have been instrumental in this process. Connect with him on LinkedIn: https://www.linkedin.com/in/venkycs/

Downloads last month: 16

GGUF

Model size

1B params

Architecture

llama

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support