Instructions to use XythicK/Seed-Coder-8B-Reasoning-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use XythicK/Seed-Coder-8B-Reasoning-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="XythicK/Seed-Coder-8B-Reasoning-GGUF",
	filename="seed_coder_8b.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 XythicK/Seed-Coder-8B-Reasoning-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf XythicK/Seed-Coder-8B-Reasoning-GGUF
# Run inference directly in the terminal:
llama-cli -hf XythicK/Seed-Coder-8B-Reasoning-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf XythicK/Seed-Coder-8B-Reasoning-GGUF
# Run inference directly in the terminal:
llama-cli -hf XythicK/Seed-Coder-8B-Reasoning-GGUF

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 XythicK/Seed-Coder-8B-Reasoning-GGUF
# Run inference directly in the terminal:
./llama-cli -hf XythicK/Seed-Coder-8B-Reasoning-GGUF

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 XythicK/Seed-Coder-8B-Reasoning-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf XythicK/Seed-Coder-8B-Reasoning-GGUF

Use Docker

docker model run hf.co/XythicK/Seed-Coder-8B-Reasoning-GGUF

LM Studio
Jan
Ollama
How to use XythicK/Seed-Coder-8B-Reasoning-GGUF with Ollama:
```
ollama run hf.co/XythicK/Seed-Coder-8B-Reasoning-GGUF
```

Unsloth Studio new

How to use XythicK/Seed-Coder-8B-Reasoning-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 XythicK/Seed-Coder-8B-Reasoning-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 XythicK/Seed-Coder-8B-Reasoning-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for XythicK/Seed-Coder-8B-Reasoning-GGUF to start chatting

Docker Model Runner
How to use XythicK/Seed-Coder-8B-Reasoning-GGUF with Docker Model Runner:
```
docker model run hf.co/XythicK/Seed-Coder-8B-Reasoning-GGUF
```

Lemonade

How to use XythicK/Seed-Coder-8B-Reasoning-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull XythicK/Seed-Coder-8B-Reasoning-GGUF

Run and chat with the model

lemonade run user.Seed-Coder-8B-Reasoning-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Seed-Coder-8B-Reasoning-GGUF

This repository contains the Seed-Coder-8B-Reasoning model converted to the GGUF format for use with llama.cpp.

Model Description

Seed-Coder-8B-Reasoning is a large language model developed by ByteDance. It's designed for code generation and understanding, and excels in reasoning tasks. This version has been converted to the GGUF format for compatibility with llama.cpp, making it easier to run locally or on resource-constrained devices.

Intended Uses & Limitations

This model is intended for research and experimentation purposes, particularly in the areas of code generation, code completion, and code understanding.

Limitations: Like any large language model, Seed-Coder-8B-Reasoning may produce incorrect or biased outputs. It's important to critically evaluate its results before using them in production environments.

How to Use

Install llama.cpp: Follow the instructions in the llama.cpp repository to install the necessary tools.
Download the Model: Download the seed_coder_8b.gguf file from this repository.
Run Inference: Use the main binary from llama.cpp to run inference with the model:

bash ./main -m seed_coder_8b.gguf -p "Your prompt here"

Training Data

The original Seed-Coder-8B-Reasoning model was trained on a massive dataset of code and text. Refer to the original model card for more details.

Evaluation Results

[Include any relevant evaluation results or benchmarks here.]

Acknowledgements

Thanks to ByteDance for creating the Seed-Coder-8B-Reasoning model.
Thanks to the llama.cpp community for developing the GGUF format and inference tools.

License

[ MIT]

Downloads last month: 6

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 1 Ask for provider support

Model tree for XythicK/Seed-Coder-8B-Reasoning-GGUF

Base model

ByteDance-Seed/Seed-Coder-8B-Base

Finetuned

ByteDance-Seed/Seed-Coder-8B-Reasoning

Quantized

(16)

this model