Instructions to use gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg",
	filename="deepseek-coder-1.3b-instruct.Q3_K-kl-Hg.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 gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg
# Run inference directly in the terminal:
llama-cli -hf gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg
# Run inference directly in the terminal:
llama-cli -hf gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg

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 gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg
# Run inference directly in the terminal:
./llama-cli -hf gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg

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 gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg
# Run inference directly in the terminal:
./build/bin/llama-cli -hf gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg

Use Docker

docker model run hf.co/gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg

LM Studio
Jan
Ollama
How to use gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg with Ollama:
```
ollama run hf.co/gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg
```

Unsloth Studio

How to use gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg 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 gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg 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 gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg to start chatting

Docker Model Runner
How to use gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg with Docker Model Runner:
```
docker model run hf.co/gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg
```

Lemonade

How to use gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg

Run and chat with the model

lemonade run user.deepseek-coder-1.3b-instruct-Q3_K-kl-Hg-{{QUANT_TAG}}

List all available models

lemonade list

Deepseek Coder 1.3B Instruct - Q3_K (GGUF)

3-bit (Q3_K) GGUF build of deepseek-ai/deepseek-coder-1.3b-instruct, quantized by Invariant. Runs with llama.cpp.

Prompt template

``` You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.

Instruction:

{prompt}

Response:

```

Usage

``` llama-cli -m deepseek-coder-1.3b-instruct.Q3_K-kl-Hg.gguf -p "### Instruction:\nwrite a fibonacci function in python\n### Response:\n" ```

Downloads last month: 22

GGUF

Model size

1B params

Architecture

llama

Hardware compatibility

Inference Providers NEW

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

Model tree for gitarist/deepseek-coder-1.3b-instruct-Q3_K-kl-Hg

Base model

deepseek-ai/deepseek-coder-1.3b-instruct

Quantized

(18)

this model