Instructions to use JoPmt/DeepMeeker-7B-Base-Ties-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JoPmt/DeepMeeker-7B-Base-Ties-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="JoPmt/DeepMeeker-7B-Base-Ties-GGUF",
	filename="deepmeeker-7b-base-ties.Q4_K_M.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 JoPmt/DeepMeeker-7B-Base-Ties-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf JoPmt/DeepMeeker-7B-Base-Ties-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf JoPmt/DeepMeeker-7B-Base-Ties-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf JoPmt/DeepMeeker-7B-Base-Ties-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf JoPmt/DeepMeeker-7B-Base-Ties-GGUF:Q4_K_M

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 JoPmt/DeepMeeker-7B-Base-Ties-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf JoPmt/DeepMeeker-7B-Base-Ties-GGUF:Q4_K_M

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 JoPmt/DeepMeeker-7B-Base-Ties-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf JoPmt/DeepMeeker-7B-Base-Ties-GGUF:Q4_K_M

Use Docker

docker model run hf.co/JoPmt/DeepMeeker-7B-Base-Ties-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use JoPmt/DeepMeeker-7B-Base-Ties-GGUF with Ollama:
```
ollama run hf.co/JoPmt/DeepMeeker-7B-Base-Ties-GGUF:Q4_K_M
```

Unsloth Studio new

How to use JoPmt/DeepMeeker-7B-Base-Ties-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 JoPmt/DeepMeeker-7B-Base-Ties-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 JoPmt/DeepMeeker-7B-Base-Ties-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for JoPmt/DeepMeeker-7B-Base-Ties-GGUF to start chatting

Docker Model Runner
How to use JoPmt/DeepMeeker-7B-Base-Ties-GGUF with Docker Model Runner:
```
docker model run hf.co/JoPmt/DeepMeeker-7B-Base-Ties-GGUF:Q4_K_M
```

Lemonade

How to use JoPmt/DeepMeeker-7B-Base-Ties-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull JoPmt/DeepMeeker-7B-Base-Ties-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.DeepMeeker-7B-Base-Ties-GGUF-Q4_K_M

List all available models

lemonade list

DeepMeeker-7B-Base-Ties

DeepMeeker-7B-Base-Ties is a merge of the following models using LazyMergekit:

🧩 Configuration

models:
  - model: ise-uiuc/Magicoder-DS-6.7B
    parameters:
      weight: 1
      density: 1
  - model: deepseek-ai/deepseek-coder-6.7b-base
    parameters:
      weight: 1
      density: 1
merge_method: ties
base_model: ise-uiuc/Magicoder-DS-6.7B
parameters:
  weight: 1
  density: 1
  normalize: true
  int8_mask: false
dtype: float16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "JoPmt/DeepMeeker-7B-Base-Ties"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Downloads last month: 5

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for JoPmt/DeepMeeker-7B-Base-Ties-GGUF

deepseek-ai/deepseek-coder-6.7b-base

ise-uiuc/Magicoder-DS-6.7B

Merge model

this model