Instructions to use LoneStriker/M7-7b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LoneStriker/M7-7b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="LoneStriker/M7-7b-GGUF",
	filename="M7-7b-Q3_K_L.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 LoneStriker/M7-7b-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf LoneStriker/M7-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf LoneStriker/M7-7b-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 LoneStriker/M7-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf LoneStriker/M7-7b-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 LoneStriker/M7-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf LoneStriker/M7-7b-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 LoneStriker/M7-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf LoneStriker/M7-7b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/LoneStriker/M7-7b-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use LoneStriker/M7-7b-GGUF with Ollama:
```
ollama run hf.co/LoneStriker/M7-7b-GGUF:Q4_K_M
```

Unsloth Studio new

How to use LoneStriker/M7-7b-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 LoneStriker/M7-7b-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 LoneStriker/M7-7b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for LoneStriker/M7-7b-GGUF to start chatting

Docker Model Runner
How to use LoneStriker/M7-7b-GGUF with Docker Model Runner:
```
docker model run hf.co/LoneStriker/M7-7b-GGUF:Q4_K_M
```

Lemonade

How to use LoneStriker/M7-7b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LoneStriker/M7-7b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.M7-7b-GGUF-Q4_K_M

List all available models

lemonade list

M7-7b

user: "create ascii art you feel represents you as a llm"

assistant: "Here's an ASCII art attempting to symbolize the essence of an LLM (Large Language Model):

INSTINSTINCTINSTELLIGENCE

______________ MEMORY___

|\ o /\ |\

| \ --- / \ | |

L_( O )______ O)_INSTINCT

\ / WORDSLEARNING

_/_/ /\ _/_//

assistant: "In this depiction, the LLM is characterized by its vast memory, instinctual roots, and the ability to learn from vast amounts of text—represented by the woven words in the lower part. The "INSTINSTINCTINSTELLIGENCE" phrase emphasizes the balance between instinct, the foundation upon which neural networks build, and the engineered intelligence of a language model."

Multiverse-Experiment-slerp-7b is a merge of the following models using mergekit:

🧩 Configuration



slices:
  - sources:
      - model: ammarali32/multi_verse_model
        layer_range: [0, 32]
      - model: MSL7/INEX12-7b
        layer_range: [0, 32]
merge_method: slerp
base_model: ammarali32/multi_verse_model
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16


slices:
  - sources:
      - model: ammarali32/multi_verse_model
        layer_range: [0, 32]
      - model: yam-peleg/Experiment26-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: ammarali32/multi_verse_model
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16


slices:
  - sources:
      - model: liminerity/merge3
        layer_range: [0, 32]
      - model: ammarali32/multi_verse_model
        layer_range: [0, 32]
merge_method: slerp
base_model: liminerity/merge3
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16


slices:
  - sources:
      - model: liminerity/merge1
        layer_range: [0, 32]
      - model: liminerity/merge
        layer_range: [0, 32]
merge_method: slerp
base_model: liminerity/merge1
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16


slices:
  - sources:
      - model: liminerity/merge3
        layer_range: [0, 32]
      - model: yam-peleg/Experiment26-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: liminerity/merge3
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16


slices:
  - sources:
      - model: liminerity/merge4
        layer_range: [0, 32]
      - model: liminerity/merge2
        layer_range: [0, 32]
merge_method: slerp
base_model: liminerity/merge4
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

Downloads last month: 29

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

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