Instructions to use RichardErkhov/SzilviaB_-_Triple-Moist-Theia-21B-SKEWED-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use RichardErkhov/SzilviaB_-_Triple-Moist-Theia-21B-SKEWED-gguf with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RichardErkhov/SzilviaB_-_Triple-Moist-Theia-21B-SKEWED-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/SzilviaB_-_Triple-Moist-Theia-21B-SKEWED-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RichardErkhov/SzilviaB_-_Triple-Moist-Theia-21B-SKEWED-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/SzilviaB_-_Triple-Moist-Theia-21B-SKEWED-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 RichardErkhov/SzilviaB_-_Triple-Moist-Theia-21B-SKEWED-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RichardErkhov/SzilviaB_-_Triple-Moist-Theia-21B-SKEWED-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 RichardErkhov/SzilviaB_-_Triple-Moist-Theia-21B-SKEWED-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RichardErkhov/SzilviaB_-_Triple-Moist-Theia-21B-SKEWED-gguf:Q4_K_M

Use Docker

docker model run hf.co/RichardErkhov/SzilviaB_-_Triple-Moist-Theia-21B-SKEWED-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use RichardErkhov/SzilviaB_-_Triple-Moist-Theia-21B-SKEWED-gguf with Ollama:
```
ollama run hf.co/RichardErkhov/SzilviaB_-_Triple-Moist-Theia-21B-SKEWED-gguf:Q4_K_M
```

Unsloth Studio

How to use RichardErkhov/SzilviaB_-_Triple-Moist-Theia-21B-SKEWED-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 RichardErkhov/SzilviaB_-_Triple-Moist-Theia-21B-SKEWED-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 RichardErkhov/SzilviaB_-_Triple-Moist-Theia-21B-SKEWED-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RichardErkhov/SzilviaB_-_Triple-Moist-Theia-21B-SKEWED-gguf to start chatting

Docker Model Runner
How to use RichardErkhov/SzilviaB_-_Triple-Moist-Theia-21B-SKEWED-gguf with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/SzilviaB_-_Triple-Moist-Theia-21B-SKEWED-gguf:Q4_K_M
```

Lemonade

How to use RichardErkhov/SzilviaB_-_Triple-Moist-Theia-21B-SKEWED-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RichardErkhov/SzilviaB_-_Triple-Moist-Theia-21B-SKEWED-gguf:Q4_K_M

Run and chat with the model

lemonade run user.SzilviaB_-_Triple-Moist-Theia-21B-SKEWED-gguf-Q4_K_M

List all available models

lemonade list

Atomic Chat

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Triple-Moist-Theia-21B-SKEWED - GGUF

Model creator: https://huggingface.co/SzilviaB/
Original model: https://huggingface.co/SzilviaB/Triple-Moist-Theia-21B-SKEWED/

Name	Quant method	Size
Triple-Moist-Theia-21B-SKEWED.Q2_K.gguf	Q2_K	7.26GB
Triple-Moist-Theia-21B-SKEWED.Q3_K_S.gguf	Q3_K_S	8.43GB
Triple-Moist-Theia-21B-SKEWED.Q3_K.gguf	Q3_K	9.33GB
Triple-Moist-Theia-21B-SKEWED.Q3_K_M.gguf	Q3_K_M	9.33GB
Triple-Moist-Theia-21B-SKEWED.Q3_K_L.gguf	Q3_K_L	10.1GB
Triple-Moist-Theia-21B-SKEWED.IQ4_XS.gguf	IQ4_XS	10.44GB
Triple-Moist-Theia-21B-SKEWED.Q4_0.gguf	Q4_0	10.87GB
Triple-Moist-Theia-21B-SKEWED.IQ4_NL.gguf	IQ4_NL	10.98GB
Triple-Moist-Theia-21B-SKEWED.Q4_K_S.gguf	Q4_K_S	10.94GB
Triple-Moist-Theia-21B-SKEWED.Q4_K.gguf	Q4_K	11.51GB
Triple-Moist-Theia-21B-SKEWED.Q4_K_M.gguf	Q4_K_M	11.51GB
Triple-Moist-Theia-21B-SKEWED.Q4_1.gguf	Q4_1	12.02GB
Triple-Moist-Theia-21B-SKEWED.Q5_0.gguf	Q5_0	13.17GB
Triple-Moist-Theia-21B-SKEWED.Q5_K_S.gguf	Q5_K_S	13.17GB
Triple-Moist-Theia-21B-SKEWED.Q5_K.gguf	Q5_K	13.5GB
Triple-Moist-Theia-21B-SKEWED.Q5_K_M.gguf	Q5_K_M	13.5GB
Triple-Moist-Theia-21B-SKEWED.Q5_1.gguf	Q5_1	14.32GB
Triple-Moist-Theia-21B-SKEWED.Q6_K.gguf	Q6_K	15.62GB
Triple-Moist-Theia-21B-SKEWED.Q8_0.gguf	Q8_0	20.22GB

Original model description:

base_model:

mergekit-community/Moist_Theia_21B library_name: transformers tags:
mergekit
merge

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the TIES merge method using mergekit-community/Moist_Theia_21B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: mergekit-community/Moist_Theia_21B
    #no parameters necessary for base model
  - model: mergekit-community/Moist_Theia_21B
    parameters:
      density: 0.2
      weight: 0.8
  - model: mergekit-community/Moist_Theia_21B
    parameters:
      density: 0.8
      weight: 0.2

merge_method: ties
base_model: mergekit-community/Moist_Theia_21B
parameters:
  normalize: false
  int8_mask: true
dtype: float16

Downloads last month: 216

GGUF

Model size

20B params

Architecture

llama

Hardware compatibility

2-bit

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

Paper for RichardErkhov/SzilviaB_-_Triple-Moist-Theia-21B-SKEWED-gguf

Resolving Interference When Merging Models

Paper • 2306.01708 • Published Jun 2, 2023 • 19