Instructions to use RichardErkhov/forcemultiplier_-_fmx-3b-augment-instruct_preview-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/forcemultiplier_-_fmx-3b-augment-instruct_preview-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/forcemultiplier_-_fmx-3b-augment-instruct_preview-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/forcemultiplier_-_fmx-3b-augment-instruct_preview-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/forcemultiplier_-_fmx-3b-augment-instruct_preview-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/forcemultiplier_-_fmx-3b-augment-instruct_preview-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/forcemultiplier_-_fmx-3b-augment-instruct_preview-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RichardErkhov/forcemultiplier_-_fmx-3b-augment-instruct_preview-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/forcemultiplier_-_fmx-3b-augment-instruct_preview-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RichardErkhov/forcemultiplier_-_fmx-3b-augment-instruct_preview-gguf:Q4_K_M

Use Docker

docker model run hf.co/RichardErkhov/forcemultiplier_-_fmx-3b-augment-instruct_preview-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use RichardErkhov/forcemultiplier_-_fmx-3b-augment-instruct_preview-gguf with Ollama:
```
ollama run hf.co/RichardErkhov/forcemultiplier_-_fmx-3b-augment-instruct_preview-gguf:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use RichardErkhov/forcemultiplier_-_fmx-3b-augment-instruct_preview-gguf with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/forcemultiplier_-_fmx-3b-augment-instruct_preview-gguf:Q4_K_M
```

Lemonade

How to use RichardErkhov/forcemultiplier_-_fmx-3b-augment-instruct_preview-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RichardErkhov/forcemultiplier_-_fmx-3b-augment-instruct_preview-gguf:Q4_K_M

Run and chat with the model

lemonade run user.forcemultiplier_-_fmx-3b-augment-instruct_preview-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

fmx-3b-augment-instruct_preview - GGUF

Model creator: https://huggingface.co/forcemultiplier/
Original model: https://huggingface.co/forcemultiplier/fmx-3b-augment-instruct_preview/

Name	Quant method	Size
fmx-3b-augment-instruct_preview.Q2_K.gguf	Q2_K	1.28GB
fmx-3b-augment-instruct_preview.IQ3_XS.gguf	IQ3_XS	1.42GB
fmx-3b-augment-instruct_preview.IQ3_S.gguf	IQ3_S	1.48GB
fmx-3b-augment-instruct_preview.Q3_K_S.gguf	Q3_K_S	1.48GB
fmx-3b-augment-instruct_preview.IQ3_M.gguf	IQ3_M	1.51GB
fmx-3b-augment-instruct_preview.Q3_K.gguf	Q3_K	1.61GB
fmx-3b-augment-instruct_preview.Q3_K_M.gguf	Q3_K_M	1.61GB
fmx-3b-augment-instruct_preview.Q3_K_L.gguf	Q3_K_L	1.71GB
fmx-3b-augment-instruct_preview.IQ4_XS.gguf	IQ4_XS	1.79GB
fmx-3b-augment-instruct_preview.Q4_0.gguf	Q4_0	1.86GB
fmx-3b-augment-instruct_preview.IQ4_NL.gguf	IQ4_NL	1.87GB
fmx-3b-augment-instruct_preview.Q4_K_S.gguf	Q4_K_S	1.87GB
fmx-3b-augment-instruct_preview.Q4_K.gguf	Q4_K	1.96GB
fmx-3b-augment-instruct_preview.Q4_K_M.gguf	Q4_K_M	1.96GB
fmx-3b-augment-instruct_preview.Q4_1.gguf	Q4_1	2.04GB
fmx-3b-augment-instruct_preview.Q5_0.gguf	Q5_0	2.22GB
fmx-3b-augment-instruct_preview.Q5_K_S.gguf	Q5_K_S	2.22GB
fmx-3b-augment-instruct_preview.Q5_K.gguf	Q5_K	2.27GB
fmx-3b-augment-instruct_preview.Q5_K_M.gguf	Q5_K_M	2.27GB
fmx-3b-augment-instruct_preview.Q5_1.gguf	Q5_1	2.4GB
fmx-3b-augment-instruct_preview.Q6_K.gguf	Q6_K	2.6GB
fmx-3b-augment-instruct_preview.Q8_0.gguf	Q8_0	3.37GB

Original model description:

base_model:

unsloth/Qwen2.5-3B-Instruct
unsloth/Qwen2.5-3B library_name: transformers tags:
mergekit
merge

fmx-3b Augmentive Instruct (preview)

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 unsloth/Qwen2.5-3B as a base.

Models Merged

The following models were included in the merge:

unsloth/Qwen2.5-3B-Instruct
triples
genstruct
kg

Downloads last month: 496

GGUF

Model size

3B params

Architecture

qwen2

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/forcemultiplier_-_fmx-3b-augment-instruct_preview-gguf

Resolving Interference When Merging Models

Paper • 2306.01708 • Published Jun 2, 2023 • 19