Instructions to use CultriX/MergeTrix-7B-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 CultriX/MergeTrix-7B-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 CultriX/MergeTrix-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf CultriX/MergeTrix-7B-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 CultriX/MergeTrix-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf CultriX/MergeTrix-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 CultriX/MergeTrix-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf CultriX/MergeTrix-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 CultriX/MergeTrix-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf CultriX/MergeTrix-7B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/CultriX/MergeTrix-7B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use CultriX/MergeTrix-7B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CultriX/MergeTrix-7B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CultriX/MergeTrix-7B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CultriX/MergeTrix-7B-GGUF:Q4_K_M

Ollama
How to use CultriX/MergeTrix-7B-GGUF with Ollama:
```
ollama run hf.co/CultriX/MergeTrix-7B-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use CultriX/MergeTrix-7B-GGUF with Docker Model Runner:
```
docker model run hf.co/CultriX/MergeTrix-7B-GGUF:Q4_K_M
```

Lemonade

How to use CultriX/MergeTrix-7B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CultriX/MergeTrix-7B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MergeTrix-7B-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

CultriX commited on Jan 15, 2024

Commit

0280a11

verified ·

1 Parent(s): 6d56539

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -9,6 +9,11 @@ tags:
 - argilla/distilabeled-Marcoro14-7B-slerp
 ---
 # MergeTrix-7B-GGUF
 Quantisized versions of MergeTrix-7B. Supports:
@@ -19,11 +24,6 @@ Name 	Quant method 	Bits 	Size 	Max RAM required 	Use case
 > mergetrix-7b.Q6_K.gguf (5.94 GB): very large, extremely low quality loss
-MergeTrix-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
-* [abideen/NexoNimbus-7B](https://huggingface.co/abideen/NexoNimbus-7B)
-* [fblgit/UNA-TheBeagle-7b-v1](https://huggingface.co/fblgit/UNA-TheBeagle-7b-v1)
-* [argilla/distilabeled-Marcoro14-7B-slerp](https://huggingface.co/argilla/distilabeled-Marcoro14-7B-slerp)
 ## 🧩 Configuration
 ```yaml

 - argilla/distilabeled-Marcoro14-7B-slerp
 ---
+MergeTrix-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [abideen/NexoNimbus-7B](https://huggingface.co/abideen/NexoNimbus-7B)
+* [fblgit/UNA-TheBeagle-7b-v1](https://huggingface.co/fblgit/UNA-TheBeagle-7b-v1)
+* [argilla/distilabeled-Marcoro14-7B-slerp](https://huggingface.co/argilla/distilabeled-Marcoro14-7B-slerp)
 # MergeTrix-7B-GGUF
 Quantisized versions of MergeTrix-7B. Supports:
 > mergetrix-7b.Q6_K.gguf (5.94 GB): very large, extremely low quality loss
 ## 🧩 Configuration
 ```yaml