Instructions to use R136a1/Ayam-2x8B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use R136a1/Ayam-2x8B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="R136a1/Ayam-2x8B-GGUF",
	filename="Ayam-2x8B.Q3_K_M-imat.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 R136a1/Ayam-2x8B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf R136a1/Ayam-2x8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf R136a1/Ayam-2x8B-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 R136a1/Ayam-2x8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf R136a1/Ayam-2x8B-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 R136a1/Ayam-2x8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf R136a1/Ayam-2x8B-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 R136a1/Ayam-2x8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf R136a1/Ayam-2x8B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/R136a1/Ayam-2x8B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use R136a1/Ayam-2x8B-GGUF with Ollama:
```
ollama run hf.co/R136a1/Ayam-2x8B-GGUF:Q4_K_M
```

Unsloth Studio new

How to use R136a1/Ayam-2x8B-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 R136a1/Ayam-2x8B-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 R136a1/Ayam-2x8B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for R136a1/Ayam-2x8B-GGUF to start chatting

Docker Model Runner
How to use R136a1/Ayam-2x8B-GGUF with Docker Model Runner:
```
docker model run hf.co/R136a1/Ayam-2x8B-GGUF:Q4_K_M
```

Lemonade

How to use R136a1/Ayam-2x8B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull R136a1/Ayam-2x8B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Ayam-2x8B-GGUF-Q4_K_M

List all available models

lemonade list

art by myself using AI

Ayam 2x8B

GGUF
Quantized using lastest llama.cpp as per writing.
Quantized using imatrix calculated from FP16 while using BF16 to create the quants to preserve accuracy.

Technical test:

Quant	PPL	VRAM
FP16	3.7393 +/- 0.14377	22GB+
Q8_0	3.7393 +/- 0.14381	14.8GB
Q6_K	3.7283 +/- 0.14309	11.7GB
Q5_K_M	3.7490 +/- 0.14440	10.4GB
Q4_K_M	3.7263 +/- 0.14158	9.1GB
Q4_K_S	3.7276 +/- 0.14139	8.5GB
Q3_K_M	3.8198 +/- 0.14552	7.5GB

Perplexity test using llama.cpp/perplexity.
VRAM at full 8K context using Nvidia L4 GPU.
VRAM test using llama.cpp/server.

Another MoE, this time using L3.
Recipe: Sao's Stheno-v3.2 + L3 8B Instruct.

This model is intended for personal use but I think it's really good and worth sharing. Stheno-v3.2 is, as you probably know well, very good. In creative writing, RP and ERP it's far better than L3 Instruct and to be honest it's the best L3 finetunes I've tried so far so yeah I liked it very much. But while playing with it, I feel like the model is (a bit) dumber than L3 Instruct. It can't understand complex scenario well and confused in multi-char scenario, at least that what I was experiencing. So yeah, I tried to improve its intelligence while still preserving its creativity.

Why MoE not merge?
Well... 2 model working together is always better than merging it into one. And (surprisingly) the result is far exceeded my expectations.
And I think merging models sometimes can damage It's quality.

Testing condition (using SillyTavern):
Context and Instruct: Llama 3 Instruct.
Sampler:

Temperature : 1.15
MinP : 0.075
TopK : 50
Other is disabled.

Switch

BF16 - GGUF

Downloads last month: 243

GGUF

Model size

14B 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