Instructions to use athirdpath/Iambe-20b-DARE-v2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use athirdpath/Iambe-20b-DARE-v2-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="athirdpath/Iambe-20b-DARE-v2-GGUF",
	filename="iambe-20b-dare-v2.q6_k.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 athirdpath/Iambe-20b-DARE-v2-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf athirdpath/Iambe-20b-DARE-v2-GGUF:Q6_K
# Run inference directly in the terminal:
llama-cli -hf athirdpath/Iambe-20b-DARE-v2-GGUF:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf athirdpath/Iambe-20b-DARE-v2-GGUF:Q6_K
# Run inference directly in the terminal:
llama-cli -hf athirdpath/Iambe-20b-DARE-v2-GGUF:Q6_K

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 athirdpath/Iambe-20b-DARE-v2-GGUF:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf athirdpath/Iambe-20b-DARE-v2-GGUF:Q6_K

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 athirdpath/Iambe-20b-DARE-v2-GGUF:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf athirdpath/Iambe-20b-DARE-v2-GGUF:Q6_K

Use Docker

docker model run hf.co/athirdpath/Iambe-20b-DARE-v2-GGUF:Q6_K

LM Studio
Jan
Ollama
How to use athirdpath/Iambe-20b-DARE-v2-GGUF with Ollama:
```
ollama run hf.co/athirdpath/Iambe-20b-DARE-v2-GGUF:Q6_K
```

Unsloth Studio new

How to use athirdpath/Iambe-20b-DARE-v2-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 athirdpath/Iambe-20b-DARE-v2-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 athirdpath/Iambe-20b-DARE-v2-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for athirdpath/Iambe-20b-DARE-v2-GGUF to start chatting

Docker Model Runner
How to use athirdpath/Iambe-20b-DARE-v2-GGUF with Docker Model Runner:
```
docker model run hf.co/athirdpath/Iambe-20b-DARE-v2-GGUF:Q6_K
```

Lemonade

How to use athirdpath/Iambe-20b-DARE-v2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull athirdpath/Iambe-20b-DARE-v2-GGUF:Q6_K

Run and chat with the model

lemonade run user.Iambe-20b-DARE-v2-GGUF-Q6_K

List all available models

lemonade list

Strange quirk: This model seems to need a context size of EXACTLY 4096 ONLY. I'm assuming this is a dares_ties effect?

Iambe-20b-DARE-v2

Description

Named after a charming daughter of Echo and Pan in Greek myth, Iambe-20b-DARE-v2 is an improved DARE merge building on my recent experiments.

Iambe is intended to have the best realistically possible understanding of anatomy and of a scene's state for a 20b merge, while remaining personable and authentic in "voice".

Update Methodology

Noromaid and the general "no-robots" vibe didn't come through like I'd hoped in v1. My hypothesis is that the "soul" MythoMax and Noromaid have is probably distributed widely over many low-value deltas, due to the "ephemeral" nature of such a thing.

My old base model was likely giving DARE conniption fits, so I replaced that with a truly vanilla 20b base model.

CleverGirl was updated to the DARE version, as Sir Hillary said, simply because it was there.

Without a large base of dare_ties models to compare to, I'm basically feeling my way through this intuitively, so here's to good results!

Recipe

merge_method: dare_ties

base_model: athirdpath/BigLlama-20b-v1.1
model: Noromaid-20b-v0.1.1

weight: 0.38 / density: 0.60
model: athirdpath/athirdpath/Eileithyia-20b

weight: 0.22 / density: 0.40
model: athirdpath/CleverGirl-20b-Blended-v1.1-DARE

weight: 0.40 / density: 0.33

int8_mask: true

dtype: bfloat16

Downloads last month: 5

GGUF

Model size

20B params

Architecture

llama

Hardware compatibility

6-bit

Inference Providers NEW

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

Collection including athirdpath/Iambe-20b-DARE-v2-GGUF

GGUF Quants - Roleplay Deployment Models

Collection

GGUF - Models I think are cool and worth using. A lot of what I make is intended only as a part in a further merge or as a test, these are the others. • 14 items • Updated Sep 3, 2024 • 5