Instructions to use BlueNipples/TimeCrystal-l2-13B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BlueNipples/TimeCrystal-l2-13B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="BlueNipples/TimeCrystal-l2-13B-GGUF",
	filename="TimeCrystal-l2-13B-Q5_K_S.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 BlueNipples/TimeCrystal-l2-13B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf BlueNipples/TimeCrystal-l2-13B-GGUF:Q5_K_S
# Run inference directly in the terminal:
llama-cli -hf BlueNipples/TimeCrystal-l2-13B-GGUF:Q5_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf BlueNipples/TimeCrystal-l2-13B-GGUF:Q5_K_S
# Run inference directly in the terminal:
llama-cli -hf BlueNipples/TimeCrystal-l2-13B-GGUF:Q5_K_S

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 BlueNipples/TimeCrystal-l2-13B-GGUF:Q5_K_S
# Run inference directly in the terminal:
./llama-cli -hf BlueNipples/TimeCrystal-l2-13B-GGUF:Q5_K_S

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 BlueNipples/TimeCrystal-l2-13B-GGUF:Q5_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf BlueNipples/TimeCrystal-l2-13B-GGUF:Q5_K_S

Use Docker

docker model run hf.co/BlueNipples/TimeCrystal-l2-13B-GGUF:Q5_K_S

LM Studio
Jan
Ollama
How to use BlueNipples/TimeCrystal-l2-13B-GGUF with Ollama:
```
ollama run hf.co/BlueNipples/TimeCrystal-l2-13B-GGUF:Q5_K_S
```

Unsloth Studio

How to use BlueNipples/TimeCrystal-l2-13B-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 BlueNipples/TimeCrystal-l2-13B-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 BlueNipples/TimeCrystal-l2-13B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for BlueNipples/TimeCrystal-l2-13B-GGUF to start chatting

Docker Model Runner
How to use BlueNipples/TimeCrystal-l2-13B-GGUF with Docker Model Runner:
```
docker model run hf.co/BlueNipples/TimeCrystal-l2-13B-GGUF:Q5_K_S
```

Lemonade

How to use BlueNipples/TimeCrystal-l2-13B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull BlueNipples/TimeCrystal-l2-13B-GGUF:Q5_K_S

Run and chat with the model

lemonade run user.TimeCrystal-l2-13B-GGUF-Q5_K_S

List all available models

lemonade list

This 13B model, TimeCrystal-l2-13B is built to maximize logic and instruct following, whilst also increasing the vividness of prose found in Chronos based models like Mythomax, over the more romantic prose, hopefully without losing the elegent narrative structure touch of newer models like synthia and xwin. TLDR: Attempt at more clever, better prose.

Tentative test results: I'm not certain if logic/instruct was improved or not (haven't tested much), but the prose infusion seems to have worked really well.

It is built so:

SLERPS: Amethyst + Openchat Super = OpenStone

MythoMax + Chronos = ChronoMax

ChronoMax + Amethyst = TimeStone

Gradient Merge:

TimeStone + OpenStone (0.9,0,0) = TimeCrystal

Props to all the mergers, fine tuners!

All models in Merge: Many, lol.

Downloads last month: 8

GGUF

Model size

13B params

Architecture

llama

Hardware compatibility

5-bit

Inference Providers NEW

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