Instructions to use TheBigBlender/Daisuke-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBigBlender/Daisuke-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TheBigBlender/Daisuke-GGUF",
	filename="Daisuke.F16.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 TheBigBlender/Daisuke-GGUF with llama.cpp:

Install from brew

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

Use Docker

docker model run hf.co/TheBigBlender/Daisuke-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use TheBigBlender/Daisuke-GGUF with Ollama:
```
ollama run hf.co/TheBigBlender/Daisuke-GGUF:Q4_K_M
```

Unsloth Studio new

How to use TheBigBlender/Daisuke-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 TheBigBlender/Daisuke-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 TheBigBlender/Daisuke-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use TheBigBlender/Daisuke-GGUF with Docker Model Runner:
```
docker model run hf.co/TheBigBlender/Daisuke-GGUF:Q4_K_M
```

Lemonade

How to use TheBigBlender/Daisuke-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TheBigBlender/Daisuke-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Daisuke-GGUF-Q4_K_M

List all available models

lemonade list

Daisuke

This is a merge of pre-trained language models created using mergekit.

Merge Details

Author's Comments

How does Shotmisser64 use Daisuke.

Use alpaca, pyg instruct is not recommended. I use (https://files.catbox.moe/61zzg9.json) along with minimalist context template. Use novel style, mainly because of Erebus. Markdown untested. Use this as an RP assistant. Thanks to pyg, it can also act as 'human' if you want to play as their narrator. You have to edit the response if things go sour at the start. Like Kayra, your config matters a lot, but after 3 turns, it should get better. Feel free to even disable the instruct. Because of Pyg, I recommend putting -3 bias on [376] token (" token) in Kcpp/ST logit bias. It is to reduce pyg's dialogue spam. Since there's another form of (" token), set bias to -100 or ban the token [1346]. As for the [525] (') token, I set it to -5 to reduce 'thinking' done by the character while not banning it outright for words that are using it. I set my Temperature at 1.2 and min p at 0.1. Feel free to play around with other sampler as you see fit.

Special thanks to PygmalionAI for Pygmalion, Jaxxks for Estopia, and Seeker for Erebus, along with the other model creator's model that's being used in the merge.

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

PygmalionAI/pygmalion-2-13b
output/Estopia_Eru

Configuration

The following YAML configuration was used to produce this model:

merge_method: task_arithmetic
base_model: TheBloke/Llama-2-13B-fp16
models:
  - model: TheBloke/Llama-2-13B-fp16
  - model: Undi95/UtopiaXL-13B
    parameters:
      weight: 1.0
  - model: Doctor-Shotgun/cat-v1.0-13b
    parameters:
      weight: 0.02
  - model: PygmalionAI/mythalion-13b
    parameters:
      weight: 0.10
  - model: Undi95/Emerhyst-13B
    parameters:
      weight: 0.05
  - model: CalderaAI/13B-Thorns-l2
    parameters:
      weight: 0.05
  - model: KoboldAI/LLaMA2-13B-Tiefighter
    parameters:
      weight: 0.20
dtype: float16
name: EstopiaV9 # 1rstSamurai 
---
merge_method: task_arithmetic
base_model: TheBloke/Llama-2-13B-fp16
models:
  - model: TheBloke/Llama-2-13B-fp16
  - model: Undi95/UtopiaXL-13B
    parameters:
      weight: 1.0
  - model: Doctor-Shotgun/cat-v1.0-13b
    parameters:
      weight: 0.01
  - model: chargoddard/rpguild-chatml-13b
    parameters:
      weight: 0.02
  - model: PygmalionAI/mythalion-13b
    parameters:
      weight: 0.08
  - model: CalderaAI/13B-Thorns-l2
    parameters:
      weight: 0.02
  - model: KoboldAI/LLaMA2-13B-Tiefighter
    parameters:
      weight: 0.20
dtype: float16
name: EstopiaV13 # No13
---
models:
  - model: output/EstopiaV9
    parameters:
      weight: 1
      density: 1
  - model: output/EstopiaV13
    parameters:
      weight: 0.05
      density: 0.30
merge_method: dare_ties
base_model: TheBloke/Llama-2-13B-fp16
parameters:
  int8_mask: true
dtype: bfloat16
name: Estopia_Dare # rainbowrainbow 
---
models:
  - model: output/Estopia_Dare
    parameters:
      weight: 1
      density: 1
  - model: /home/mixer/koboldai/models/llama2-13b-erebus-v3
    parameters:
      weight: 0.2
      density: 0.1
merge_method: dare_ties
base_model: TheBloke/Llama-2-13B-fp16
parameters:
  int8_mask: true
dtype: bfloat16
name: Estopia_Eru # A-JAX
---
# From the top to Estopia_Eru is by Jaxxks, I just stack Estopia_Eru with Pyg2 to give it Pyg's dialogue capability. 
slices:
  - sources:
    - model: output/Estopia_Eru
      layer_range: [0, 16]
  - sources:
    - model: PygmalionAI/pygmalion-2-13b
      layer_range: [8, 24]
  - sources:
    - model: output/Estopia_Eru
      layer_range: [17, 32]
  - sources:
    - model: PygmalionAI/pygmalion-2-13b
      layer_range: [25, 40]
merge_method: passthrough
dtype: float16

Downloads last month: 69

GGUF

Model size

20B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

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

Model tree for TheBigBlender/Daisuke-GGUF

Base model

PygmalionAI/pygmalion-2-13b

Quantized

(8)

this model