Instructions to use QuantFactory/Insanity-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use QuantFactory/Insanity-GGUF with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("QuantFactory/Insanity-GGUF", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use QuantFactory/Insanity-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 QuantFactory/Insanity-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf QuantFactory/Insanity-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 QuantFactory/Insanity-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf QuantFactory/Insanity-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 QuantFactory/Insanity-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf QuantFactory/Insanity-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 QuantFactory/Insanity-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf QuantFactory/Insanity-GGUF:Q4_K_M
Use Docker
docker model run hf.co/QuantFactory/Insanity-GGUF:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use QuantFactory/Insanity-GGUF with Ollama:
ollama run hf.co/QuantFactory/Insanity-GGUF:Q4_K_M
- Unsloth Studio
How to use QuantFactory/Insanity-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 QuantFactory/Insanity-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 QuantFactory/Insanity-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for QuantFactory/Insanity-GGUF to start chatting
- Pi
How to use QuantFactory/Insanity-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf QuantFactory/Insanity-GGUF:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "QuantFactory/Insanity-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use QuantFactory/Insanity-GGUF with Docker Model Runner:
docker model run hf.co/QuantFactory/Insanity-GGUF:Q4_K_M
- Lemonade
How to use QuantFactory/Insanity-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull QuantFactory/Insanity-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Insanity-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use QuantFactory/Insanity-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf QuantFactory/Insanity-GGUF:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default QuantFactory/Insanity-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use QuantFactory/Insanity-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf QuantFactory/Insanity-GGUF:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "QuantFactory/Insanity-GGUF:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,137 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
|
| 4 |
+
base_model:
|
| 5 |
+
- v000000/NM-12B-Lyris-dev-3
|
| 6 |
+
- ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.1
|
| 7 |
+
library_name: transformers
|
| 8 |
+
tags:
|
| 9 |
+
- mergekit
|
| 10 |
+
- merge
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
[](https://hf.co/QuantFactory)
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
# QuantFactory/Insanity-GGUF
|
| 19 |
+
This is quantized version of [Nohobby/Insanity](https://huggingface.co/Nohobby/Insanity) created using llama.cpp
|
| 20 |
+
|
| 21 |
+
# Original Model Card
|
| 22 |
+
|
| 23 |
+
# insanity
|
| 24 |
+
|
| 25 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 26 |
+
|
| 27 |
+
## Merge Details
|
| 28 |
+
### Merge Method
|
| 29 |
+
|
| 30 |
+
This model was merged using the della_linear merge method using [ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.1](https://huggingface.co/ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.1) as a base.
|
| 31 |
+
|
| 32 |
+
### Configuration
|
| 33 |
+
|
| 34 |
+
The following YAML configuration was used to produce this model:
|
| 35 |
+
|
| 36 |
+
```yaml
|
| 37 |
+
models:
|
| 38 |
+
- model: natong19/Mistral-Nemo-Instruct-2407-abliterated
|
| 39 |
+
- model: Fizzarolli/MN-12b-Sunrose
|
| 40 |
+
parameters:
|
| 41 |
+
density: 0.5
|
| 42 |
+
weight: [0.495, 0.165, 0.165, 0.495, 0.495, 0.165, 0.165, 0.495]
|
| 43 |
+
- model: nbeerbower/mistral-nemo-gutenberg-12B-v4
|
| 44 |
+
parameters:
|
| 45 |
+
density: [0.35, 0.65, 0.5, 0.65, 0.35]
|
| 46 |
+
weight: [-0.01891, 0.01554, -0.01325, 0.01791, -0.01458]
|
| 47 |
+
merge_method: dare_ties
|
| 48 |
+
base_model: natong19/Mistral-Nemo-Instruct-2407-abliterated
|
| 49 |
+
parameters:
|
| 50 |
+
normalize: false
|
| 51 |
+
int8_mask: true
|
| 52 |
+
dtype: bfloat16
|
| 53 |
+
name: uncen
|
| 54 |
+
|
| 55 |
+
---
|
| 56 |
+
models:
|
| 57 |
+
- model: unsloth/Mistral-Nemo-Instruct-2407
|
| 58 |
+
- model: NeverSleep/Lumimaid-v0.2-12B
|
| 59 |
+
parameters:
|
| 60 |
+
density: 0.5
|
| 61 |
+
weight: [0.139, 0.208, 0.139, 0.208, 0.139]
|
| 62 |
+
- model: nbeerbower/mistral-nemo-cc-12B
|
| 63 |
+
parameters:
|
| 64 |
+
density: [0.65, 0.35, 0.5, 0.35, 0.65]
|
| 65 |
+
weight: [0.01823, -0.01647, 0.01422, -0.01975, 0.01128]
|
| 66 |
+
- model: nbeerbower/mistral-nemo-bophades-12B
|
| 67 |
+
parameters:
|
| 68 |
+
density: [0.35, 0.65, 0.5, 0.65, 0.35]
|
| 69 |
+
weight: [-0.01891, 0.01554, -0.01325, 0.01791, -0.01458]
|
| 70 |
+
merge_method: della
|
| 71 |
+
base_model: unsloth/Mistral-Nemo-Instruct-2407
|
| 72 |
+
parameters:
|
| 73 |
+
epsilon: 0.04
|
| 74 |
+
lambda: 1.05
|
| 75 |
+
normalize: false
|
| 76 |
+
int8_mask: true
|
| 77 |
+
dtype: bfloat16
|
| 78 |
+
name: conv
|
| 79 |
+
---
|
| 80 |
+
models:
|
| 81 |
+
- model: unsloth/Mistral-Nemo-Base-2407
|
| 82 |
+
- model: elinas/Chronos-Gold-12B-1.0
|
| 83 |
+
parameters:
|
| 84 |
+
density: 0.9
|
| 85 |
+
gamma: 0.01
|
| 86 |
+
weight: [0.139, 0.208, 0.208, 0.139, 0.139]
|
| 87 |
+
- model: shuttleai/shuttle-2.5-mini
|
| 88 |
+
parameters:
|
| 89 |
+
density: 0.9
|
| 90 |
+
gamma: 0.01
|
| 91 |
+
weight: [0.208, 0.139, 0.139, 0.139, 0.208]
|
| 92 |
+
- model: Epiculous/Violet_Twilight-v0.2
|
| 93 |
+
parameters:
|
| 94 |
+
density: 0.9
|
| 95 |
+
gamma: 0.01
|
| 96 |
+
weight: [0.139, 0.139, 0.208, 0.208, 0.139]
|
| 97 |
+
merge_method: breadcrumbs_ties
|
| 98 |
+
base_model: unsloth/Mistral-Nemo-Base-2407
|
| 99 |
+
parameters:
|
| 100 |
+
normalize: false
|
| 101 |
+
int8_mask: true
|
| 102 |
+
dtype: bfloat16
|
| 103 |
+
name: chatml
|
| 104 |
+
---
|
| 105 |
+
models:
|
| 106 |
+
- model: ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.1
|
| 107 |
+
parameters:
|
| 108 |
+
weight: [0.2, 0.3, 0.2, 0.3, 0.2]
|
| 109 |
+
density: [0.45, 0.55, 0.45, 0.55, 0.45]
|
| 110 |
+
- model: chatml
|
| 111 |
+
parameters:
|
| 112 |
+
weight: [0.01768, -0.01675, 0.01285, -0.01696, 0.01421]
|
| 113 |
+
density: [0.6, 0.4, 0.5, 0.4, 0.6]
|
| 114 |
+
- model: uncen
|
| 115 |
+
parameters:
|
| 116 |
+
density: [0.6, 0.4, 0.5, 0.4, 0.6]
|
| 117 |
+
weight: [0.01768, -0.01675, 0.01285, -0.01696, 0.01421]
|
| 118 |
+
- model: conv
|
| 119 |
+
parameters:
|
| 120 |
+
weight: [0.208, 0.139, 0.139, 0.139, 0.208]
|
| 121 |
+
density: [0.7]
|
| 122 |
+
- model: v000000/NM-12B-Lyris-dev-3
|
| 123 |
+
parameters:
|
| 124 |
+
weight: [0.33]
|
| 125 |
+
density: [0.45, 0.55, 0.45, 0.55, 0.45]
|
| 126 |
+
merge_method: della_linear
|
| 127 |
+
base_model: ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.1
|
| 128 |
+
parameters:
|
| 129 |
+
epsilon: 0.04
|
| 130 |
+
lambda: 1.05
|
| 131 |
+
int8_mask: true
|
| 132 |
+
rescale: true
|
| 133 |
+
normalize: false
|
| 134 |
+
dtype: bfloat16
|
| 135 |
+
tokenizer_source: base
|
| 136 |
+
```
|
| 137 |
+
|