nsfw

roleplay

español

uncensored

4-bit precision

Not-For-All-Audiences

imatrix

conversational

Model card Files Files and versions

xet

Community

Instructions to use Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

Transformers

How to use Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-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 Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF:Q4_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF:Q4_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 Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF:Q4_K_S
# Run inference directly in the terminal:
./llama-cli -hf Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF:Q4_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 Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF:Q4_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF:Q4_K_S

Use Docker

docker model run hf.co/Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF:Q4_K_S

LM Studio
Jan

vLLM

How to use Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF:Q4_K_S

SGLang

How to use Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF with Ollama:
```
ollama run hf.co/Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF:Q4_K_S
```

Unsloth Studio

How to use Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-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 Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-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 Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF to start chatting

How to use Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF:Q4_K_S

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": "Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF:Q4_K_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF:Q4_K_S

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 "Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF:Q4_K_S" \
  --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"

Docker Model Runner
How to use Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF with Docker Model Runner:
```
docker model run hf.co/Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF:Q4_K_S
```

Lemonade

How to use Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF:Q4_K_S

Run and chat with the model

lemonade run user.Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF-Q4_K_S

List all available models

lemonade list

Hermes Agent

How to use Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-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 Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF:Q4_K_S

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 Novaciano/Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF:Q4_K_S

Run Hermes

hermes

Atomic Chat

Aesir-3.2-1B-GRPO_MiniThinky_Q4_K_S-GGUF / README.md

Novaciano

Update README.md

9646bf8 verified over 1 year ago

preview code

Raw

History Blame Contribute Delete

1.05 kB

metadata

library_name: transformers
license: apache-2.0
datasets:
  - NickyNicky/ngxson_MiniThinky_v1_deduplicated_11_percent
  - MinervaAI/Aesir-Preview
language:
  - en
  - es
base_model: NickyNicky/Llama-1B-base-GRPO-miniThinky_v1
pipeline_tag: text-generation
tags:
  - llama-cpp
  - koboldcpp
  - nsfw
  - rp
  - roleplay
  - español
  - uncensored
  - 1b
  - 4-bit
  - not-for-all-audiences

Aesir 3.2 1B GRPO MiniThinky

Este es el modelo Aesir 3.2 1B GRPO MiniThinky de NickyNicky combinado con el dataset Aesir Preview de MinervaAI.

Mejoras conocidas:

Si, fue creado en base de un modelo entrenado con un dataset de razonamiento.

Además cuenta con mejoras técnicas, fue entrenado con técnica GRPO (Ver más abajo que significa).

Lo conforman dos versiones:

IQ4_XS: Es una versión rápida e ideal para celulares pero con un costo minimo de coherencia.
Q4_K_S: Una versión intermedia.
Q5_0: Es una versión mas... digamos... inteligente, pero pide mayor requisitos computacionales.

Elige la versión que más se adapte a tus necesidades.