Instructions to use moheith/Yulya-Llama-3.2-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use moheith/Yulya-Llama-3.2-1B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="moheith/Yulya-Llama-3.2-1B",
	filename="V2 Yulya Llama 3.2 1B/Yulya-V2-Llama-3.2-1B-Instruct-Q8_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use moheith/Yulya-Llama-3.2-1B 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 moheith/Yulya-Llama-3.2-1B:Q8_0
# Run inference directly in the terminal:
llama cli -hf moheith/Yulya-Llama-3.2-1B:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf moheith/Yulya-Llama-3.2-1B:Q8_0
# Run inference directly in the terminal:
llama cli -hf moheith/Yulya-Llama-3.2-1B:Q8_0

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 moheith/Yulya-Llama-3.2-1B:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf moheith/Yulya-Llama-3.2-1B:Q8_0

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 moheith/Yulya-Llama-3.2-1B:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf moheith/Yulya-Llama-3.2-1B:Q8_0

Use Docker

docker model run hf.co/moheith/Yulya-Llama-3.2-1B:Q8_0

LM Studio
Jan

vLLM

How to use moheith/Yulya-Llama-3.2-1B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/moheith/Yulya-Llama-3.2-1B:Q8_0

Ollama
How to use moheith/Yulya-Llama-3.2-1B with Ollama:
```
ollama run hf.co/moheith/Yulya-Llama-3.2-1B:Q8_0
```

Unsloth Studio

How to use moheith/Yulya-Llama-3.2-1B 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 moheith/Yulya-Llama-3.2-1B 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 moheith/Yulya-Llama-3.2-1B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for moheith/Yulya-Llama-3.2-1B to start chatting

How to use moheith/Yulya-Llama-3.2-1B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf moheith/Yulya-Llama-3.2-1B:Q8_0

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": "moheith/Yulya-Llama-3.2-1B:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use moheith/Yulya-Llama-3.2-1B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf moheith/Yulya-Llama-3.2-1B:Q8_0

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 moheith/Yulya-Llama-3.2-1B:Q8_0

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use moheith/Yulya-Llama-3.2-1B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf moheith/Yulya-Llama-3.2-1B:Q8_0

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 "moheith/Yulya-Llama-3.2-1B:Q8_0" \
  --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 moheith/Yulya-Llama-3.2-1B with Docker Model Runner:
```
docker model run hf.co/moheith/Yulya-Llama-3.2-1B:Q8_0
```

Lemonade

How to use moheith/Yulya-Llama-3.2-1B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull moheith/Yulya-Llama-3.2-1B:Q8_0

Run and chat with the model

lemonade run user.Yulya-Llama-3.2-1B-Q8_0

List all available models

lemonade list

🩵 Yulya Llama 3.2 1B

⚡ Lightweight. Fast. Expressive. Built for Local AI.

A compact 1B-parameter conversational AI that brings Yulya's playful, expressive, chaotic, and supportive personality to lightweight local applications.

🌟 About Yulya Llama 3.2 1B

Yulya Llama 3.2 1B is a lightweight member of the Yulya model family.

Built on Meta Llama 3.2 1B Instruct, this model is designed for users who want Yulya's conversational personality in a smaller and more computationally accessible model.

The 1B parameter scale makes this version particularly suitable for lightweight local AI projects, desktop companions, experimental applications, and environments where faster inference and lower memory usage are preferred over the capabilities of larger language models.

Yulya is designed to communicate more like an expressive and chaotic best friend than a traditional AI assistant.

Expect:

😂 Expressive emoji usage
🔥 Playful roasting and banter
💀 Chaotic reactions
🗣️ Casual conversational language
💙 Supportive responses during serious conversations
⚡ Lightweight local inference
🤖 Fast AI integrations
🎭 Character-driven interactions

✨ What Makes This Version Special?

🪶 Lightweight 1B Parameter Scale

Yulya Llama 3.2 1B is based on the compact Llama 3.2 1B Instruct architecture.

Compared with the larger Yulya models, this version is designed to prioritize:

⚡ Faster inference
💾 Lower memory requirements
🖥️ Greater hardware accessibility
🔌 Easier local integrations
🤖 Lightweight AI applications
🎮 Interactive projects
🧪 Faster experimentation

🚀 Built for Lightweight Local AI

The smaller model size makes Yulya Llama 3.2 1B particularly interesting for applications where responsiveness and computational efficiency are important.

Potential applications include:

Desktop AI companions
Local chat applications
Background AI systems
Experimental agents
Interactive characters
Lightweight conversational interfaces

😂 The Yulya Personality

Despite its smaller parameter size, the model is fine-tuned around the same core Yulya personality.

Her conversational style focuses on:

Playful teasing
Dramatic reactions
Expressive emojis
Casual language
Chaotic banter
Emotional interactions
Character-driven conversations

💙 More Than Just Chaos

Yulya's personality is designed around more than playful roasting and dramatic reactions.

The fine-tuning data also includes conversational patterns intended to encourage more supportive responses when conversations become serious.

🤖 Model Details

Information	Details
🧠 Model Name	Yulya Llama 3.2 1B
⚡ Edition	Lightweight
🏗️ Base Model	Meta Llama 3.2 1B Instruct
🔢 Parameter Scale	Approximately 1B
💬 Primary Use	Conversational AI
🎭 Secondary Uses	Roleplay and Virtual Companionship
🌎 Language	English
📜 License	Llama 3.2 Community License
📦 Available Formats	Adapters and GGUF
👨‍💻 Developed By	moheith
💰 Funded By	moheith
📤 Shared By	moheith

📦 Available Versions

This repository contains two version directories for Yulya Llama 3.2 1B.

⚪ Version 1

The V1 directory does not contain released model weights or adapters.

📄 Available File

Yulya-V1-Llama-3.2-1B-NA.txt

📦 Availability

Format	Availability
Adapters	❌ Not Available
GGUF Model	❌ Not Available
Merged Model	❌ Not Available
Status File	✅ Available

The V1 directory is retained as part of the repository's version structure and development history.

No runnable V1 model file is currently provided in this repository.

🔵 Version 2

The second generation of the Yulya Llama 3.2 1B fine-tune.

📄 Available Files

Yulya-V2-Llama-3.2-1B-Adapters.zip

Yulya-V2-Llama-3.2-1B-Instruct-Q8_0.gguf

Version 2 provides:

📦 Fine-tuning adapters
💎 A Q8_0 quantized GGUF model

🆚 Version Comparison

Feature	⚪ V1	🔵 V2
Fine-Tuning Adapters	❌	✅
GGUF Model	❌	✅
Q8_0 Quantization	❌	✅
Runnable Model Provided	❌	✅
Recommended for Local Use	❌	⭐ Yes

📁 Repository Structure

Yulya Llama 3.2 1B
│
├── V1 Yulya Llama 3.2 1B
│   │
│   └── Yulya-V1-Llama-3.2-1B-NA.txt
│
└── V2 Yulya Llama 3.2 1B
    │
    ├── Yulya-V2-Llama-3.2-1B-Adapters.zip
    │
    └── Yulya-V2-Llama-3.2-1B-Instruct-Q8_0.gguf

🚀 Which Version Should You Use?

⚪ V1

The V1 directory does not currently provide runnable model weights or fine-tuning adapters.

It is retained as part of the repository structure and model development history.

🔵 Use V2 If...

You want:

The available Yulya Llama 3.2 1B fine-tune
Fine-tuning adapters
A ready-to-use GGUF model
Q8_0 quantization
Lightweight local inference
A compact model for personal AI projects

V2 is the runnable and recommended version currently available in this repository.

💾 Available Model Formats

📦 Fine-Tuning Adapters

Available for:

🔵 V2

The adapter archive contains the fine-tuning adapter files associated with Yulya Llama 3.2 1B V2.

Yulya-V2-Llama-3.2-1B-Adapters.zip

💎 Q8_0 GGUF

Available for:

🔵 V2

The ready-to-use GGUF model is provided as:

Yulya-V2-Llama-3.2-1B-Instruct-Q8_0.gguf

The Q8_0 model uses 8-bit quantization and is intended for use with compatible GGUF inference software.

⚙️ Q8_0 Quantization

The V2 GGUF model is available using Q8_0 quantization.

Compared with lower-bit quantizations, Q8_0 generally uses a larger model file and requires more memory while retaining greater numerical precision.

Actual model performance and memory usage will depend on factors such as:

Available system RAM
Available VRAM
CPU performance
GPU performance
Context length
Inference software
GPU offloading configuration

💻 Compatible Software

The GGUF version may be used with compatible local inference software such as:

llama.cpp
LM Studio
text-generation-webui
Other GGUF-compatible inference engines

The adapter files require a compatible base model and appropriate software for loading PEFT/LoRA-style adapters.

Compatibility and setup requirements may vary depending on the application and software version being used.

🎯 Intended Uses

Yulya Llama 3.2 1B is primarily intended for:

💬 Local conversational AI
🎭 Character-based roleplay
💙 Virtual companionship
🖥️ Desktop AI companions
🤖 Personal AI projects
🎮 Interactive applications
🧠 Memory-based conversational systems
🔌 Lightweight local AI integrations
⚡ Fast conversational applications
🧪 Conversational AI experimentation

🖥️ Why Choose a 1B Model?

Smaller language models can be useful for applications where efficiency and accessibility are important.

Potential advantages include:

⚡ Faster inference
💾 Lower memory requirements than larger models
🖥️ Greater accessibility on consumer hardware
🔌 Easier integration into local projects
🤖 Suitability for background AI applications
🧪 Faster testing and experimentation

However, smaller models also have limitations.

Compared with larger Yulya models, the 1B version may have more limited:

Complex reasoning capabilities
Long-context understanding
Factual reliability
Instruction following
Conversation consistency

The best model depends on your available hardware and intended use case.

🚫 Out-of-Scope Uses

The model is not specifically designed or validated for:

❌ Professional medical advice
❌ Professional legal advice
❌ Critical financial decisions
❌ Safety-critical applications
❌ Guaranteed factual accuracy
❌ Formal academic research without independent verification

Important information generated by the model should always be independently verified.

📚 Training Details

📊 Training Data

Yulya was fine-tuned using custom-curated conversational data.

The training data was designed to encourage behaviors such as:

Modern texting styles
Expressive emoji usage
Conversational banter
Playful interactions
Personality consistency
Emotional conversations
Supportive responses
Context-dependent conversational shifts

The goal of the fine-tuning process was to adapt the base model toward Yulya's distinctive conversational personality.

Detailed information about the complete training dataset is not currently provided.

⚙️ Training Approach

The model was fine-tuned from:

meta-llama/Llama-3.2-1B-Instruct

The fine-tuning process focused on adapting the conversational behavior and response style of the base model.

Fine-tuning adapters for V2 are included in this repository.

🧪 Evaluation

📊 Evaluation Method

Yulya Llama 3.2 1B has primarily been evaluated through informal and qualitative conversational testing.

No standardized benchmark scores are currently reported in this model card.

Testing focused on areas such as:

Persona consistency
Conversational behavior
Emoji usage
Emotional transitions
Informal interactions
Response style
Multi-turn conversations

🔍 Qualitative Testing Areas

The model was informally tested across conversational scenarios including:

Short conversations
Casual banter
Playful interactions
Topic changes
Emotional conversations
Multi-turn conversations

📈 Observed Behavior

During informal conversational testing, the model demonstrated the ability to generate responses aligned with the intended Yulya personality.

The 1B parameter version is primarily intended to provide a lightweight and computationally accessible Yulya experience.

Areas of focus include:

⚡ Response speed
💾 Computational efficiency
💬 Conversational behavior
🎭 Personality consistency
😂 Expressive responses
💙 Emotional interactions

These observations are qualitative and should not be interpreted as standardized benchmark results.

⚠️ Bias, Risks, and Limitations

Yulya Llama 3.2 1B is fine-tuned toward an informal, expressive, and character-driven conversational personality.

Depending on the prompt and context, the model may generate:

Sarcastic responses
Playful insults
Informal slang
Aggressive capitalization
Heavy emoji usage
Dramatic reactions
Repetitive responses
Incorrect information
Hallucinated information
Biased or otherwise undesirable outputs

Because this is a relatively small language model, its reasoning capabilities, factual reliability, context handling, and conversational consistency may be more limited than larger models.

Users should independently verify important factual information.

💡 Recommendations

Yulya Llama 3.2 1B is best suited for applications where efficiency, personality, local inference, entertainment, and experimentation are important.

Developers integrating the model into applications should:

Clearly communicate that users are interacting with an AI model
Inform users about the model's limitations
Independently verify important information
Test the model for the intended use case
Implement appropriate safeguards where necessary
Avoid relying on the model for safety-critical decisions

🔬 Technical Specifications

Specification	Details
🏗️ Architecture	Llama 3.2
🔢 Parameter Scale	Approximately 1B
🧠 Base Model	Llama 3.2 1B Instruct
⚪ V1	No Released Model
📦 V2 Formats	Adapters and GGUF
💎 GGUF Quantization	Q8_0
💬 Primary Purpose	Conversational AI
🎭 Personality	Yulya

🌱 Environmental Impact

Detailed environmental impact measurements are not currently available.

Information	Details
💻 Hardware Type	Consumer Hardware
⏱️ Training Hours	Not Reported
☁️ Cloud Provider	Not Reported
🌎 Compute Region	Not Reported
🌱 Carbon Emissions	Not Measured

📜 License

This model is based on Meta Llama 3.2 1B Instruct.

Users are responsible for reviewing and complying with the applicable Llama 3.2 Community License Agreement, Acceptable Use Policy, and any other applicable terms associated with the base model and this fine-tuned model.

👨‍💻 Developer

Developed by moheith

Yulya is part of an ongoing project focused on building expressive local AI companions with personality, memory, emotional continuity, and interactive capabilities.

The Yulya model family explores how different language model architectures and parameter sizes can be adapted toward the same conversational personality.

🩵 Final Note

Small model. Fast responses. Maximum Yulya energy.

Yulya Llama 3.2 1B is designed for users who want a lightweight version of Yulya that can fit more easily into local AI projects.

Small enough for accessible local experimentation.

Fast enough for interactive applications.

Expressive enough to feel like Yulya.

Chaotic enough to roast you.

And supportive enough to stay when the conversation gets serious. 🩵

⭐ Welcome to Yulya Llama 3.2 1B

Downloads last month: 13

GGUF

Model size

1B params

Architecture

llama

Hardware compatibility

8-bit

Model tree for moheith/Yulya-Llama-3.2-1B

Base model

meta-llama/Llama-3.2-1B-Instruct

Quantized

(406)

this model

Collection including moheith/Yulya-Llama-3.2-1B

Yulya

Collection

💙 A family of fine-tuned conversational AI models across multiple architectures and sizes — built to bring Yulya's expressive, playful and chaotic. • 6 items • Updated 15 days ago • 1