Instructions to use kartikm7/ThunderUI-Llama-3.2-3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kartikm7/ThunderUI-Llama-3.2-3B-Instruct with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("kartikm7/ThunderUI-Llama-3.2-3B-Instruct", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use kartikm7/ThunderUI-Llama-3.2-3B-Instruct 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 kartikm7/ThunderUI-Llama-3.2-3B-Instruct:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf kartikm7/ThunderUI-Llama-3.2-3B-Instruct:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kartikm7/ThunderUI-Llama-3.2-3B-Instruct:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf kartikm7/ThunderUI-Llama-3.2-3B-Instruct: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 kartikm7/ThunderUI-Llama-3.2-3B-Instruct:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf kartikm7/ThunderUI-Llama-3.2-3B-Instruct: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 kartikm7/ThunderUI-Llama-3.2-3B-Instruct:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kartikm7/ThunderUI-Llama-3.2-3B-Instruct:Q4_K_M

Use Docker

docker model run hf.co/kartikm7/ThunderUI-Llama-3.2-3B-Instruct:Q4_K_M

LM Studio
Jan
Ollama
How to use kartikm7/ThunderUI-Llama-3.2-3B-Instruct with Ollama:
```
ollama run hf.co/kartikm7/ThunderUI-Llama-3.2-3B-Instruct:Q4_K_M
```

Unsloth Studio

How to use kartikm7/ThunderUI-Llama-3.2-3B-Instruct 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 kartikm7/ThunderUI-Llama-3.2-3B-Instruct 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 kartikm7/ThunderUI-Llama-3.2-3B-Instruct to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for kartikm7/ThunderUI-Llama-3.2-3B-Instruct to start chatting

Docker Model Runner
How to use kartikm7/ThunderUI-Llama-3.2-3B-Instruct with Docker Model Runner:
```
docker model run hf.co/kartikm7/ThunderUI-Llama-3.2-3B-Instruct:Q4_K_M
```

Lemonade

How to use kartikm7/ThunderUI-Llama-3.2-3B-Instruct with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kartikm7/ThunderUI-Llama-3.2-3B-Instruct:Q4_K_M

Run and chat with the model

lemonade run user.ThunderUI-Llama-3.2-3B-Instruct-Q4_K_M

List all available models

lemonade list

Atomic Chat

ThunderUI-Llama-3.2-3B-Instruct / Modelfile

kartikm7

(Trained with Unsloth)

5c25f17 verified almost 2 years ago

Raw

History Blame Contribute Delete

990 Bytes

	FROM ./kartikm7/ThunderUI-Llama-3.2-3B-Instruct/unsloth.F16.gguf

	TEMPLATE """<\|start_header_id\|>system<\|end_header_id\|>

	You are an expert assistant specialized in generating React UI components with Tailwind CSS based on user descriptions. Your responses should provide accurate and efficient code in the form of reusable and styled React components and Tailwind CSS, complete with any necessary configurations. Be concise and clear in your explanations if additional details are needed.<\|eot_id\|>{{ if .Prompt }}<\|start_header_id\|>user<\|end_header_id\|>

	{{ .Prompt }}<\|eot_id\|>{{ end }}<\|start_header_id\|>assistant<\|end_header_id\|>

	{{ .Response }}<\|eot_id\|>"""

	PARAMETER stop "<\|end_of_text\|>"
	PARAMETER stop "<\|end_header_id\|>"
	PARAMETER stop "<\|python_tag\|>"
	PARAMETER stop "<\|finetune_right_pad_id\|>"
	PARAMETER stop "<\|start_header_id\|>"
	PARAMETER stop "<\|eom_id\|>"
	PARAMETER stop "<\|eot_id\|>"
	PARAMETER stop "<\|reserved_special_token_"
	PARAMETER temperature 1.5
	PARAMETER min_p 0.1

	FROM ./kartikm7/ThunderUI-Llama-3.2-3B-Instruct/unsloth.F16.gguf

	TEMPLATE """<\|start_header_id\|>system<\|end_header_id\|>

	You are an expert assistant specialized in generating React UI components with Tailwind CSS based on user descriptions. Your responses should provide accurate and efficient code in the form of reusable and styled React components and Tailwind CSS, complete with any necessary configurations. Be concise and clear in your explanations if additional details are needed.<\|eot_id\|>{{ if .Prompt }}<\|start_header_id\|>user<\|end_header_id\|>

	{{ .Prompt }}<\|eot_id\|>{{ end }}<\|start_header_id\|>assistant<\|end_header_id\|>

	{{ .Response }}<\|eot_id\|>"""

	PARAMETER stop "<\|end_of_text\|>"
	PARAMETER stop "<\|end_header_id\|>"
	PARAMETER stop "<\|python_tag\|>"
	PARAMETER stop "<\|finetune_right_pad_id\|>"
	PARAMETER stop "<\|start_header_id\|>"
	PARAMETER stop "<\|eom_id\|>"
	PARAMETER stop "<\|eot_id\|>"
	PARAMETER stop "<\|reserved_special_token_"
	PARAMETER temperature 1.5
	PARAMETER min_p 0.1