Instructions to use DevQuasar/falcon2-11B_chat_brainstorm-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DevQuasar/falcon2-11B_chat_brainstorm-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="DevQuasar/falcon2-11B_chat_brainstorm-GGUF",
	filename="falcon2-11B_chat_brainstorm.Q2_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use DevQuasar/falcon2-11B_chat_brainstorm-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf DevQuasar/falcon2-11B_chat_brainstorm-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf DevQuasar/falcon2-11B_chat_brainstorm-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 DevQuasar/falcon2-11B_chat_brainstorm-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf DevQuasar/falcon2-11B_chat_brainstorm-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 DevQuasar/falcon2-11B_chat_brainstorm-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf DevQuasar/falcon2-11B_chat_brainstorm-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 DevQuasar/falcon2-11B_chat_brainstorm-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf DevQuasar/falcon2-11B_chat_brainstorm-GGUF:Q4_K_M

Use Docker

docker model run hf.co/DevQuasar/falcon2-11B_chat_brainstorm-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use DevQuasar/falcon2-11B_chat_brainstorm-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DevQuasar/falcon2-11B_chat_brainstorm-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": "DevQuasar/falcon2-11B_chat_brainstorm-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DevQuasar/falcon2-11B_chat_brainstorm-GGUF:Q4_K_M

Ollama
How to use DevQuasar/falcon2-11B_chat_brainstorm-GGUF with Ollama:
```
ollama run hf.co/DevQuasar/falcon2-11B_chat_brainstorm-GGUF:Q4_K_M
```

Unsloth Studio new

How to use DevQuasar/falcon2-11B_chat_brainstorm-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 DevQuasar/falcon2-11B_chat_brainstorm-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 DevQuasar/falcon2-11B_chat_brainstorm-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for DevQuasar/falcon2-11B_chat_brainstorm-GGUF to start chatting

Docker Model Runner
How to use DevQuasar/falcon2-11B_chat_brainstorm-GGUF with Docker Model Runner:
```
docker model run hf.co/DevQuasar/falcon2-11B_chat_brainstorm-GGUF:Q4_K_M
```

Lemonade

How to use DevQuasar/falcon2-11B_chat_brainstorm-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DevQuasar/falcon2-11B_chat_brainstorm-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.falcon2-11B_chat_brainstorm-GGUF-Q4_K_M

List all available models

lemonade list

Quantized GGUF model files for DevQuasar/falcon2-11B_chat_brainstorm

Brainstorm facilitates idea exploration through interaction with a Language Model (LLM). Rather than providing direct answers, the model engages in a dialogue with users, offering probing questions aimed at fostering deeper contemplation and consideration of various facets of their ideas.

falcon-11B):

"The model is made available under the TII Falcon License 2.0, the permissive Apache 2.0-based software license which includes an acceptable use policy that promotes the responsible use of AI."

Note:

I'm experiencing issues with Stop Strings with LMStudio, the following inference code works fine https://github.com/csabakecskemeti/ai_utils/blob/main/brainstorm_inference.py (hardcoded model name has to change)

Examples

Inference code

https://github.com/csabakecskemeti/ai_utils/blob/main/brainstorm_falcon11b_inference.py

Usage

python brainstorm_falcon11b_inference.py DevQuasar/falcon2-11B_chat_brainstorm

Example generations

[USER] (Ctrl+C to exit): I'd like to start a company that sells unique tshirts with AI generated resign

[CHAT]: That sounds interesting! What kind of technology would you use to create these shirts? Would it be something new or existing? And how do you plan to incorporate the AI into the design?

[USER] (Ctrl+C to exit):

I think I'd user existing tshirst print services. 2) Not wure what you mean 'Would it be something new or existing?' 3) I plan to use a a commerically available image generator like dall-e

[CHAT]: Wow, that's quite advanced! Have you considered how you'll handle the logistics of shipping and handling for these specialty garments? Will you partner with existing suppliers or develop your own manufacturing process?' What kind of customer service would you provide? And how would you ensure that the AI technology is scalable and adaptable to different production methods?

[USER] (Ctrl+C to exit): Use the postal service and direct ship from the print service. Yes I believe AI would be scalable.

[CHAT]: That makes sense. How do you envision the AI system working? Would it be integrated with traditional fashion brands or independent retailers? Or would you see this happening in the future?

I'm doing this to 'Make knowledge free for everyone', using my personal time and resources.

If you want to support my efforts please visit my ko-fi page: https://ko-fi.com/devquasar

Also feel free to visit my website https://devquasar.com/