Instructions to use behzatindustries/BehzatOne-8B-A1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use behzatindustries/BehzatOne-8B-A1B 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 behzatindustries/BehzatOne-8B-A1B:BF16
# Run inference directly in the terminal:
llama cli -hf behzatindustries/BehzatOne-8B-A1B:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf behzatindustries/BehzatOne-8B-A1B:BF16
# Run inference directly in the terminal:
llama cli -hf behzatindustries/BehzatOne-8B-A1B:BF16

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 behzatindustries/BehzatOne-8B-A1B:BF16
# Run inference directly in the terminal:
./llama-cli -hf behzatindustries/BehzatOne-8B-A1B:BF16

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 behzatindustries/BehzatOne-8B-A1B:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf behzatindustries/BehzatOne-8B-A1B:BF16

Use Docker

docker model run hf.co/behzatindustries/BehzatOne-8B-A1B:BF16

LM Studio
Jan

vLLM

How to use behzatindustries/BehzatOne-8B-A1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "behzatindustries/BehzatOne-8B-A1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "behzatindustries/BehzatOne-8B-A1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/behzatindustries/BehzatOne-8B-A1B:BF16

Ollama
How to use behzatindustries/BehzatOne-8B-A1B with Ollama:
```
ollama run hf.co/behzatindustries/BehzatOne-8B-A1B:BF16
```

Unsloth Studio

How to use behzatindustries/BehzatOne-8B-A1B 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 behzatindustries/BehzatOne-8B-A1B 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 behzatindustries/BehzatOne-8B-A1B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for behzatindustries/BehzatOne-8B-A1B to start chatting

Docker Model Runner
How to use behzatindustries/BehzatOne-8B-A1B with Docker Model Runner:
```
docker model run hf.co/behzatindustries/BehzatOne-8B-A1B:BF16
```

Lemonade

How to use behzatindustries/BehzatOne-8B-A1B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull behzatindustries/BehzatOne-8B-A1B:BF16

Run and chat with the model

lemonade run user.BehzatOne-8B-A1B-BF16

List all available models

lemonade list

Atomic Chat

BehzatOne-8B-A1B / Modelfile

rebehzat

Upload BehzatOne v109 GGUF release artifacts

7d54cc7 verified about 1 month ago

Raw

History Blame Contribute Delete

736 Bytes

	FROM ./gguf/BehzatOne-8B-A1B-v109.Q4_K_M.gguf

	TEMPLATE """<\|startoftext\|>{{ if .System }}<\|im_start\|>system
	{{ .System }}<\|im_end\|>
	{{ else }}<\|im_start\|>system
	You are BehzatOne, a careful code assistant by Behzat Industries.
	Answer with the requested final artifact only. Do not include hidden reasoning,
	<think> blocks, or unrelated prose. If you do not know, say UNKNOWN.<\|im_end\|>
	{{ end }}<\|im_start\|>user
	{{ .Prompt }}

	Answer final only. Do not output <think> blocks.<\|im_end\|>
	<\|im_start\|>assistant
	"""

	RENDERER lfm2-thinking
	PARSER lfm2-thinking

	PARAMETER stop "<\|im_end\|>"
	PARAMETER stop "<\|im_start\|>"
	PARAMETER temperature 0.1
	PARAMETER top_k 30
	PARAMETER top_p 0.85
	PARAMETER repeat_penalty 1.1
	PARAMETER typical_p 0.9