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 / SFT-adapter /README.md

rebehzat

BehzatOne-8B-A1B v1.0: SFT LoRA adapter

6572764 verified about 2 months ago

preview code

Raw

History Blame Contribute Delete

2.31 kB

	---
	license: apache-2.0
	# adjusted: base_model pinned to upstream
	# LiquidAI/LFM2.5-8B-A1B
	tags:
	- lfm2
	- lora
	- behzat-industries
	- code
	- sft
	pipeline_tag: text-generation
	---

	# BehzatOne-8B-A1B (LoRA)

	This is the first model of Behzat Industries — a code-focused SFT LoRA on top of [LiquidAI/LFM2.5-8B-A1B](https://huggingface.co/LiquidAI/LFM2.5-8B-A1B).

	## What's in this repo

	- `adapter_model.safetensors` — LoRA adapter (rank 32, alpha 64, target modules on attention + MLP projections). Attach to the base model with `peft`.
	- `tokenizer.json` — LFM2.5 tokenizer.
	- `adapter_config.json` — peft config.

	## What's in Behzat

	- Multi-source code SFT dataset (~109k samples) drawn from
	open-thoughts/OpenThoughts, OpenThoughts3-1.2M,
	iamtarun/python_code_instructions_18k_alpaca, glaiveai/glaive-function-calling-v2,
	Agent-Ark/Toucan-1.5M and NousResearch/hermes-function-calling-v1.
	- 2,000 optimizer steps, effective batch 16, lr 2e-4 linear decay,
	packing disabled to avoid token-level cross-contamination with sdpa attention.
	- Final mean token accuracy ~80% on the training slice, train loss ~0.85
	(started ~1.0).
	- Trained on a single Quadro RTX 6000 on Vast.ai ($0.17/hr).

	## How to use

	```python
	import torch
	from peft import PeftModel
	from transformers import AutoModelForCausalLM, AutoTokenizer

	base = AutoModelForCausalLM.from_pretrained(
	"LiquidAI/LFM2.5-8B-A1B",
	torch_dtype=torch.bfloat16,
	device_map="auto",
	)
	model = PeftModel.from_pretrained(base, "rebehzat/BehzatOne-8B-A1B")
	tok = AutoTokenizer.from_pretrained("rebehzat/BehzatOne-8B-A1B")
	```

	## Roadmap (Behzat Industries)

	- v1.0 (this): SFT LoRA + tokenizer.
	- v1.1: DPO on UltraFeedback binarized (single GPU).
	- v1.2: drop merged BF16 weights for direct inference.
	- v1.3: Q4_K_M GGUF runtime quant.

	## Limits

	- Base is 8B-param MoE with ~1B active params; quality ceiling is bounded by it.
	- Trained with sdpa attention (no flash-attn was available on the host).
	- Best on simple code completion; not a SWE-bench-grade coder.

	## About Behzat Industries

	Behzat Industries builds small, openly published coding models for hobbyists,
	LLM-studio tinkerers and small-team dev tools. BehzatOne is the first of an
	ongoing series. Buy nothing. Try everything. Tell us what fails.