Instructions to use Alsamir/Abjad_0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Alsamir/Abjad_0.2 with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("Alsamir/Abjad_0.2")
config = load_config("Alsamir/Abjad_0.2")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use Alsamir/Abjad_0.2 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Alsamir/Abjad_0.2"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Alsamir/Abjad_0.2"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use Alsamir/Abjad_0.2 with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Alsamir/Abjad_0.2"

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 Alsamir/Abjad_0.2

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Alsamir/Abjad_0.2 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Alsamir/Abjad_0.2"

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 "Alsamir/Abjad_0.2" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Abjad_0.2 / docs /training.md

Alsamir

Add Hunyuan-style repository documentation and tooling

91dc4aa verified about 1 month ago

preview code

Raw History Blame Contribute Delete

2.26 kB

# Training guide

Abjad fine-tuning uses MLX-VLM LoRA on Apple Silicon. The repository keeps previous adapters and datasets so old
experiments remain reproducible; new runs should use a new output name instead of overwriting a previous adapter.

## 1. Prepare data

Start with manually verified JSONL. Copy `configs/data_list.example.txt` and edit the paths for the run. For a
small correction run, a single JSONL file is enough:

```bash
cp configs/data_list.example.txt configs/data_list.local.txt
```

Review the rows before training, especially Arabic names, Arabic-Indic digits, tables, stamps, and signatures.

## 2. Run LoRA

The low-level entry point is:

```bash
.venv/bin/python run_lora_training.py \
  --model mlx-community/Qwen3-VL-4B-Instruct-4bit \
  --dataset dataset/abjad_0_2/train_compact.jsonl \
  --output adapters/abjad_0_3_domain.safetensors \
  --iters 300 \
  --image-size 224 \
  --max-seq-length 1024
```

The command writes `training_status.json` and `logs/lora_training.log`. Checkpoints are saved during the run.
Use `--resume-adapter` only when the new run intentionally continues the same adapter lineage.

## 3. Verify before fusion

Evaluate on pages that were not used for training. Look for:

- omitted or duplicated phrases;
- Arabic and Western digit confusion;
- wrong names or diacritics;
- reading-order errors in columns and tables;
- watermark, stamp, and signature contamination;
- output that stops early because of the token limit.

Do not fuse an adapter only because the training loss decreased. Keep the best checkpoint based on held-out OCR
quality and the document types that matter to the deployment.

## 4. Fuse for standalone inference

The current fused model was created from the final selected adapter and can be run with `--no-adapter`. Keep the
adapter backup separately so the fusion can be audited or repeated.

## 5. Publishing checklist

Before uploading a model or dataset:

1. Remove private filesystem paths and tokens.
2. Confirm every source document may be redistributed.
3. State the base model, training method, cumulative row count, and overlap caveat.
4. Include a test example and known limitations.
5. Never claim zero OCR errors; report evaluation results on a fixed held-out set.

	# Training guide

	Abjad fine-tuning uses MLX-VLM LoRA on Apple Silicon. The repository keeps previous adapters and datasets so old
	experiments remain reproducible; new runs should use a new output name instead of overwriting a previous adapter.

	## 1. Prepare data

	Start with manually verified JSONL. Copy `configs/data_list.example.txt` and edit the paths for the run. For a
	small correction run, a single JSONL file is enough:

	```bash
	cp configs/data_list.example.txt configs/data_list.local.txt
	```

	Review the rows before training, especially Arabic names, Arabic-Indic digits, tables, stamps, and signatures.

	## 2. Run LoRA

	The low-level entry point is:

	```bash
	.venv/bin/python run_lora_training.py \
	--model mlx-community/Qwen3-VL-4B-Instruct-4bit \
	--dataset dataset/abjad_0_2/train_compact.jsonl \
	--output adapters/abjad_0_3_domain.safetensors \
	--iters 300 \
	--image-size 224 \
	--max-seq-length 1024
	```

	The command writes `training_status.json` and `logs/lora_training.log`. Checkpoints are saved during the run.
	Use `--resume-adapter` only when the new run intentionally continues the same adapter lineage.

	## 3. Verify before fusion

	Evaluate on pages that were not used for training. Look for:

	- omitted or duplicated phrases;
	- Arabic and Western digit confusion;
	- wrong names or diacritics;
	- reading-order errors in columns and tables;
	- watermark, stamp, and signature contamination;
	- output that stops early because of the token limit.

	Do not fuse an adapter only because the training loss decreased. Keep the best checkpoint based on held-out OCR
	quality and the document types that matter to the deployment.

	## 4. Fuse for standalone inference

	The current fused model was created from the final selected adapter and can be run with `--no-adapter`. Keep the
	adapter backup separately so the fusion can be audited or repeated.

	## 5. Publishing checklist

	Before uploading a model or dataset:

	1. Remove private filesystem paths and tokens.
	2. Confirm every source document may be redistributed.
	3. State the base model, training method, cumulative row count, and overlap caveat.
	4. Include a test example and known limitations.
	5. Never claim zero OCR errors; report evaluation results on a fixed held-out set.