Instructions to use AyoubChLin/deepseek_ocr2_arabic_jsonify with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AyoubChLin/deepseek_ocr2_arabic_jsonify with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="AyoubChLin/deepseek_ocr2_arabic_jsonify", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("AyoubChLin/deepseek_ocr2_arabic_jsonify", trust_remote_code=True, device_map="auto")

PEFT
How to use AyoubChLin/deepseek_ocr2_arabic_jsonify with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AyoubChLin/deepseek_ocr2_arabic_jsonify with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AyoubChLin/deepseek_ocr2_arabic_jsonify"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AyoubChLin/deepseek_ocr2_arabic_jsonify",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AyoubChLin/deepseek_ocr2_arabic_jsonify

SGLang

How to use AyoubChLin/deepseek_ocr2_arabic_jsonify with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "AyoubChLin/deepseek_ocr2_arabic_jsonify" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AyoubChLin/deepseek_ocr2_arabic_jsonify",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "AyoubChLin/deepseek_ocr2_arabic_jsonify" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AyoubChLin/deepseek_ocr2_arabic_jsonify",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use AyoubChLin/deepseek_ocr2_arabic_jsonify 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 AyoubChLin/deepseek_ocr2_arabic_jsonify 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 AyoubChLin/deepseek_ocr2_arabic_jsonify to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AyoubChLin/deepseek_ocr2_arabic_jsonify to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="AyoubChLin/deepseek_ocr2_arabic_jsonify",
    max_seq_length=2048,
)

Docker Model Runner
How to use AyoubChLin/deepseek_ocr2_arabic_jsonify with Docker Model Runner:
```
docker model run hf.co/AyoubChLin/deepseek_ocr2_arabic_jsonify
```

deepseek_ocr2_arabic_jsonify / config.json

AyoubChLin

Update config.json

3753561 verified 5 months ago

Raw

History Blame Contribute Delete

3.58 kB

	{
	"architectures": [
	"DeepseekOCR2ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"auto_map": {
	"AutoConfig": "modeling_deepseekocr2.DeepseekOCR2Config",
	"AutoModel": "modeling_deepseekocr2.DeepseekOCR2ForCausalLM"
	},
	"aux_loss_alpha": 0.001,
	"bos_token_id": 0,
	"candidate_resolutions": [
	[
	1024,
	1024
	]
	],
	"torch_dtype": "bfloat16",
	"eos_token_id": 1,
	"first_k_dense_replace": 1,
	"global_view_pos": "head",
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 1280,
	"initializer_range": 0.02,
	"intermediate_size": 6848,
	"kv_lora_rank": null,
	"language_config": {
	"architectures": [
	"DeepseekV2ForCausalLM"
	],
	"auto_map": {
	"AutoConfig": "configuration_deepseekv2.DeepseekV2Config",
	"AutoModel": "modeling_deepseek.DeepseekV2Model",
	"AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
	},
	"bos_token_id": 0,
	"eos_token_id": 1,
	"first_k_dense_replace": 1,
	"hidden_size": 1280,
	"intermediate_size": 6848,
	"kv_lora_rank": null,
	"lm_head": true,
	"max_position_embeddings": 8192,
	"moe_intermediate_size": 896,
	"n_group": 1,
	"n_routed_experts": 64,
	"n_shared_experts": 2,
	"num_attention_heads": 10,
	"num_experts_per_tok": 6,
	"num_hidden_layers": 12,
	"num_key_value_heads": 10,
	"q_lora_rank": null,
	"qk_nope_head_dim": 0,
	"qk_rope_head_dim": 0,
	"rm_head": false,
	"topk_group": 1,
	"topk_method": "greedy",
	"torch_dtype": "bfloat16",
	"use_mla": false,
	"v_head_dim": 0,
	"vocab_size": 129280
	},
	"lm_head": true,
	"max_position_embeddings": 8192,
	"mlp_bias": false,
	"model_name": "deepseek_ocr2_arabic_jsonify",
	"model_type": "DeepseekOCR2",
	"moe_intermediate_size": 896,
	"n_group": 1,
	"n_routed_experts": 64,
	"n_shared_experts": 2,
	"norm_topk_prob": false,
	"num_attention_heads": 10,
	"num_experts_per_tok": 6,
	"num_hidden_layers": 12,
	"num_key_value_heads": 10,
	"pad_token_id": 2,
	"projector_config": {
	"input_dim": 896,
	"model_type": "mlp_projector",
	"n_embed": 1280,
	"projector_type": "linear"
	},
	"q_lora_rank": null,
	"qk_nope_head_dim": 0,
	"qk_rope_head_dim": 0,
	"rm_head": false,
	"rms_norm_eps": 1e-06,
	"rope_scaling": null,
	"rope_theta": 10000.0,
	"routed_scaling_factor": 1.0,
	"seq_aux": true,
	"tie_word_embeddings": false,
	"tile_tag": "2D",
	"topk_group": 1,
	"topk_method": "greedy",
	"unsloth_version": "2026.3.15",
	"use_cache": true,
	"use_mla": false,
	"v_head_dim": 0,
	"vision_config": {
	"image_size": 1024,
	"mlp_ratio": 3.7362,
	"model_name": "deepencoderv2",
	"model_type": "vision",
	"width": {
	"qwen2-0-5b": {
	"dim": 896
	},
	"sam_vit_b": {
	"downsample_channels": [
	512,
	1024
	],
	"global_attn_indexes": [
	2,
	5,
	8,
	11
	],
	"heads": 12,
	"layers": 12,
	"width": 768
	}
	}
	},
	"vocab_size": 129280
	}