Instructions to use Arijit-09/RoadXpert_AI-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Arijit-09/RoadXpert_AI-v1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="Arijit-09/RoadXpert_AI-v1")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Arijit-09/RoadXpert_AI-v1")
model = AutoModelForMultimodalLM.from_pretrained("Arijit-09/RoadXpert_AI-v1")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Arijit-09/RoadXpert_AI-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Arijit-09/RoadXpert_AI-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Arijit-09/RoadXpert_AI-v1",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Arijit-09/RoadXpert_AI-v1

SGLang

How to use Arijit-09/RoadXpert_AI-v1 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 "Arijit-09/RoadXpert_AI-v1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Arijit-09/RoadXpert_AI-v1",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "Arijit-09/RoadXpert_AI-v1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Arijit-09/RoadXpert_AI-v1",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use Arijit-09/RoadXpert_AI-v1 with Docker Model Runner:
```
docker model run hf.co/Arijit-09/RoadXpert_AI-v1
```

RoadXpert_AI-v1 / config.json

Arijit-09

Duplicate from deepcogito/cogito-v2-preview-llama-109B-MoE

6f932ea verified 8 months ago

Raw

History Blame

4.43 kB

	{
	"architectures": [
	"Llama4ForConditionalGeneration"
	],
	"boi_token_index": 200080,
	"eoi_token_index": 200081,
	"image_token_index": 200092,
	"model_type": "llama4",
	"text_config": {
	"attention_bias": false,
	"attention_chunk_size": 8192,
	"attention_dropout": 0.0,
	"attn_scale": 0.1,
	"attn_temperature_tuning": true,
	"bos_token_id": 200000,
	"eos_token_id": [
	200001,
	200007,
	200008
	],
	"floor_scale": 8192,
	"for_llm_compressor": false,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 5120,
	"initializer_range": 0.02,
	"interleave_moe_layer_step": 1,
	"intermediate_size": 8192,
	"intermediate_size_mlp": 16384,
	"layer_types": [
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention",
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention",
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention",
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention",
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention",
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention",
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention",
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention",
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention",
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention",
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention",
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention"
	],
	"max_position_embeddings": 262144,
	"model_type": "llama4_text",
	"moe_layers": [
	0,
	1,
	2,
	3,
	4,
	5,
	6,
	7,
	8,
	9,
	10,
	11,
	12,
	13,
	14,
	15,
	16,
	17,
	18,
	19,
	20,
	21,
	22,
	23,
	24,
	25,
	26,
	27,
	28,
	29,
	30,
	31,
	32,
	33,
	34,
	35,
	36,
	37,
	38,
	39,
	40,
	41,
	42,
	43,
	44,
	45,
	46,
	47
	],
	"no_rope_layers": [
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0
	],
	"num_attention_heads": 40,
	"num_experts_per_tok": 1,
	"num_hidden_layers": 48,
	"num_key_value_heads": 8,
	"num_local_experts": 16,
	"output_router_logits": false,
	"pad_token_id": 200018,
	"rms_norm_eps": 1e-05,
	"rope_scaling": {
	"factor": 16.0,
	"high_freq_factor": 1.0,
	"low_freq_factor": 1.0,
	"original_max_position_embeddings": 8192,
	"rope_type": "llama3"
	},
	"rope_theta": 500000.0,
	"router_aux_loss_coef": 0.001,
	"router_jitter_noise": 0.0,
	"torch_dtype": "bfloat16",
	"use_cache": true,
	"use_qk_norm": true,
	"vocab_size": 201135
	},
	"tie_word_embeddings": false,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.53.0",
	"vision_config": {
	"attention_dropout": 0.0,
	"hidden_act": "gelu",
	"hidden_size": 1408,
	"image_size": 336,
	"initializer_range": 0.02,
	"intermediate_size": 5632,
	"model_type": "llama4_vision_model",
	"multi_modal_projector_bias": false,
	"norm_eps": 1e-05,
	"num_attention_heads": 16,
	"num_channels": 3,
	"num_hidden_layers": 34,
	"patch_size": 14,
	"pixel_shuffle_ratio": 0.5,
	"projector_dropout": 0.0,
	"projector_input_dim": 4096,
	"projector_output_dim": 4096,
	"rope_theta": 10000,
	"vision_feature_layer": -1,
	"vision_feature_select_strategy": "default",
	"vision_output_dim": 4096
	}
	}