Instructions to use inference-optimization/Inkling-0.6B-A0.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inference-optimization/Inkling-0.6B-A0.6B with Transformers:

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

pipe = pipeline("image-text-to-text", model="inference-optimization/Inkling-0.6B-A0.6B")
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("inference-optimization/Inkling-0.6B-A0.6B")
model = AutoModelForMultimodalLM.from_pretrained("inference-optimization/Inkling-0.6B-A0.6B")
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 inference-optimization/Inkling-0.6B-A0.6B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inference-optimization/Inkling-0.6B-A0.6B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "inference-optimization/Inkling-0.6B-A0.6B",
		"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/inference-optimization/Inkling-0.6B-A0.6B

SGLang

How to use inference-optimization/Inkling-0.6B-A0.6B 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 "inference-optimization/Inkling-0.6B-A0.6B" \
    --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": "inference-optimization/Inkling-0.6B-A0.6B",
		"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 "inference-optimization/Inkling-0.6B-A0.6B" \
        --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": "inference-optimization/Inkling-0.6B-A0.6B",
		"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 inference-optimization/Inkling-0.6B-A0.6B with Docker Model Runner:
```
docker model run hf.co/inference-optimization/Inkling-0.6B-A0.6B
```

Inkling-0.6B-A0.6B / config.json

kylesayrs

Upload folder using huggingface_hub

0a1dd46 verified about 24 hours ago

Raw

History Blame

3.37 kB

	{
	"architectures": [
	"InklingForConditionalGeneration"
	],
	"audio_bos_token_id": 200020,
	"audio_config": {
	"audio_mode": "dmel",
	"bias": false,
	"decoder_dmodel": 1024,
	"dmel_max_value": 2.0,
	"dmel_min_value": -7.0,
	"dtype": "float32",
	"initializer_range": 0.02,
	"mel_vocab_size": 16,
	"model_type": "inkling_audio",
	"n_mel_bins": 80,
	"rms_norm_eps": 1e-06,
	"text_hidden_size": 1024,
	"use_audio_norm": true
	},
	"audio_token_id": 200053,
	"dtype": "float32",
	"eos_token_id": 200006,
	"image_bos_token_id": 200005,
	"image_token_id": 200054,
	"model_type": "inkling_mm_model",
	"mtp_config": {
	"chain_hidden_post_norm": false,
	"local_layer_ids": [
	0
	],
	"num_nextn_predict_layers": 1
	},
	"text_config": {
	"attention_dropout": 0.0,
	"bos_token_id": 1,
	"chain_hidden_post_norm": false,
	"conv_kernel_size": 4,
	"d_rel": 16,
	"dtype": "float32",
	"eos_token_id": 2,
	"final_logit_softcapping": null,
	"gate_activation": "sigmoid",
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 1024,
	"initializer_range": 0.02,
	"intermediate_size": 4096,
	"layer_types": [
	"hybrid_sliding",
	"hybrid_sliding",
	"hybrid_sliding",
	"hybrid_sliding",
	"hybrid_sliding",
	"hybrid",
	"hybrid_sliding",
	"hybrid_sliding",
	"hybrid_sliding",
	"hybrid_sliding",
	"hybrid_sliding",
	"hybrid"
	],
	"local_layer_ids": [
	0,
	1,
	2,
	3,
	4,
	6,
	7,
	8,
	9,
	10
	],
	"log_scaling_alpha": 0.1,
	"log_scaling_n_floor": 128000,
	"logits_mup_width_multiplier": 24.0,
	"max_position_embeddings": 1048576,
	"mlp_layer_types": [
	"dense",
	"dense",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse"
	],
	"model_type": "inkling_text",
	"moe_intermediate_size": 512,
	"mtp_hidden_states_first": true,
	"mtp_local_layer_ids": [
	0
	],
	"n_routed_experts": 8,
	"n_shared_experts": 2,
	"norm_after_topk": true,
	"num_attention_heads": 8,
	"num_experts_per_tok": 4,
	"num_hidden_layers": 12,
	"num_key_value_heads": 2,
	"num_mtp_layers": 1,
	"number_of_conv_states": 4,
	"o_bias": false,
	"pad_token_id": null,
	"q_bias": false,
	"rel_extent": 1024,
	"rms_norm_eps": 1e-06,
	"rms_norm_eps_moe_gate": 1e-06,
	"route_scale": 8.0,
	"shared_expert_sink": true,
	"sliding_window_size": 512,
	"swa_head_dim": 128,
	"swa_num_attention_heads": 8,
	"swa_num_key_value_heads": 4,
	"unpadded_vocab_size": 200058,
	"use_embed_norm": true,
	"use_gate_bias": true,
	"use_global_scale": true,
	"use_sconv": true,
	"vocab_size": 201024
	},
	"transformers_version": "5.15.0.dev0",
	"vision_config": {
	"decoder_dmodel": 1024,
	"dtype": "float32",
	"hidden_size": 256,
	"initializer_range": 0.02,
	"model_type": "inkling_vision",
	"n_channels": 3,
	"n_layers": 1,
	"num_attention_heads": 4,
	"num_channels": 3,
	"patch_size": 40,
	"rms_norm_eps": 1e-06,
	"temporal_patch_size": 2,
	"text_hidden_size": 1024,
	"use_vision_norm": true,
	"vision_encoder_type": "hmlp"
	}
	}