Instructions to use tiny-random/inkling-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiny-random/inkling-2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="tiny-random/inkling-2", trust_remote_code=True)
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("tiny-random/inkling-2", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("tiny-random/inkling-2", trust_remote_code=True, device_map="auto")
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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tiny-random/inkling-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiny-random/inkling-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiny-random/inkling-2",
		"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/tiny-random/inkling-2

SGLang

How to use tiny-random/inkling-2 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 "tiny-random/inkling-2" \
    --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": "tiny-random/inkling-2",
		"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 "tiny-random/inkling-2" \
        --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": "tiny-random/inkling-2",
		"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 tiny-random/inkling-2 with Docker Model Runner:
```
docker model run hf.co/tiny-random/inkling-2
```

inkling-2 / config.json

yujiepan

Restore independent Inkling 2 embedding and output head

4c88f31 verified about 6 hours ago

Raw History Blame Contribute Delete

2.51 kB

{
  "architectures": [
    "Inkling2ForConditionalGeneration"
  ],
  "model_type": "inkling2",
  "eos_token_id": 200006,
  "text_config": {
    "model_max_length": 1048576,
    "torch_dtype": "bfloat16",
    "hidden_size": 32,
    "num_hidden_layers": 12,
    "vocab_size": 201024,
    "num_attention_heads": 24,
    "num_key_value_heads": 4,
    "head_dim": 32,
    "d_rel": 16,
    "rel_extent": 1024,
    "q_bias": false,
    "o_bias": false,
    "log_scaling_n_floor": 128000,
    "log_scaling_alpha": 0.1,
    "rms_norm_eps": 1e-06,
    "pre_norm_pre_affine": false,
    "final_norm_pre_affine": false,
    "use_value_norm_no_gamma": true,
    "qk_l2_clip_threshold": 22.627416997969522,
    "rel_l2_clip_threshold": 8.0,
    "local_layer_ids": [
      0,
      1,
      2,
      3,
      4,
      6,
      7,
      8,
      9,
      10
    ],
    "sconv_kernel_size": 4,
    "unpadded_vocab_size": 200058,
    "final_logit_softcapping": 30.0,
    "swa_head_dim": 32,
    "swa_num_attention_heads": 24,
    "swa_num_key_value_heads": 4,
    "sliding_window_size": 1024,
    "n_layers_per_attn_res_block": 6,
    "attn_res_normalize_values": true,
    "n_routed_experts": 96,
    "num_experts_per_tok": 8,
    "n_shared_experts": 0,
    "intermediate_size": 32,
    "mlp_gate_softcap": 4.0,
    "mlp_up_softcap": 25.0,
    "route_scale": 8.0,
    "use_gate_bias": true,
    "tie_word_embeddings": false
  },
  "vision_config": {
    "temporal_patch_size": 2,
    "native_patch_size": 20,
    "adapter_merge_size": 2,
    "projection_hidden_dim": 32,
    "projector_bias": false,
    "hidden_size": 32,
    "num_hidden_layers": 4,
    "num_attention_heads": 4,
    "mlp_ratio": 4.0,
    "posemb_grid_size": 32,
    "layer_norm_eps": 1e-05,
    "text_hidden_size": 32
  },
  "mtp_config": {
    "hidden_size": 32,
    "num_hidden_layers": 5,
    "num_attention_heads": 24,
    "num_key_value_heads": 4,
    "head_dim": 32,
    "intermediate_size": 128,
    "max_position_embeddings": 1048576,
    "torch_dtype": "bfloat16",
    "q_bias": false,
    "o_bias": false,
    "rms_norm_eps": 1e-06,
    "rope_theta": 1000000.0,
    "local_layer_ids": [
      0,
      1,
      3,
      4
    ],
    "sliding_window_size": 1024,
    "block_size": 8,
    "markov_rank": 8,
    "markov_head_type": "rnn_hidden",
    "target_layer_ids": [
      5,
      12
    ]
  },
  "tie_word_embeddings": false,
  "auto_map": {
    "AutoModelForImageTextToText": "modeling_inkling2_tiny.Inkling2TinyForConditionalGeneration"
  }
}

	{
	"architectures": [
	"Inkling2ForConditionalGeneration"
	],
	"model_type": "inkling2",
	"eos_token_id": 200006,
	"text_config": {
	"model_max_length": 1048576,
	"torch_dtype": "bfloat16",
	"hidden_size": 32,
	"num_hidden_layers": 12,
	"vocab_size": 201024,
	"num_attention_heads": 24,
	"num_key_value_heads": 4,
	"head_dim": 32,
	"d_rel": 16,
	"rel_extent": 1024,
	"q_bias": false,
	"o_bias": false,
	"log_scaling_n_floor": 128000,
	"log_scaling_alpha": 0.1,
	"rms_norm_eps": 1e-06,
	"pre_norm_pre_affine": false,
	"final_norm_pre_affine": false,
	"use_value_norm_no_gamma": true,
	"qk_l2_clip_threshold": 22.627416997969522,
	"rel_l2_clip_threshold": 8.0,
	"local_layer_ids": [
	0,
	1,
	2,
	3,
	4,
	6,
	7,
	8,
	9,
	10
	],
	"sconv_kernel_size": 4,
	"unpadded_vocab_size": 200058,
	"final_logit_softcapping": 30.0,
	"swa_head_dim": 32,
	"swa_num_attention_heads": 24,
	"swa_num_key_value_heads": 4,
	"sliding_window_size": 1024,
	"n_layers_per_attn_res_block": 6,
	"attn_res_normalize_values": true,
	"n_routed_experts": 96,
	"num_experts_per_tok": 8,
	"n_shared_experts": 0,
	"intermediate_size": 32,
	"mlp_gate_softcap": 4.0,
	"mlp_up_softcap": 25.0,
	"route_scale": 8.0,
	"use_gate_bias": true,
	"tie_word_embeddings": false
	},
	"vision_config": {
	"temporal_patch_size": 2,
	"native_patch_size": 20,
	"adapter_merge_size": 2,
	"projection_hidden_dim": 32,
	"projector_bias": false,
	"hidden_size": 32,
	"num_hidden_layers": 4,
	"num_attention_heads": 4,
	"mlp_ratio": 4.0,
	"posemb_grid_size": 32,
	"layer_norm_eps": 1e-05,
	"text_hidden_size": 32
	},
	"mtp_config": {
	"hidden_size": 32,
	"num_hidden_layers": 5,
	"num_attention_heads": 24,
	"num_key_value_heads": 4,
	"head_dim": 32,
	"intermediate_size": 128,
	"max_position_embeddings": 1048576,
	"torch_dtype": "bfloat16",
	"q_bias": false,
	"o_bias": false,
	"rms_norm_eps": 1e-06,
	"rope_theta": 1000000.0,
	"local_layer_ids": [
	0,
	1,
	3,
	4
	],
	"sliding_window_size": 1024,
	"block_size": 8,
	"markov_rank": 8,
	"markov_head_type": "rnn_hidden",
	"target_layer_ids": [
	5,
	12
	]
	},
	"tie_word_embeddings": false,
	"auto_map": {
	"AutoModelForImageTextToText": "modeling_inkling2_tiny.Inkling2TinyForConditionalGeneration"
	}
	}