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

This is a tiny version of thinkingmachines/Inkling created for testing and development.

Model Details

Base Model: thinkingmachines/Inkling
Architecture: inkling_mm_model (InklingForConditionalGeneration)
Total Parameters: 0.644B
Activated Parameters: 0.602B

Configuration Changes

The following parameters were reduced from the original model:

Parameter	Original	Tiny
`text_config.num_hidden_layers`	66	12
`text_config.hidden_size`	6144	1024
`text_config.intermediate_size`	24576	4096
`text_config.num_attention_heads`	64	8
`text_config.num_key_value_heads`	8	2
`text_config.swa_num_attention_heads`	64	8
`text_config.swa_num_key_value_heads`	16	4
`text_config.n_routed_experts`	256	8
`text_config.num_experts_per_tok`	6	4
`text_config.moe_intermediate_size`	3072	512
`text_config.num_mtp_layers`	8	1
`vision_config.n_layers`	4	1
`vision_config.hidden_size`	1024	256
`vision_config.decoder_dmodel`	6144	1024
`audio_config.decoder_dmodel`	6144	1024

Layer type patterns are preserved: 2 repetitions of [5× hybrid_sliding + 1× hybrid], with the first 2 MLP layers as dense and the rest as sparse (MoE).

Checkpoint Structure

Single safetensors file (model.safetensors). Key naming matches the original checkpoint format (model.llm.*, model.audio.*, model.visual.*).

Usage

from transformers.models.inkling import InklingForConditionalGeneration
from transformers import AutoTokenizer

model = InklingForConditionalGeneration.from_pretrained("inference-optimization/Inkling-0.6B-A0.6B", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("inference-optimization/Inkling-0.6B-A0.6B")

input_ids = tokenizer("According to all known laws", return_tensors="pt").input_ids.to(model.device)
output = model.generate(input_ids, max_new_tokens=20)
print(tokenizer.decode(output[0]))

Creation Process

This model was created using the llm-compressor create-tiny-model claude skill.

Config inspected via inspect_config.py
Tiny model created via modified save_tiny_model.py — all-zero params fixed post init_weights
Fine-tuned on copypasta dataset; reached perplexity 1.45 (target: ≤3.0) at lr=5e-4
Checkpoint structure validated against original HuggingFace index
Inference validated via validate_tiny_model.py

Notes

The embed_tokens weights require explicit re-initialization after init_weights() (they initialize to zero in this architecture). The save script applies a fixup: any all-zero, non-finite, or extreme-valued parameter is re-initialized with kaiming_uniform / normal / ones as appropriate.
MTP (Multi-Token Prediction) layers present in the original checkpoint (model.mtp.*) are not included, as InklingForConditionalGeneration does not expose them through its standard interface.
Validation output: Success: 1.4451 <= 10.0

Downloads last month: 185

Safetensors

Model size

0.6B params

Tensor type

F32

Model tree for inference-optimization/Inkling-0.6B-A0.6B

Base model

thinkingmachines/Inkling

Finetuned

(6)

this model

Collection including inference-optimization/Inkling-0.6B-A0.6B

Tiny Models

Collection

Tiny models used for testing • 10 items • Updated about 13 hours ago