---
license: mit
base_model:
- thinkingmachines/Inkling
library_name: transformers
---

# Inkling-0.6B-A0.6B

This is a tiny version of [thinkingmachines/Inkling](https://huggingface.co/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

```python
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.

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