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:

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.

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