|
Download README.md from North-ML1/ink: direct link, hf CLI and curl.
- Browser
- Download file 1.99 kB
-
https://huggingface.co/North-ML1/ink/resolve/main/README.md
- Command line
-
hf download hf://North-ML1/ink/README.md
-
curl -L -o README.md https://huggingface.co/North-ML1/ink/resolve/main/README.md
1.99 kB
| license: apache-2.0 | |
| tags: | |
| - north-ml | |
| - flare-1 | |
| - deltanet | |
| - hybrid-attention | |
| thumbnail: banner.png | |
| # Ink — North ML Flare-1 (~725M) | |
| The smallest Flare-1 tier: Qwen3.5-derived gated **DeltaNet + GQA hybrid** | |
| backbone with **AgentRegisters** — persistent learned state slots for | |
| agent-style memory. This is the full-precision training checkpoint | |
| (HF `transformers` format). The production 8-bit Kestrel build with the | |
| learned router, Fiber memory trunk, and search pipeline is at | |
| [North-ML1/Ink-1](https://huggingface.co/North-ML1/Ink-1). | |
| ## Benchmarks (measured, same harness — Modal L4, greedy, Nov-2025) | |
| | Model | ARC-C | MMLU | GSM8K | HumanEval | | |
| |---|---|---|---|---| | |
| | **ink (725M)** | 63.8% | 32.0% | 30.0% | 37.5% | | |
| | fiber-lite (1.6B) | 72.9% | 38.0% | 16.0% | 37.5% | | |
| | fiber-pro (1.6B) | 80.9% | 40.0% | 14.0% | 48.4% | | |
| | Qwen3-0.6B (raw) | 49.2% | 29.0% | 4.0% | 4.7% | | |
| | Qwen3-1.7B (raw) | 72.9% | 39.5% | 43.0% | 68.8% | | |
| | SmolLM3-3B (raw) | 77.9% | 36.0% | 51.0% | 71.9% | | |
| Subsets: ARC-C n=199, MMLU n=200, GSM8K n=100, HumanEval n=64. Honest read: | |
| strongest size-adjusted scores on knowledge MC in this lineup; trails the | |
| newer 1.7B-3B models on math and code. | |
| ## Specs | |
| | | | | |
| |---|---| | |
| | Parameters | ~725M (565M backbone + 158M Fiber trunk + registers + bridge) | | |
| | Layers | 24 | | |
| | Hidden | 1024 | | |
| | Attention | GQA 8 heads / 2 KV, DeltaNet:GQA = 3:1 | | |
| | Context | 262,144 tokens | | |
| | Vocab | 65,536 | | |
| ## Interactive chat | |
| ```bash | |
| pip install torch transformers safetensors huggingface_hub | |
| python3 chat.py --model North-ML1/ink | |
| ``` | |
| `chat.py` (in this repo) auto-downloads the weights, attaches the | |
| AgentRegisters, and starts a REPL with optional two-phase thinking. | |
| ## Links | |
| - Architecture report: [Flare-1 paper](https://huggingface.co/spaces/North-ML1/flare-1-paper) | |
| - Runtime artifacts: [Ink-1](https://huggingface.co/North-ML1/Ink-1) · [Fiber](https://huggingface.co/North-ML1/Fiber) · [Fiber-pro](https://huggingface.co/North-ML1/Fiber-pro) | |