Transformers
Safetensors
nano_deep_reasoner_hypermini
causal-lm
decoder-only
reasoning
deep-reasoning
recurrent-transformer
adaptive-computation
chain-of-thought
adaptive-reasoning
Instructions to use WithinUsAI/Nano.Deep.Reasoner.11m-HyperMini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WithinUsAI/Nano.Deep.Reasoner.11m-HyperMini with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import HyperMiniReasoner model = HyperMiniReasoner.from_pretrained("WithinUsAI/Nano.Deep.Reasoner.11m-HyperMini", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from WithinUsAI/Nano.Deep.Reasoner.11m-HyperMini: direct link, hf CLI and curl.
- Browser
- Download file 1.74 kB
-
https://huggingface.co/WithinUsAI/Nano.Deep.Reasoner.11m-HyperMini/resolve/main/README.md
- Command line
-
hf download hf://WithinUsAI/Nano.Deep.Reasoner.11m-HyperMini/README.md
-
curl -L -o README.md https://huggingface.co/WithinUsAI/Nano.Deep.Reasoner.11m-HyperMini/resolve/main/README.md
1.74 kB
metadata
license: mit
library_name: transformers
tags:
- causal-lm
- decoder-only
- reasoning
- deep-reasoning
- recurrent-transformer
- adaptive-computation
- chain-of-thought
- adaptive-reasoning
Nano.Deep.Reasoner.11m-HyperMini
An approximately 11,094,003-parameter decoder-only adaptive recurrent reasoning language model.
Architecture
- Parameters: 11,094,003
- Context: 1096
- Vocabulary: 16,000
- Hidden size: 240
- Base Transformer blocks: 6
- Attention heads: 8
- Head dimension: 30
- Intermediate size: 1072
- Shared recurrent reasoning block
- Learned latent reasoning memory: 8 tokens
- Adaptive reasoning depth: 2-16
- Gated recurrent memory updates
- Adaptive halting controller
- Verification head
- Revision head
- RoPE
- Tied input/output embeddings
- Padding-aware causal attention
- Explicit padded-state suppression
Reasoning tokens
Training
Dataset:
Plans11/Organized_PreTrain_1k_Context
Each session contains up to 200,000 NEW examples.
Examples are protected by SHA-256 hashes.
Session reservations are committed before training so a hard Kaggle interruption cannot cause the same reserved examples to be selected again.
Resume safety
The checkpoint contains:
- model.safetensors
- optimizer.pt
- rng_state.pt
- training_state.json
- example_ledger.json
- tokenizer.json
- tokenizer_config.json
- token_id_manifest.json
- config.json
Dataset fingerprint and tokenizer artifact hashes are verified before resume.
Current state
Completed sessions: 5
Unique examples reserved/trained: 200,000
Unique completed examples: 460,000
Global optimizer steps: 7,189
Last session loss: 0.17293200694084168