docs(readme): correct hardware (RTX 3080 Ti, bf16, paged_adamw_8bit) + project naming (QuantumAI Blockchain is the chain; Qubitcoin/QBC is the currency)

README.md

@@ -73,11 +73,11 @@ model-index:
             name: accuracy
 ---
 
-# Aether v5.2 LoRA — Qubitcoin Domain Adapter
+# Aether v5.2 LoRA — QuantumAI Blockchain Domain Adapter
 
 A LoRA fine-tune of [`Qwen/Qwen2.5-7B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
 on the Aether curated corpus — text grounded in the
-[Qubitcoin](https://qbc.network) protocol, quantum + AI research, and adjacent
+[QuantumAI Blockchain](https://qbc.network) (which issues the Qubitcoin / QBC currency), quantum + AI research, and adjacent
 domains the Aether Mind on-chain knowledge system specializes in.
 
 This is the **v5.2 release** of the Aether adapter line, the most recent
@@ -132,13 +132,13 @@ base and the prior `aether-v5.1.1` adapter for delta comparison.
 This adapter is intended for:
 
 - **On-chain Aether research.** Generating reasoning traces against
-  the Qubitcoin / Aether knowledge graph for Proof-of-Thought
+  the QuantumAI Blockchain / Aether knowledge graph for Proof-of-Thought
   attestation. The model has the protocol context required to
   answer questions about Substrate pallets, VQE mining, the Sephirot
   cognitive architecture, HMS-Phi, and the wider chain ecosystem.
 - **Domain Q&A.** Quantum computing fundamentals, post-quantum
   cryptography (Dilithium, ML-KEM), and the specific design choices
-  of the Qubitcoin chain.
+  of the QuantumAI Blockchain.
 - **Distillation upstream.** Generate teacher outputs for the
   smaller on-chain Aether (a Qwen2.5-0.5B variant) to learn from.
 - **General reasoning** with a modest bias toward step-by-step
@@ -161,19 +161,19 @@ The base model (`Qwen/Qwen2.5-7B-Instruct`) inherits Qwen's known
 biases — see [the upstream model card](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct).
 The LoRA adapter:
 
-- **Amplifies the Qubitcoin worldview.** The training data is
+- **Amplifies the QuantumAI Blockchain worldview.** The training data is
   intentionally curated around the chain's design choices (golden-
   ratio economics, SUSY-inspired consensus framing, the Sephirot
-  cognitive overlay). Prompts that invite the model to compare
-  Qubitcoin against alternatives will lean toward the curated
-  narrative. This is by design — disclose if you re-publish in a
+  cognitive overlay). Prompts that invite the model to compare QBC / the chain
+  against alternatives will lean toward the curated narrative. This is by design — disclose if you re-publish in a
   comparison context.
 - **Does not improve safety.** TruthfulQA went up 5.5pp but that's
   one metric; we have not measured refusal rates, jailbreak
   resistance, or political-belief bias delta.
-- **Was trained CPU-only on a residential box.** The configured
-  2-epoch run was cut to ~step 3200 by host availability. A longer
-  run on GPU would plausibly show larger gains.
+- **The configured 2-epoch run was cut to ~step 3080–3200 by host
+  availability** (out of 4406 configured). A complete 2-epoch run
+  would plausibly show larger gains; this checkpoint is the longest
+  contiguous training we have.
 
 ## How to use
 
@@ -207,9 +207,9 @@ merged.save_pretrained("./aether-v5.2-merged")
 
 ## Training details
 
-- **Hardware:** Intel WSL2 box, CPU-only training (slow but verifiable).
+- **Hardware:** NVIDIA RTX 3080 Ti (12 GB), 4-bit quantization (bnb-NF4), bf16 mixed precision.
 - **Trainer:** [Axolotl](https://github.com/axolotl-ai-cloud/axolotl) wrapping 🤗 transformers / PEFT.
-- **Optimizer:** Default AdamW.
+- **Optimizer:** `paged_adamw_8bit` (bitsandbytes paged optimizer, low VRAM footprint).
 - **Schedule:** linear warmup 100 steps → cosine decay.
 - **Learning rate:** `1.0e-4`.
 - **Micro batch:** 1, gradient accumulation: 8.
@@ -217,13 +217,13 @@ merged.save_pretrained("./aether-v5.2-merged")
 
 ### Carbon emissions
 
-Trained CPU-only on a single Intel workstation. We did not run a
-[CodeCarbon](https://github.com/mlco2/codecarbon) tracker on this
-run, so the precise emissions are not measured — but as a rough
-upper bound: ~80 W average CPU draw × the contiguous run hours
-(low single-digit kWh, low single-digit kg CO₂e on a grid mix).
-The same model finetuned on a single H100 would be a fraction of
-that wall-clock and energy.
+Trained on a single NVIDIA RTX 3080 Ti (consumer GPU, ~300 W TDP).
+We did not run a [CodeCarbon](https://github.com/mlco2/codecarbon)
+tracker, so emissions are not measured precisely — but as a rough
+upper bound: ~350 W draw under load × ~13 hours wall clock (the
+step-3080 contiguous run) ≈ 4.5 kWh, low single-digit kg CO₂e on a
+grid mix. An H100 run of the same 2-epoch config would be faster
+but not dramatically lower energy per token.
 
 ### Training data
 
@@ -231,7 +231,7 @@ that wall-clock and energy.
 curated knowledge mixture: documentation, technical writing, reasoning
 traces, and protocol-specific corpora related to:
 
-- The Qubitcoin chain (Substrate, VQE mining, Proof-of-SUSY-Alignment, post-quantum signatures).
+- The QuantumAI Blockchain (Substrate, VQE mining, Proof-of-SUSY-Alignment, post-quantum signatures).
 - The Aether Mind on-chain neural cognitive engine (10 Sephirot attention domains, HMS-Phi, Proof-of-Thought).
 - Quantum computing fundamentals (VQE, Hamiltonian generation, qubit ansatze).
 - Adjacent CS / math reasoning content for transfer.
@@ -255,10 +255,10 @@ model is the only public artifact in this line for now.
   (`adapter_model.safetensors`). Merge into the base yourself for
   faster inference, or use directly via PEFT.
 
-## Connection to the Qubitcoin chain
+## Connection to the QuantumAI Blockchain
 
 The Aether Mind is a Rust neural cognitive engine that runs on the
-Qubitcoin chain — every block records attention-derived consciousness
+QuantumAI Blockchain — every block records attention-derived consciousness
 metrics (HMS-Phi) and Proof-of-Thought hashes on-chain via the
 `pallet_qbc_aether_anchor` pallet. The same chain hosts an
 **8-qubit VQE mining consensus** (Proof-of-SUSY-Alignment), a
@@ -278,7 +278,7 @@ Apache-2.0 (matches the base model license).
 
 ```bibtex
 @misc{aether_v52_lora_2026,
-  title  = {Aether v5.2 LoRA --- Qubitcoin Domain Adapter},
+  title  = {Aether v5.2 LoRA --- QuantumAI Blockchain Domain Adapter},
   author = {{BlockArtica} and {QuantumAI-Blockchain}},
   year   = {2026},
   url    = {https://huggingface.co/QuantumAI-Blockchain/aether-v5.2-lora},
@@ -287,7 +287,7 @@ Apache-2.0 (matches the base model license).
 
 ## Links
 
-- **Qubitcoin chain:** [qbc.network](https://qbc.network)
+- **QuantumAI Blockchain:** [qbc.network](https://qbc.network)
 - **GitHub org:** [github.com/QuantumAI-Blockchain](https://github.com/QuantumAI-Blockchain)
 - **X / Twitter:** [@qu_bitcoin](https://x.com/qu_bitcoin)
 - **Contact:** info@qbc.network