attacklm 0.8.2__tar.gz → 0.8.4__tar.gz

{attacklm-0.8.2 → attacklm-0.8.4}/CHANGELOG.md

@@ -1,7 +1,33 @@
 # Changelog
 
+## [0.8.4] — 2026-07-01 — Documentation overhaul
+
+### Changed
+- **Tagline updated**: Now lists all 5 training methods (QLoRA, GaLore, Q-GaLore, Spectrum, PiSSA) instead of just QLoRA
+- **GUI section expanded**: Added dedicated Terminal GUI section with live monitor screenshot, preset list, and screen-by-screen breakdown
+- **AttackLM-Models README synced**: Updated pair count (16,027 → 24,652), added missing defensive sources, updated all hyphenated commands to unified CLI format
+
+---
+
+## [0.8.3] — 2026-07-01 — Training pair evolution
+
+### Added
+- **Training pair evolution**: New `scripts/evolve_pairs.py` with 3 strategies to expand short training pairs into longer, richer examples
+  - **Evol-Instruct**: Rewrites answers with deeper reasoning, edge cases, and detection artifacts (3-5x longer)
+  - **Multi-turn Decomposition**: Breaks Q&A into 3-5 turn conversations for better training flow
+  - **Chain-of-Thought Injection**: Adds explicit reasoning steps before final answers
+- **Quality filtering**: `scripts/filter_evolved.py` validates evolved pairs (structure, length, provenance, dedup)
+- **`--evolved-ratio` flag**: Mix evolved pairs into training at configurable ratio in `train_all.py` and `train_template.py`
+- **`scripts/evolved_mixer.py`**: Standalone mixer module for evolved pair integration
+
+### Changed
+- **Agent models upgraded**: glm-5.1 → glm-5.2, minimax-m2.7 → minimax-m3, added kimi-k2.7-code
+
+---
+
 ## [0.8.1] — 2026-06-30 — Zero-config dataset init
 
+
 ### Added
 - **Zero-config init**: `attacklm init` now downloads a pre-built dataset tarball (~50 MB) from GitHub releases by default. No git clone, no extractors, no manual setup required.
 - **`--from-source` flag**: `attacklm init --from-source` preserves the old clone+extract pipeline for developers who want to rebuild from upstream repos.

{attacklm-0.8.2 → attacklm-0.8.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: attacklm
-Version: 0.8.2
+Version: 0.8.4
 Summary: QLoRA-fine-tuned Qwen2.5-Coder for offensive/defensive security and AI red-teaming
 Project-URL: Homepage, https://github.com/Veedubin/AttackLM
 Project-URL: Repository, https://github.com/Veedubin/AttackLM
@@ -203,7 +203,7 @@ Description-Content-Type: text/markdown
 [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
 [![Build Status](https://img.shields.io/badge/build-passing-brightgreen.svg)](#)
 
-**A high-performance QLoRA fine-tuning pipeline for creating MITRE ATT&CK-grounded security AI assistants.**
+**A high-performance fine-tuning pipeline (QLoRA, GaLore, Q-GaLore, Spectrum, PiSSA) for creating MITRE ATT&CK-grounded security AI assistants.**
 
 ---
 
@@ -287,10 +287,24 @@ By default, AttackLM leverages PyTorch's built-in `torch.backends.cuda.enable_me
 
 - **Comprehensive Security Corpus**: 24,652 high-quality training pairs across 18 distinct security sources.
 - **Advanced Training Methods**: Support for QLoRA, GaLore, Q-GaLore, Spectrum, and PiSSA to enable training of large models on consumer hardware.
+- **Training Pair Evolution**: New capability to synthetically expand short, factual pairs into complex reasoning examples using three specialized strategies:
+
+| Strategy | Approach | Impact |
+| :--- | :--- | :--- |
+| **Evol-Instruct** | Rewrites responses with deeper reasoning and edge cases | 3-5x increase in response length/depth |
+| **Multi-turn** | Decomposes Q&A into interactive conversations | Improved conversational flow and context |
+| **CoT Injection** | Adds explicit "Chain-of-Thought" reasoning steps | Higher logical consistency in complex tasks |
+
 - **Zero-Config Setup**: One-shot `init` command that handles dataset retrieval, extraction, and bucket organization.
 - **Anti-Bias Balancing**: Integrated balancing engine to ensure the model learns diverse tactics rather than just the most voluminous sources.
 - **Provenance Tracking**: Strict per-source attribution and license tracking for every record in the dataset.
-- **Terminal GUI**: A professional Textual-based TUI for managing training runs without memorizing 40+ CLI flags.
+- **Terminal GUI**: A professional Textual-based TUI that eliminates the need to memorize 40+ CLI flags. Features include:
+  - **Tabbed Training Form** — 40+ parameters organized across Basic, LoRA, GaLore, Advanced, and Hardware tabs
+  - **Live Training Monitor** — Real-time loss sparkline, VRAM gauge, token throughput, and scrolling log output
+  - **Built-in Presets** — One-click configurations for 3B/7B models (Q-GaLore Spectrum, QLoRA, etc.)
+  - **One-Click Commands** — Init, Balance, Infer, Build, and Eval all accessible from the main menu
+  - **Pause/Resume Controls** — SIGSTOP/SIGCONT the training process without losing progress
+  - **Zero Dependencies** — No X11, no GPU, no browser required. Works over SSH, WSL, and headless servers.
 - **Deployment Ready**: Built-in merge and conversion pipeline to export adapters to GGUF format for LM Studio or Ollama.
 - **Rock-Solid Stability**: 26/26 core tests passing.
 
@@ -314,11 +328,20 @@ attacklm balance --profile 7b-16gb --preset red-team
 ### Model Training
 `attacklm train`
 The core training engine. Supports Qwen2.5-Coder 3B and 7B base models.
+
+**Standard Training**
 ```bash
 # Train a single model on the entire balanced dataset
 attacklm train -- --dataset all --epochs 10 --lora-r 16 --use-galore
 ```
 
+**Training with Evolved Pairs**
+Use the `--evolved-ratio` flag to mix synthetically evolved high-reasoning pairs into your training set.
+```bash
+# Train with 20% evolved pairs for better reasoning depth
+attacklm train -- --dataset all --evolved-ratio 0.2 --epochs 10
+```
+
 ### Deployment & Testing
 `attacklm build`
 Merge LoRA adapters and convert to GGUF for local deployment.
@@ -332,9 +355,51 @@ Perform a smoke-test of the trained model against representative security prompt
 attacklm infer -- --adapter models/attacklm-single_TIMESTAMP
 ```
 
-### Specialized Tools
+### Terminal GUI
+
+`attacklm gui`
+
+Launch the Textual-based Terminal GUI for an interactive training experience. No memorizing 40+ CLI flags.
+
+```bash
+attacklm gui
+```
+
+The GUI provides:
+
+| Screen | What it does |
+|--------|-------------|
+| **Train** | Tabbed form (Basic, LoRA, GaLore, Advanced, Hardware) with 5 built-in presets |
+| **Init** | One-click dataset initialization (download, extract, organize) |
+| **Balance** | Build balanced training subsets with configurable caps |
+| **Inference** | Smoke-test trained models against security prompts |
+| **Build** | Merge adapter → GGUF conversion → install to LM Studio/Ollama |
+| **Eval** | Retention evaluation, reference collection, scoring, comparison |
+
+**Live Training Monitor** — Once training starts, you get a real-time dashboard:
+
+```
+┌─────────────────────────────────────────────────────┐
+│  Training: attacklm-3b-qgalore-spectrum             │
+│  Epoch 12/30  |  Step 1896  |  Elapsed: 1h 23m     │
+├──────────────────────┬──────────────────────────────┤
+│  Loss: 1.1143 ▂▃▅▆▇  │  VRAM: 5.9/15.6 GB (62%)   │
+│  Eval Loss: 1.176    │  alloc: 5.9  cache: 4.8     │
+│  Trend: ↓ -0.0116    │  ████████░░░░               │
+├──────────────────────┴──────────────────────────────┤
+│  [P]ause  [S]top at checkpoint  [Q]uit              │
+└─────────────────────────────────────────────────────┘
+```
+
+**Built-in Presets:**
+- `3B Q-GaLore Spectrum` — Full-parameter training on 16GB GPU
+- `3B Q-GaLore Rank 128` — Higher quality variant
+- `3B LoRA Default` — Standard QLoRA
+- `7B Q-GaLore` — For 24GB GPUs
+- `7B QLoRA Default` — Standard QLoRA for 7B
+
+### Other Tools
 - `attacklm eval`: Run the retention evaluation suite and score candidate models.
-- `attacklm gui`: Launch the Terminal GUI for an interactive training experience.
 - `attacklm demo`: Run the multi-agent orchestrator demo.
 
 ---
@@ -384,6 +449,7 @@ This hierarchy ensures that the pipeline can be rebuilt from upstream sources wi
 | :--- | :--- |
 | `attacklm train` | Train a model (QLoRA, GaLore, Q-GaLore, Spectrum, PiSSA) |
 | `attacklm train --dataset all` | Train all buckets combined |
+| `attacklm train --evolved-ratio 0.2` | Mix evolved reasoning pairs into training |
 | `attacklm train --hpo` | Run Hyper-Parameter Optimization sweep |
 | `attacklm init` | Initialize dataset: download pre-built or clone $\rightarrow$ extract $\rightarrow$ attribute |
 | `attacklm balance` | Build a balanced subset of buckets to prevent overfitting |

{attacklm-0.8.2 → attacklm-0.8.4}/README.md

@@ -5,7 +5,7 @@
 [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
 [![Build Status](https://img.shields.io/badge/build-passing-brightgreen.svg)](#)
 
-**A high-performance QLoRA fine-tuning pipeline for creating MITRE ATT&CK-grounded security AI assistants.**
+**A high-performance fine-tuning pipeline (QLoRA, GaLore, Q-GaLore, Spectrum, PiSSA) for creating MITRE ATT&CK-grounded security AI assistants.**
 
 ---
 
@@ -89,10 +89,24 @@ By default, AttackLM leverages PyTorch's built-in `torch.backends.cuda.enable_me
 
 - **Comprehensive Security Corpus**: 24,652 high-quality training pairs across 18 distinct security sources.
 - **Advanced Training Methods**: Support for QLoRA, GaLore, Q-GaLore, Spectrum, and PiSSA to enable training of large models on consumer hardware.
+- **Training Pair Evolution**: New capability to synthetically expand short, factual pairs into complex reasoning examples using three specialized strategies:
+
+| Strategy | Approach | Impact |
+| :--- | :--- | :--- |
+| **Evol-Instruct** | Rewrites responses with deeper reasoning and edge cases | 3-5x increase in response length/depth |
+| **Multi-turn** | Decomposes Q&A into interactive conversations | Improved conversational flow and context |
+| **CoT Injection** | Adds explicit "Chain-of-Thought" reasoning steps | Higher logical consistency in complex tasks |
+
 - **Zero-Config Setup**: One-shot `init` command that handles dataset retrieval, extraction, and bucket organization.
 - **Anti-Bias Balancing**: Integrated balancing engine to ensure the model learns diverse tactics rather than just the most voluminous sources.
 - **Provenance Tracking**: Strict per-source attribution and license tracking for every record in the dataset.
-- **Terminal GUI**: A professional Textual-based TUI for managing training runs without memorizing 40+ CLI flags.
+- **Terminal GUI**: A professional Textual-based TUI that eliminates the need to memorize 40+ CLI flags. Features include:
+  - **Tabbed Training Form** — 40+ parameters organized across Basic, LoRA, GaLore, Advanced, and Hardware tabs
+  - **Live Training Monitor** — Real-time loss sparkline, VRAM gauge, token throughput, and scrolling log output
+  - **Built-in Presets** — One-click configurations for 3B/7B models (Q-GaLore Spectrum, QLoRA, etc.)
+  - **One-Click Commands** — Init, Balance, Infer, Build, and Eval all accessible from the main menu
+  - **Pause/Resume Controls** — SIGSTOP/SIGCONT the training process without losing progress
+  - **Zero Dependencies** — No X11, no GPU, no browser required. Works over SSH, WSL, and headless servers.
 - **Deployment Ready**: Built-in merge and conversion pipeline to export adapters to GGUF format for LM Studio or Ollama.
 - **Rock-Solid Stability**: 26/26 core tests passing.
 
@@ -116,11 +130,20 @@ attacklm balance --profile 7b-16gb --preset red-team
 ### Model Training
 `attacklm train`
 The core training engine. Supports Qwen2.5-Coder 3B and 7B base models.
+
+**Standard Training**
 ```bash
 # Train a single model on the entire balanced dataset
 attacklm train -- --dataset all --epochs 10 --lora-r 16 --use-galore
 ```
 
+**Training with Evolved Pairs**
+Use the `--evolved-ratio` flag to mix synthetically evolved high-reasoning pairs into your training set.
+```bash
+# Train with 20% evolved pairs for better reasoning depth
+attacklm train -- --dataset all --evolved-ratio 0.2 --epochs 10
+```
+
 ### Deployment & Testing
 `attacklm build`
 Merge LoRA adapters and convert to GGUF for local deployment.
@@ -134,9 +157,51 @@ Perform a smoke-test of the trained model against representative security prompt
 attacklm infer -- --adapter models/attacklm-single_TIMESTAMP
 ```
 
-### Specialized Tools
+### Terminal GUI
+
+`attacklm gui`
+
+Launch the Textual-based Terminal GUI for an interactive training experience. No memorizing 40+ CLI flags.
+
+```bash
+attacklm gui
+```
+
+The GUI provides:
+
+| Screen | What it does |
+|--------|-------------|
+| **Train** | Tabbed form (Basic, LoRA, GaLore, Advanced, Hardware) with 5 built-in presets |
+| **Init** | One-click dataset initialization (download, extract, organize) |
+| **Balance** | Build balanced training subsets with configurable caps |
+| **Inference** | Smoke-test trained models against security prompts |
+| **Build** | Merge adapter → GGUF conversion → install to LM Studio/Ollama |
+| **Eval** | Retention evaluation, reference collection, scoring, comparison |
+
+**Live Training Monitor** — Once training starts, you get a real-time dashboard:
+
+```
+┌─────────────────────────────────────────────────────┐
+│  Training: attacklm-3b-qgalore-spectrum             │
+│  Epoch 12/30  |  Step 1896  |  Elapsed: 1h 23m     │
+├──────────────────────┬──────────────────────────────┤
+│  Loss: 1.1143 ▂▃▅▆▇  │  VRAM: 5.9/15.6 GB (62%)   │
+│  Eval Loss: 1.176    │  alloc: 5.9  cache: 4.8     │
+│  Trend: ↓ -0.0116    │  ████████░░░░               │
+├──────────────────────┴──────────────────────────────┤
+│  [P]ause  [S]top at checkpoint  [Q]uit              │
+└─────────────────────────────────────────────────────┘
+```
+
+**Built-in Presets:**
+- `3B Q-GaLore Spectrum` — Full-parameter training on 16GB GPU
+- `3B Q-GaLore Rank 128` — Higher quality variant
+- `3B LoRA Default` — Standard QLoRA
+- `7B Q-GaLore` — For 24GB GPUs
+- `7B QLoRA Default` — Standard QLoRA for 7B
+
+### Other Tools
 - `attacklm eval`: Run the retention evaluation suite and score candidate models.
-- `attacklm gui`: Launch the Terminal GUI for an interactive training experience.
 - `attacklm demo`: Run the multi-agent orchestrator demo.
 
 ---
@@ -186,6 +251,7 @@ This hierarchy ensures that the pipeline can be rebuilt from upstream sources wi
 | :--- | :--- |
 | `attacklm train` | Train a model (QLoRA, GaLore, Q-GaLore, Spectrum, PiSSA) |
 | `attacklm train --dataset all` | Train all buckets combined |
+| `attacklm train --evolved-ratio 0.2` | Mix evolved reasoning pairs into training |
 | `attacklm train --hpo` | Run Hyper-Parameter Optimization sweep |
 | `attacklm init` | Initialize dataset: download pre-built or clone $\rightarrow$ extract $\rightarrow$ attribute |
 | `attacklm balance` | Build a balanced subset of buckets to prevent overfitting |