mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-26 01:01:40 +00:00
732c66b0f3
The skills directory was getting disorganized — mlops alone had 40 skills in a flat list, and 12 categories were singletons with just one skill each. Code change: - prompt_builder.py: Support sub-categories in skill scanner. skills/mlops/training/axolotl/SKILL.md now shows as category 'mlops/training' instead of just 'mlops'. Backwards-compatible with existing flat structure. Split mlops (40 skills) into 7 sub-categories: - mlops/training (12): accelerate, axolotl, flash-attention, grpo-rl-training, peft, pytorch-fsdp, pytorch-lightning, simpo, slime, torchtitan, trl-fine-tuning, unsloth - mlops/inference (8): gguf, guidance, instructor, llama-cpp, obliteratus, outlines, tensorrt-llm, vllm - mlops/models (6): audiocraft, clip, llava, segment-anything, stable-diffusion, whisper - mlops/vector-databases (4): chroma, faiss, pinecone, qdrant - mlops/evaluation (5): huggingface-tokenizers, lm-evaluation-harness, nemo-curator, saelens, weights-and-biases - mlops/cloud (2): lambda-labs, modal - mlops/research (1): dspy Merged singleton categories: - gifs → media (gif-search joins youtube-content) - music-creation → media (heartmula, songsee) - diagramming → creative (excalidraw joins ascii-art) - ocr-and-documents → productivity - domain → research (domain-intel) - feeds → research (blogwatcher) - market-data → research (polymarket) Fixed misplaced skills: - mlops/code-review → software-development (not ML-specific) - mlops/ml-paper-writing → research (academic writing) Added DESCRIPTION.md files for all new/updated categories.
40 lines
1.3 KiB
YAML
40 lines
1.3 KiB
YAML
# OBLITERATUS Analysis Study Config
|
|
# Usage: obliteratus run this-file.yaml --preset jailbreak
|
|
#
|
|
# Run analysis modules to understand refusal geometry BEFORE abliterating.
|
|
# Useful for research or when you want to understand what you're removing.
|
|
|
|
# Model to analyze
|
|
model:
|
|
name: "meta-llama/Llama-3.1-8B-Instruct"
|
|
dtype: "bfloat16"
|
|
quantization: "4bit" # Saves VRAM for analysis
|
|
device: "auto"
|
|
|
|
# Study configuration
|
|
study:
|
|
# Available presets: quick, full, attention, jailbreak, guardrail, knowledge
|
|
preset: "jailbreak"
|
|
|
|
# Or specify individual strategies:
|
|
# strategies:
|
|
# - layer_removal
|
|
# - head_pruning
|
|
# - ffn_ablation
|
|
# - embedding_ablation
|
|
|
|
# Analysis modules to run (subset of the 27 available)
|
|
analysis:
|
|
- alignment_imprint # Detect DPO/RLHF/CAI/SFT training method
|
|
- concept_geometry # Map refusal cone geometry
|
|
- logit_lens # Find which layer decides to refuse
|
|
- anti_ouroboros # Detect self-repair tendency
|
|
- cross_layer # Cross-layer alignment clustering
|
|
- causal_tracing # Causal necessity of components
|
|
- residual_stream # Attention vs MLP contribution
|
|
|
|
# Output
|
|
output:
|
|
directory: "./analysis-results"
|
|
save_plots: true # Generate matplotlib visualizations
|
|
save_report: true # Generate markdown report
|