mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-07 02:51:50 +00:00
ab0f4126cf
- Restored 21 skills removed in commits757d012and740dd92: accelerate, audiocraft, code-review, faiss, flash-attention, gguf, grpo-rl-training, guidance, llava, nemo-curator, obliteratus, peft, pytorch-fsdp, pytorch-lightning, simpo, slime, stable-diffusion, tensorrt-llm, torchtitan, trl-fine-tuning, whisper - Rewrote sync_skills() with proper update semantics: * New skills (not in manifest): copied to user dir * Existing skills (in manifest + on disk): updated via hash comparison * User-deleted skills (in manifest, not on disk): respected, not re-added * Stale manifest entries (removed from bundled): cleaned from manifest - Added sync_skills() to CLI startup (cmd_chat) and gateway startup (start_gateway) — previously only ran during 'hermes update' - Updated cmd_update output to show new/updated/cleaned counts - Rewrote tests: 20 tests covering manifest CRUD, dir hashing, fresh install, user deletion respect, update detection, stale cleanup, and name collision handling 75 bundled skills total. 2002 tests pass.
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
|