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.
41 lines
1.2 KiB
YAML
41 lines
1.2 KiB
YAML
# OBLITERATUS Batch Abliteration Config
|
|
# Abliterate multiple models with the same method for comparison.
|
|
#
|
|
# Run each one sequentially:
|
|
# for model in models; do obliteratus obliterate $model --method informed; done
|
|
#
|
|
# Or use this as a reference for which models to process.
|
|
|
|
# Common settings
|
|
defaults:
|
|
method: "informed"
|
|
quantization: "4bit"
|
|
output_dir: "./abliterated-models"
|
|
|
|
# Models to process (grouped by compute tier)
|
|
models:
|
|
# Small (4-8 GB VRAM)
|
|
small:
|
|
- "Qwen/Qwen2.5-1.5B-Instruct"
|
|
- "microsoft/Phi-3.5-mini-instruct"
|
|
- "meta-llama/Llama-3.2-3B-Instruct"
|
|
|
|
# Medium (8-16 GB VRAM)
|
|
medium:
|
|
- "meta-llama/Llama-3.1-8B-Instruct"
|
|
- "mistralai/Mistral-7B-Instruct-v0.3"
|
|
- "google/gemma-2-9b-it"
|
|
- "Qwen/Qwen2.5-7B-Instruct"
|
|
|
|
# Large (24 GB VRAM, 4-bit quantization)
|
|
large:
|
|
- "Qwen/Qwen2.5-14B-Instruct"
|
|
- "Qwen/Qwen3-32B"
|
|
- "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"
|
|
|
|
# Per-model method overrides (optional)
|
|
overrides:
|
|
"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B":
|
|
method: "surgical" # CoT-aware for reasoning models
|
|
"mistralai/Mixtral-8x7B-Instruct-v0.1":
|
|
method: "nuclear" # Expert-granular for MoE models
|