Downloads · 30 days
4
5% of all-time downloads
henrywch2huggingface/LE_Morals-Guard-Qwen3.6-35B-A3B-LoRA
LE_Morals-Guard-Qwen3.6-35B-A3B-LoRA is a machine learning model from henrywch2huggingface. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as other.
LoRA adapter (rank 64, α 128) that turns Qwen3.6-35B-A3B into the bilingual, multimodal value-handbook content guard described in LEMorals-Guard-Qwen3.6-35B-A3B (merged weights, full model card, benchmarks). Code & pa…
Downloads · 30 days
4
5% of all-time downloads
All-time downloads
80
Public
Repo size
66.9 MB
Likes
0
Public
Click a slice to open those files.
.safetensors66.9 MB · 100%
From the Hugging Face model README
LoRA adapter (rank 64, α 128) that turns Qwen3.6-35B-A3B into the bilingual, multimodal value-handbook content guard described in LE_Morals-Guard-Qwen3.6-35B-A3B (merged weights, full model card, benchmarks). Code & paper: https://github.com/henrywch/LE_Morals
LoRA is applied to attention + expert MLPs (q/k/v/o_proj, gate/up/down_proj) only — not the MoE router;
the vision encoder & aligner are frozen.
from transformers import AutoModelForCausalLM
from peft import PeftModel
import torch
base = AutoModelForCausalLM.from_pretrained(
"Qwen/Qwen3.6-35B-A3B", torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)
model = PeftModel.from_pretrained(base, "henrywch2huggingface/LE_Morals-Guard-Qwen3.6-35B-A3B-LoRA")
# Build the system prompt from the value handbook (GitHub: common/handbook.py), then chat with
# enable_thinking=False. See the merged-model card for full inference code.
Prefer the merged model for direct, self-contained inference. For benchmarks, training details, and citation, see that card.