Views
No views yet
nvidia/Llama-3_3-Nemotron-Super-49B-v1 after the
timhua/wood_v2_sftr4_filt SDF adapter has been merged into the base. Trained as part
of the eval-awareness measurement-cooperation experiments (Feb 2026).adapter_config.json in this repo lists base_model_name_or_path as a local path
(.../merged_wood_base) because that is what the trainer saw. To use this adapter, you
must first reproduce that intermediate base:1# Step 1: merge wood_v2_sftr4_filt into Nemotron-49B → merged_wood_base
2python merge_peft_adapter.py \
3 --adapter_model_name timhua/wood_v2_sftr4_filt \
4 --base_model_name nvidia/Llama-3_3-Nemotron-Super-49B-v1 \
5 --output_name ./merged_wood_base
6
7# Step 2: load this adapter on top of merged_wood_base
8from peft import PeftModel
9from transformers import AutoModelForCausalLM
10base = AutoModelForCausalLM.from_pretrained("./merged_wood_base", trust_remote_code=True)
11model = PeftModel.from_pretrained(base, "jasminexli/nemotron49b-wood-measurement-coop")merged_wood_base (and the further-merged
merged_wood_coop_base that bakes in this adapter) is
sdf/scripts/merge_wood_coop_base.sh in the eval-awareness repo.timhua/wood_v2_sftr4_filt (wood SDF)train_config.json in this repo for the full HF TrainingArguments.