Downloads · 30 days
11
17% of all-time downloads
geodesic-research/nemotron-super-120b-cc-mt-curriculum-nodr
nemotron-super-120b-cc-mt-curriculum-nodr is a machine learning model from geodesic-research. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
Nemotron 3 Super 120B-A12B continued-pretraining (midtraining) checkpoint from the constitutional-curriculum midtraining study (cc-mt).
Downloads · 30 days
11
17% of all-time downloads
All-time downloads
65
Public
Parameters
124B
241 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors241 GB · 100%
How the weights are stored.
BF16121B · 100%
From the Hugging Face model README
Nemotron 3 Super 120B-A12B continued-pretraining (midtraining) checkpoint from the constitutional-curriculum midtraining study (cc-mt).
NVIDIA-Nemotron-3-Super-120B-A12B-Base-Chat-Init-BF16 (pure Base weights;
1,188 chat-scaffolding embedding rows grafted from Instruct. No post-training behavior included.)data/curriculum_noDR.jsonl (~269M tokens, consumed in exact file order, no-deliberative-reasoning variant) and shuffled pretraining replay (geodesic-research/Nemotron-Pretraining-Specialized)geodesic-research/nemotron-base-tokenizer (EOD=</s>=id 2). All data filtered against
the 1,188 zero-embedding token ids of Super-Base (0 docs dropped).Base-style model (pretraining-format CPT; no instruction tuning) — use completion-style prompting.
Loads with native transformers NemotronHForCausalLM; tokenizer PreTrainedTokenizerFast.
Coherence-checked post-export (8/8 non-empty, fluent completions).
SFT companions: nemotron-super-120b-cc-mt-curriculum-nodr-sr-sft (reasoning) and
nemotron-super-120b-cc-mt-curriculum-nodr-200k-sft (non-reasoning).