leannachr commited on
Commit
56790cc
·
verified ·
1 Parent(s): 1894ae1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -116,7 +116,7 @@ Every model NVIDIA ships rests on a data layer — and that data shapes how the
116
  | **TRAINING STAGES** |  |  |
117
  | RL data with verifiable rewards (math, code, agentic, instruction) | [**Nemotron Reinforcement Learning Collection**](https://huggingface.co/collections/nvidia/nemotron-reinforcement-learning) | Nemotron-RL-math-OpenMathReasoning, Nemotron-RL-coding-competitive\_coding, Nemotron-RL-Agentic-Function-Calling-Pivot-v1 |
118
  | Train a reward model | [**Nemotron Reward Modeling Collection**](https://huggingface.co/collections/nvidia/nemotron-reward-modeling) | HelpSteer3, HelpSteer2, Nemotron-RLHF-GenRM-v1 |
119
- | Full post-training recipe (SFT \+ RL blend) | [**Nemotron Post-Training Blends Collection**](https://huggingface.co/collections/nvidia/nemotron-post-training-v3) | Llama-Nemotron-Post-Training-Dataset, Nemotron-Post-Training-Dataset-v2, Nemotron-Cascade-2-SFT-Data |
120
  | Evaluate model performance | **Nemotron Eval & Benchmark Collection** | SPEED-bench |
121
  | **SPECIALIZED & SOVEREIGN** |  |  |
122
  | Multilingual or domain-specific (e.g. finance) capability | [**Nemotron Supervised Fine-Tuning Collection**](https://huggingface.co/collections/nvidia/nemotron-supervised-fine-tuning) | Nemotron-SFT-Multilingual-v1, Nemotron-SpecializedDomains-Finance-v1 |
 
116
  | **TRAINING STAGES** |  |  |
117
  | RL data with verifiable rewards (math, code, agentic, instruction) | [**Nemotron Reinforcement Learning Collection**](https://huggingface.co/collections/nvidia/nemotron-reinforcement-learning) | Nemotron-RL-math-OpenMathReasoning, Nemotron-RL-coding-competitive\_coding, Nemotron-RL-Agentic-Function-Calling-Pivot-v1 |
118
  | Train a reward model | [**Nemotron Reward Modeling Collection**](https://huggingface.co/collections/nvidia/nemotron-reward-modeling) | HelpSteer3, HelpSteer2, Nemotron-RLHF-GenRM-v1 |
119
+ | Full post-training recipe (SFT \+ RL blend) | [**Nemotron Post-Training Blends Collection**](https://huggingface.co/collections/nvidia/nemotron-post-training-datasets) | Llama-Nemotron-Post-Training-Dataset, Nemotron-Post-Training-Dataset-v2, Nemotron-Cascade-2-SFT-Data |
120
  | Evaluate model performance | **Nemotron Eval & Benchmark Collection** | SPEED-bench |
121
  | **SPECIALIZED & SOVEREIGN** |  |  |
122
  | Multilingual or domain-specific (e.g. finance) capability | [**Nemotron Supervised Fine-Tuning Collection**](https://huggingface.co/collections/nvidia/nemotron-supervised-fine-tuning) | Nemotron-SFT-Multilingual-v1, Nemotron-SpecializedDomains-Finance-v1 |