Hugging Face's logo

nvidia
/
Llama3-70B-SteerLM-RM

NeMo
English
nvidia
steerlm
llama3
reward model
Model card Files Community
4
zhilinw commited on
Commit
c1f346b
•
1 Parent(s): 22c5a66

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -45,7 +45,7 @@ Llama3-70B-SteerLM-RM is trained with NVIDIA [NeMo-Aligner](https://github.com/N
45
  ## RewardBench LeaderBoard
46
 
47
 
48
- | Model | Type of Model| Overall | Chat | Chat Hard | Safety | Reasoning |
49
  |:-----------------------------|:----------------|:-----|:----------|:-------|:----------|:-----------------------|
50
  | Nemotron-4-340B-SteerLM-RM | Proprietary LLM| **91.6** | 95.5 |**86.4** | 90.8 | 93.6 |
51
  | ArmoRM-Llama3-8B-v0.1 | Trained with GPT4 Data| 90.8 | 96.9 | 76.8 | 92.2 | 97.3 |
 
45
  ## RewardBench LeaderBoard
46
 
47
 
48
+ | Model | Type of Model| Overall | Chat | Chat-Hard | Safety | Reasoning |
49
  |:-----------------------------|:----------------|:-----|:----------|:-------|:----------|:-----------------------|
50
  | Nemotron-4-340B-SteerLM-RM | Proprietary LLM| **91.6** | 95.5 |**86.4** | 90.8 | 93.6 |
51
  | ArmoRM-Llama3-8B-v0.1 | Trained with GPT4 Data| 90.8 | 96.9 | 76.8 | 92.2 | 97.3 |