Hugging Face's logo

Salesforce
/
LLaMA-3-8B-SFR-Iterative-DPO-R

Text Generation
Transformers
Safetensors
llama
conversational
Inference Endpoints
text-generation-inference
Model card Files Community
1
bpucla commited on
Commit
ad7d1ae
•
1 Parent(s): b4e0ac6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -34,7 +34,7 @@ For a detailed exposition, please refer to our accompanying technical report.
34
  | **Ours** | | | | | |
35
  | Ours (SFT baseline) | 8B | SFT | 10.2 | 7.69 | 5.6 |
36
  | Ours (DPO baseline) | 8B | Vanilla DPO | 22.5 | 8.17 | 22.4 |
37
- | Ours (Online RLHF) | 8B | Iterative DPO | **37.2** | **8.46** | **29.1** |
38
  | **Large Open-Sourced Models** | | | | | |
39
  | Vicuna-33b-v1.3 | 33B | SFT | 17.6 | 7.12 | 8.6 |
40
  | Yi-34B-Chat | 34B | SFT | 27.2 | - | 23.1 |
 
34
  | **Ours** | | | | | |
35
  | Ours (SFT baseline) | 8B | SFT | 10.2 | 7.69 | 5.6 |
36
  | Ours (DPO baseline) | 8B | Vanilla DPO | 22.5 | 8.17 | 22.4 |
37
+ | Ours (Online RLHF) | 8B | Iterative DPO | **31.3** | **8.46** | **29.1** |
38
  | **Large Open-Sourced Models** | | | | | |
39
  | Vicuna-33b-v1.3 | 33B | SFT | 17.6 | 7.12 | 8.6 |
40
  | Yi-34B-Chat | 34B | SFT | 27.2 | - | 23.1 |