Text Generation
Transformers
Safetensors
English
olmoe
Mixture of Experts
olmo
SaveBertAndGpt commited on
Commit
81ae7ca
Β·
verified Β·
1 Parent(s): 4e8ad20

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -64,7 +64,8 @@ Important branches:
64
  | Model | Active Params | Open Data | MMLU | HellaSwag | ARC-Chall. | ARC-Easy | PIQA | WinoGrande |
65
  |-----------------------------|---------------|-----------|------|-----------|------------|----------|------|------------|
66
  | **LMs with ~1B active parameters** | | | | | | | | |
67
- | **OLMoE-1B-7B** | **1.3B** | **βœ…** | **54.1** | **80.0** | **62.1** | **84.2** | **79.8** | **70.2** |
 
68
  | DCLM-1B | 1.4B | βœ… | 48.5 | 75.1 | 57.6 | 79.5 | 76.6 | 68.1 |
69
  | TinyLlama-1B | 1.1B | βœ… | 33.6 | 60.8 | 38.1 | 69.5 | 71.7 | 60.1 |
70
  | OLMo-1B (0724) | 1.3B | βœ… | 32.1 | 67.5 | 36.4 | 53.5 | 74.0 | 62.9 |
 
64
  | Model | Active Params | Open Data | MMLU | HellaSwag | ARC-Chall. | ARC-Easy | PIQA | WinoGrande |
65
  |-----------------------------|---------------|-----------|------|-----------|------------|----------|------|------------|
66
  | **LMs with ~1B active parameters** | | | | | | | | |
67
+ | **OLMoE-1B-7B-0125** | **1.3B** | **βœ…** | **56.3** | **81.7** | **67.5** | **84.4** | 78.7 | **70.6** |
68
+ | OLMoE-1B-7B-0924 | 1.3B | βœ… | 54.1 | 80.0 | 62.1 | 84.2 | **79.8** | 70.2 |
69
  | DCLM-1B | 1.4B | βœ… | 48.5 | 75.1 | 57.6 | 79.5 | 76.6 | 68.1 |
70
  | TinyLlama-1B | 1.1B | βœ… | 33.6 | 60.8 | 38.1 | 69.5 | 71.7 | 60.1 |
71
  | OLMo-1B (0724) | 1.3B | βœ… | 32.1 | 67.5 | 36.4 | 53.5 | 74.0 | 62.9 |