qywu commited on
Commit
a845695
1 Parent(s): 18b21a5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -13
README.md CHANGED
@@ -115,25 +115,25 @@ This model has the same license as the [original Gemma model collection](https:/
115
 
116
  ## OpenLLM Leaderboard Performance
117
 
118
- | Models | Avg. | ARC-C | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8k |
119
- |-------------------------------|------|-------|-----------|------|------------|------------|-------|
120
- | google/gemma-2b | 46.37| 48.38 | 71.77 | 41.77| 33.08 | 34.42 | 16.91 |
121
- | wandb/gemma-2b-zephyr-sft | 47.18| 49.74 | 72.38 | 41.37| 34.42 | 66.93 | 18.27 |
122
- | wandb/gemma-2b-zephyr-dpo | 46.92| 49.66 | 72.23 | 41.13| 34.47 | 66.54 | 17.51 |
123
- | **Columbia-NLP/gemma-2b-zephyr-sft** | 48.75| 51.80 | 72.63 | 42.20| 41.96 | 63.85 | 20.09 |
124
- | Columbia-NLP/gemma-2b-zephyr-dpo | 49.14| 52.22 | 73.11 | 42.55| 42.64 | 64.40 | 19.94 |
125
 
126
 
127
  ## MT-Bench
128
 
129
  GPT-4-0125-preview as Judge
130
 
131
- | Model | Total | Coding | Extraction | Humanities | Math | Reasoning | Roleplay | STEM | Writing |
132
- |-------------------------------------|--------|--------|------------|------------|------|-----------|----------|-------|---------|
133
- | wandb/gemma-2b-zephyr-sft | 4.03 | 3.10 | 3.15 | 5.00 | 2.70 | 2.65 | 5.1 4.80 | 5.75 |
134
- | wandb/gemma-2b-zephyr-dpo | 4.06 | 2.80 | 2.90 | 5.55 | 2.65 | 2.70 | 5.2 4.80 | 5.85 |
135
- | **Columbia-NLP/gemma-2b-zephyr-sft** | 4.34 | 3.10 | 3.70 | 6.25 | 2.65 | 2.7 | 5.55 | 5.25 | 5.50 |
136
- | Columbia-NLP/gemma-2b-zephyr-dpo | 4.75 | 3.50 | 4.05 | 6.75 | 3.30 | 3.7 | 5.85 | 5.40 | 5.53 |
137
 
138
 
139
 
 
115
 
116
  ## OpenLLM Leaderboard Performance
117
 
118
+ | Models | Avg. | ARC-C | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8k |
119
+ |-----------------------------------------|------|-------|-----------|------|------------|------------|-------|
120
+ | google/gemma-2b | 46.37| 48.38 | 71.77 | 41.77| 33.08 | 34.42 | 16.91 |
121
+ | wandb/gemma-2b-zephyr-sft | 47.18| 49.74 | 72.38 | 41.37| 34.42 | 66.93 | 18.27 |
122
+ | wandb/gemma-2b-zephyr-dpo | 46.92| 49.66 | 72.23 | 41.13| 34.47 | 66.54 | 17.51 |
123
+ | **Columbia-NLP/gemma-2b-zephyr-sft** | 48.75| 51.80 | 72.63 | 42.20| 41.96 | 63.85 | 20.09 |
124
+ | Columbia-NLP/gemma-2b-zephyr-dpo | 49.14| 52.22 | 73.11 | 42.55| 42.64 | 64.40 | 19.94 |
125
 
126
 
127
  ## MT-Bench
128
 
129
  GPT-4-0125-preview as Judge
130
 
131
+ | Model | Total | Coding | Extraction | Humanities | Math | Reasoning | Roleplay | STEM | Writing |
132
+ |------------------------------------------|-------|--------|------------|------------|------|-----------|----------|------|---------|
133
+ | wandb/gemma-2b-zephyr-sft | 4.03 | 3.10 | 3.15 | 5.00 | 2.70 | 2.65 | 5.10 | 4.80 | 5.75 |
134
+ | wandb/gemma-2b-zephyr-dpo | 4.06 | 2.80 | 2.90 | 5.55 | 2.65 | 2.70 | 5.20 | 4.80 | 5.85 |
135
+ | **Columbia-NLP/gemma-2b-zephyr-sft** | 4.34 | 3.10 | 3.70 | 6.25 | 2.65 | 2.70 | 5.55 | 5.25 | 5.50 |
136
+ | Columbia-NLP/gemma-2b-zephyr-dpo | 4.75 | 3.50 | 4.05 | 6.75 | 3.30 | 3.70 | 5.85 | 5.40 | 5.53 |
137
 
138
 
139