Update README.md
Browse files
README.md
CHANGED
@@ -119,10 +119,10 @@ This model has the same license as the [original Gemma model collection](https:/
|
|
119 |
|-----------------------------------------|------|-------|-----------|------|------------|------------|-------|
|
120 |
| google/gemma-2b | 46.37| 48.38 | 71.77 | 41.77| 33.08 | 66.77 | 16.91 |
|
121 |
| google/gemma-2b-it | 42.75| 43.94 | 62.70 | 37.65| 45.82 | 60.93 | 5.46 |
|
122 |
-
| wandb/gemma-2b-zephyr-sft | 47.18| 49.74 | 72.38 | 41.37| 34.42 | 66.93 | 18.27 |
|
123 |
| wandb/gemma-2b-zephyr-dpo | 46.92| 49.66 | 72.23 | 41.13| 34.47 | 66.54 | 17.51 |
|
124 |
-
| Columbia-NLP/gemma-2b-zephyr-sft | 48.75| 51.80 | 72.63 | 42.20| 41.96 | 63.85 | 20.09 |
|
125 |
-
| **Columbia-NLP/gemma-2b-zephyr-dpo** | 49.14
|
126 |
|
127 |
|
128 |
## MT-Bench
|
@@ -131,8 +131,8 @@ We evaluate our model with `GPT-4-0125-preview` as the judge.
|
|
131 |
|
132 |
| Model | Total | Coding | Extraction | Humanities | Math | Reasoning | Roleplay | STEM | Writing |
|
133 |
|------------------------------------------|-------|--------|------------|------------|------|-----------|----------|------|---------|
|
134 |
-
| google/gemma-2b-it | 4.71 | 2.95 | 4.35 | 6.15 | 2.90 | 3.50 | 5.60 | 5.50 | 6.70 |
|
135 |
| wandb/gemma-2b-zephyr-sft | 4.03 | 3.10 | 3.15 | 5.00 | 2.70 | 2.65 | 5.10 | 4.80 | 5.75 |
|
136 |
| wandb/gemma-2b-zephyr-dpo | 4.06 | 2.80 | 2.90 | 5.55 | 2.65 | 2.70 | 5.20 | 4.80 | 5.85 |
|
137 |
| Columbia-NLP/gemma-2b-zephyr-sft | 4.34 | 3.10 | 3.70 | 6.25 | 2.65 | 2.70 | 5.55 | 5.25 | 5.50 |
|
138 |
-
| **Columbia-NLP/gemma-2b-zephyr-dpo** | **4.75** | 3.50 | 4.05 | 6.75 | 3.30 | 3.70 | 5.85 | 5.40 | 5.53 |
|
|
|
119 |
|-----------------------------------------|------|-------|-----------|------|------------|------------|-------|
|
120 |
| google/gemma-2b | 46.37| 48.38 | 71.77 | 41.77| 33.08 | 66.77 | 16.91 |
|
121 |
| google/gemma-2b-it | 42.75| 43.94 | 62.70 | 37.65| 45.82 | 60.93 | 5.46 |
|
122 |
+
| wandb/gemma-2b-zephyr-sft | 47.18| 49.74 | 72.38 | 41.37| 34.42 | **66.93** | 18.27 |
|
123 |
| wandb/gemma-2b-zephyr-dpo | 46.92| 49.66 | 72.23 | 41.13| 34.47 | 66.54 | 17.51 |
|
124 |
+
| Columbia-NLP/gemma-2b-zephyr-sft | 48.75| 51.80 | 72.63 | 42.20| 41.96 | 63.85 | **20.09** |
|
125 |
+
| **Columbia-NLP/gemma-2b-zephyr-dpo** | **49.14**| **52.22** | **73.11** | **42.55**| **42.64** | 64.40 | 19.94 |
|
126 |
|
127 |
|
128 |
## MT-Bench
|
|
|
131 |
|
132 |
| Model | Total | Coding | Extraction | Humanities | Math | Reasoning | Roleplay | STEM | Writing |
|
133 |
|------------------------------------------|-------|--------|------------|------------|------|-----------|----------|------|---------|
|
134 |
+
| google/gemma-2b-it | 4.71 | 2.95 | **4.35** | 6.15 | 2.90 | 3.50 | 5.60 | **5.50** | **6.70** |
|
135 |
| wandb/gemma-2b-zephyr-sft | 4.03 | 3.10 | 3.15 | 5.00 | 2.70 | 2.65 | 5.10 | 4.80 | 5.75 |
|
136 |
| wandb/gemma-2b-zephyr-dpo | 4.06 | 2.80 | 2.90 | 5.55 | 2.65 | 2.70 | 5.20 | 4.80 | 5.85 |
|
137 |
| Columbia-NLP/gemma-2b-zephyr-sft | 4.34 | 3.10 | 3.70 | 6.25 | 2.65 | 2.70 | 5.55 | 5.25 | 5.50 |
|
138 |
+
| **Columbia-NLP/gemma-2b-zephyr-dpo** | **4.75** | **3.50** | 4.05 | **6.75** | **3.30** | **3.70** | **5.85** | 5.40 | 5.53 |
|