Update README.md
Browse files
README.md
CHANGED
|
@@ -27,14 +27,32 @@ pipeline_tag: text-generation
|
|
| 27 |
|
| 28 |
| Model | Checkpoint | Paper | GSM8k | MATH |Online Demo| License|
|
| 29 |
| ----- |------| ---- |------|-------| ----- | ----- |
|
| 30 |
-
| **WizardMath-7B-V1.
|
| 31 |
| WizardMath-70B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-70B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **81.6** | **22.7** |[Demo](http://47.103.63.15:50083/)| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 </a> |
|
| 32 |
| WizardMath-13B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-13B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **63.9** | **14.0** |[Demo](http://47.103.63.15:50082/)| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 </a> |
|
| 33 |
| WizardMath-7B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-7B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **54.9** | **10.7** | [Demo](http://47.103.63.15:50080/)| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 </a>|
|
| 34 |
|
| 35 |
|
| 36 |
|
| 37 |
-
## [12/19/2023] Comparing WizardMath-7B-V1.1 with
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
|
| 39 |
🔥
|
| 40 |
❗<b>Note for model system prompts usage:</b>
|
|
|
|
| 27 |
|
| 28 |
| Model | Checkpoint | Paper | GSM8k | MATH |Online Demo| License|
|
| 29 |
| ----- |------| ---- |------|-------| ----- | ----- |
|
| 30 |
+
| **WizardMath-7B-V1.1** | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-7B-V1.1" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **83.2** | **30.0** | [Demo](http://47.103.63.15:50080/)| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank"> </a>|
|
| 31 |
| WizardMath-70B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-70B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **81.6** | **22.7** |[Demo](http://47.103.63.15:50083/)| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 </a> |
|
| 32 |
| WizardMath-13B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-13B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **63.9** | **14.0** |[Demo](http://47.103.63.15:50082/)| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 </a> |
|
| 33 |
| WizardMath-7B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-7B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **54.9** | **10.7** | [Demo](http://47.103.63.15:50080/)| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 </a>|
|
| 34 |
|
| 35 |
|
| 36 |
|
| 37 |
+
## [12/19/2023] Comparing WizardMath-7B-V1.1 with other open source 7B size math LLMs.
|
| 38 |
+
|
| 39 |
+
| Model | GSM8k Pass@1 | MATH Pass@1 |
|
| 40 |
+
| ----- |------| ---- |
|
| 41 |
+
| MPT-7B | 6.8 | 3.0 |
|
| 42 |
+
|Llama 1-7B | 11.0 | 2.9 |
|
| 43 |
+
|Llama 2-7b|12.96 |2.78 |
|
| 44 |
+
|Yi-6b| 32.6 |5.78 |
|
| 45 |
+
|Mistral-7b|37.83 |9.06 |
|
| 46 |
+
|Qwen-7b|47.84 |9.34 |
|
| 47 |
+
| RFT-7B | 50.3 | -- |
|
| 48 |
+
| MAmmoTH-7B (COT) | 50.5 | 10.4 |
|
| 49 |
+
| WizardMath-7B-V1.0 | 54.9 | 10.7 |
|
| 50 |
+
|Abel-7B-001 |59.7 |13 |
|
| 51 |
+
| MetaMath-7B | 66.5 | 19.8 |
|
| 52 |
+
| Arithmo-Mistral-7B | 74.7 | 25.3 |
|
| 53 |
+
|MetaMath-Mistral-7B|77.7 |28.2 |
|
| 54 |
+
|Abel-7B-002 | 80.4 | 29.5 |
|
| 55 |
+
| **WizardMath-7B-V1.1** | **83.2** | **30.0** |
|
| 56 |
|
| 57 |
🔥
|
| 58 |
❗<b>Note for model system prompts usage:</b>
|