Hugging Face's logo

pipizhao
/
Pandalyst_13B_V1.0

Text Generation
Transformers
PyTorch
English
llama
code
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
1
pipizhao commited on
Commit
395cff7
•
1 Parent(s): 397585f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -5
README.md CHANGED
@@ -39,14 +39,16 @@ language:
39
  - Pandalyst can handle complex data tables (multiple columns and multiple rows), allowing us to enter enough context to describe our table in detail.
40
  - Pandalyst has very competitive performance, significantly outperforming models of the same size and even outperforming some of the strongest closed-source models.
41
 
 
42
  ## News
 
 
43
 
44
- - 🔥[2023/09/28] We released **Pandalyst-13B-V1.0** , which achieves the **70.7 exec@1** in our **PandaTest_V1.0** and surpasses **WizardCoder-Python-13B-V1.0** and **ChatGPT-3.5 (2023/06/13)**.
45
 
46
- | Model | Checkpoint | PandaTest_V1.0 | PandaTest_V1.0_EASY | PandaTest_V1.0_HARD | License |
47
- |--------------------|------------------------------------------------------------------------------------------------------|----------------|---------------------|---------------------| ----- |
48
- | Pandalyst-13B-V1.0 | 🤗 <a href="https://huggingface.co/pipizhao/Pandalyst_13B_V1.0" target="_blank">HF Link</a> | 70.7 | 75.6 | 65.9 | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama2</a> |
49
- | Pandalyst-7B-V1.0 | coming soon | - | - | - | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama2</a> |
50
 
51
 
52
  ## Usage
 
39
  - Pandalyst can handle complex data tables (multiple columns and multiple rows), allowing us to enter enough context to describe our table in detail.
40
  - Pandalyst has very competitive performance, significantly outperforming models of the same size and even outperforming some of the strongest closed-source models.
41
 
42
+
43
  ## News
44
+ - 🔥[2023/09/30] We released **Pandalyst-7B-V1.1** , which was trained on **CodeLlama-7b-Python** and achieves the **76.1 exec@1** in our **PandaTest_V1.0** and surpasses **Pandalyst-13B-V1.0**, **WizardCoder-Python-13B-V1.0** and **ChatGPT-3.5 (2023/06/13)**.
45
+ - 🔥[2023/09/28] We released **Pandalyst-13B-V1.0** , which was trained on **WizardCoder-Python-13B-V1.0** and achieves the **70.7 exec@1** in our **PandaTest_V1.0** and surpasses **WizardCoder-Python-13B-V1.0** and **ChatGPT-3.5 (2023/06/13)**.
46
 
 
47
 
48
+ | Model | Checkpoint | Base Model | PandaTest_V1.0 | EASY | HARD | License |
49
+ |--------------------|---------------------------------------------------------------------------------------------|------------|----------------|---------------------|---------------------| ----- |
50
+ | Pandalyst-13B-V1.0 | 🤗 <a href="https://huggingface.co/pipizhao/Pandalyst_13B_V1.0" target="_blank">HF Link</a> | WizardCoder-Python-13B-V1.0 | 70.7 | 75.6 | 65.9 | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama2</a> |
51
+ | Pandalyst-7B-V1.1 | 🤗 <a href="https://huggingface.co/pipizhao/Pandalyst-7B-V1.1" target="_blank">HF Link</a> | CodeLlama-7b-Python | 76.1 | 85.2 | 67.0 | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama2</a> |
52
 
53
 
54
  ## Usage