update usage

README.md

@@ -2,21 +2,21 @@
 license: mit
 license_link: https://huggingface.co/microsoft/wavecoder-ultra-6.7b/blob/main/LICENSE
 language:
-- en
+  - en
 library_name: transformers
 datasets:
-- humaneval
+  - humaneval
 pipeline_tag: text-generation
 tags:
-- code
+  - code
 metrics:
-- code_eval
+  - code_eval
 ---
+
 <h1 align="center">
 🌊 WaveCoder: Widespread And Versatile Enhanced Code LLM
 </h1>
 
-
 <p align="center">
   <a href="https://arxiv.org/abs/2312.14187"><b>[📜 Paper]</b></a> •
   <!-- <a href=""><b>[🤗 HF Models]</b></a> • -->
@@ -33,29 +33,36 @@ metrics:
 Repo for "<a href="https://arxiv.org/abs/2312.14187" target="_blank">WaveCoder: Widespread And Versatile Enhanced Instruction Tuning with Refined Data Generation</a>" 
 </p>
 
-
 ## 🔥 News
 
-- [2024/04/10] 🔥🔥🔥  WaveCoder repo, models released at [🤗 HuggingFace](https://huggingface.co/microsoft/wavecoder-ultra-6.7b)!
+- [2024/04/10] 🔥🔥🔥 WaveCoder repo, models released at [🤗 HuggingFace](https://huggingface.co/microsoft/wavecoder-ultra-6.7b)!
 - [2023/12/26] WaveCoder paper released.
+
 ## 💡 Introduction
 
-WaveCoder 🌊 is a series of large language models (LLMs) for the coding domain, designed to solve relevant problems in the field of code through instruction-following learning. Its training dataset was generated from a subset of code-search-net data using a generator-discriminator framework based on LLMs that we proposed, covering four general code-related tasks: code generation, code summary, code translation, and code repair. 
+WaveCoder 🌊 is a series of large language models (LLMs) for the coding domain, designed to solve relevant problems in the field of code through instruction-following learning. Its training dataset was generated from a subset of code-search-net data using a generator-discriminator framework based on LLMs that we proposed, covering four general code-related tasks: code generation, code summary, code translation, and code repair.
 
-| Model | HumanEval | MBPP(500) | HumanEval<br>Fix(Avg.) | HumanEval<br>Explain(Avg.)|
-|---|---|---|---|---|
-| GPT-4 | 85.4 | - | 47.8 | 52.1 |
-| [🌊 WaveCoder-DS-6.7B](https://huggingface.co/microsoft/wavecoder-ds-6.7b) | 65.8 | 63.0 | 49.5 | 40.8| 
-| [🌊 WaveCoder-Pro-6.7B](https://huggingface.co/microsoft/wavecoder-pro-6.7b) | 74.4 |  63.4 | 52.1 | 43.0 |
-| [🌊 WaveCoder-Ultra-6.7B](https://huggingface.co/microsoft/wavecoder-ultra-6.7b) | 79.9 | 64.6 | 52.3 | 45.7 |
+| Model                                                                            | HumanEval | MBPP(500) | HumanEval<br>Fix(Avg.) | HumanEval<br>Explain(Avg.) |
+| -------------------------------------------------------------------------------- | --------- | --------- | ---------------------- | -------------------------- |
+| GPT-4                                                                            | 85.4      | -         | 47.8                   | 52.1                       |
+| [🌊 WaveCoder-DS-6.7B](https://huggingface.co/microsoft/wavecoder-ds-6.7b)       | 65.8      | 63.0      | 49.5                   | 40.8                       |
+| [🌊 WaveCoder-Pro-6.7B](https://huggingface.co/microsoft/wavecoder-pro-6.7b)     | 74.4      | 63.4      | 52.1                   | 43.0                       |
+| [🌊 WaveCoder-Ultra-6.7B](https://huggingface.co/microsoft/wavecoder-ultra-6.7b) | 79.9      | 64.6      | 52.3                   | 45.7                       |
 
 ## 🪁 Evaluation
 
 Please refer to WaveCoder's [GitHub repo](https://github.com/microsoft/WaveCoder) for inference, evaluation, and training code.
 
+```python
+# Load model directly
+from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("microsoft/wavecoder-ultra-6.7b")
+model = AutoModelForCausalLM.from_pretrained("microsoft/wavecoder-ultra-6.7b")
+```
+
 ## 📖 License
+
 This code repository is licensed under the MIT License. The use of DeepSeek Coder models is subject to the its [License](https://github.com/deepseek-ai/DeepSeek-Coder/blob/main/LICENSE-MODEL).
- 
 
 ## ☕️ Citation
 
@@ -69,6 +76,7 @@ If you find this repository helpful, please consider citing our paper:
   year={2023}
 }
 ```
+
 ## Note
 
-WaveCoder models are trained on the synthetic data generated by OpenAI models. Please pay attention to OpenAI's [terms of use](https://openai.com/policies/terms-of-use) when using the models and the datasets. 
+WaveCoder models are trained on the synthetic data generated by OpenAI models. Please pay attention to OpenAI's [terms of use](https://openai.com/policies/terms-of-use) when using the models and the datasets.