Update README.md

README.md

@@ -16,12 +16,11 @@ tags:
 - code
 ---
 
-# KStack-full models
+# Model description
 
-KStack-full models is a collection of fine-tuned open-source generative text models fine-tuned on KStack dataset with rule-based filtering. 
-This is a repository for fine-tuned CodeLlama-7b model in the Hugging Face Transformers format.
+This is a repository for the **CodeLlama-7b** model fine-tuned on the [KStack](https://huggingface.co/datasets/JetBrains/KStack) dataset with rule-based filtering, in the *Hugging Face Transformers* format. KStack is the largest collection of permissively licensed Kotlin code, and so the model is fine-tuned to work better with Kotlin code.
 
-# Model use
+# How to use
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
@@ -70,31 +69,31 @@ The model was trained on one A100 GPU with following hyperparameters:
 |        `total_batch_size`        |          128 (~65K tokens per step)          |
 |        `num_epochs`        |          1          |
 
-More details about finetuning can be found in the technical report
+More details about fine-tuning can be found in the technical report.
 
-# Data filtering
+# Fine-tuning data
 
-To increase the quality of the dataset and filter out statistical outliers such as homework assignments, we filter out the dataset entries according to the following rules:
-* We filter out files which belong to the low-popular repos (the sum of stars and forks is less than 6)
-* Next, we filter out files which belong to the repos with less than 5 Kotlin files
-* Finally, we remove files which have less than 20 SLOC
+For tuning the model, we used the [KStack](https://huggingface.co/datasets/JetBrains/KStack) dataset, the largest collection of permissively licensed Kotlin code. To increase the quality of the dataset and filter out outliers, such as homework assignments, we filter out the dataset entries according to the following rules:
+* We filter out files, which belong to low-popular repos (the sum of stars and forks is less than 6)
+* Next, we filter out files, which belong to repos with less than 5 Kotlin files
+* Finally, we remove files which have fewer than 20 SLOC
 
 We clean the content of the remaining dataset entries according to the following rules:
 * We remove all non-ASCII entries
-* We remove all package lines such as _package kotlinx.coroutines.channels_
-* We remove half of the import lines.
+* We remove all package lines, such as _package kotlinx.coroutines.channels_
+* We remove half of the import lines
 
 # Evaluation 
 
-To evaluate we used [Kotlin Humaneval](https://huggingface.co/datasets/JetBrains/Kotlin_HumanEval)
+For evaluation, we used the [Kotlin HumanEval](https://huggingface.co/datasets/JetBrains/Kotlin_HumanEval) dataset, which contains all 161 tasks from HumanEval translated into Kotlin by human experts. You can find more details about the pre-processing necessary to obtain our results, including the code for running, on the [datasets's page](https://huggingface.co/datasets/JetBrains/Kotlin_HumanEval).
 
-Fine-tuned model:
+Here are the results of our evaluation:
 
 |         **Model name**           |             **Kotlin HumanEval Pass Rate**              |
 |:---------------------------:|:----------------------------------------:|
-|           `base model`            |           26.09            |
-|        `fine-tuned model`        |          **29.19**         |
+|           `CodeLlama-7B`            |           26.09            |
+|        `CodeLlama-7B-KStack`        |          **29.19**         |
 
 # Ethical Considerations and Limitations
 
-CodeLlama-7B-KStack-full and its variants are a new technology that carries risks with use. The testing conducted to date could not cover all scenarios. For these reasons, as with all LLMs, CodeLlama-7B-KStack-full's potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. The model was fine-tuned on a specific data format (Kotlin tasks), and deviation from this format can also lead to inaccurate or undesirable responses to user queries. Therefore, before deploying any applications of CodeLlama-7B-KStack-full, developers should perform safety testing and tuning tailored to their specific applications of the model.
+CodeLlama-7B-KStack is a new technology that carries risks with use. The testing conducted to date has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, CodeLlama-7B-KStack's potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. The model was fine-tuned on a specific data format (Kotlin tasks), and deviation from this format can also lead to inaccurate or undesirable responses to user queries. Therefore, before deploying any applications of CodeLlama-7B-KStack, developers should perform safety testing and tuning tailored to their specific applications of the model.