phi-2-coder / README.md
mrm8488's picture
Update README.md
bb81dc4
---
tags:
- generated_from_trainer
- code
- coding
- phi-2
- phi2
model-index:
- name: phi-2-coder
results: []
license: apache-2.0
language:
- code
thumbnail: https://huggingface.co/mrm8488/llama-2-coder-7b/resolve/main/llama2-coder-logo-removebg-preview.png
datasets:
- HuggingFaceH4/CodeAlpaca_20K
pipeline_tag: text-generation
---
<div style="text-align:center;width:250px;height:250px;">
<img src="https://huggingface.co/mrm8488/llama-2-coder-7b/resolve/main/llama2-coder-logo-removebg-preview.png" alt="llama-2 coder logo"">
</div>
# Phi-2 Coder πŸ‘©β€πŸ’»
**Phi-2** fine-tuned on the **CodeAlpaca 20k instructions dataset** by using the method **QLoRA** with [PEFT](https://github.com/huggingface/peft) library.
## Model description 🧠
[Phi-2](https://huggingface.co/microsoft/phi-2)
Phi-2 is a Transformer with **2.7 billion** parameters. It was trained using the same data sources as [Phi-1.5](https://huggingface.co/microsoft/phi-1.5), augmented with a new data source that consists of various NLP synthetic texts and filtered websites (for safety and educational value). When assessed against benchmarks testing common sense, language understanding, and logical reasoning, Phi-2 showcased a nearly state-of-the-art performance among models with less than 13 billion parameters.
## Training and evaluation data πŸ“š
[CodeAlpaca_20K](https://huggingface.co/datasets/HuggingFaceH4/CodeAlpaca_20K): contains 20K instruction-following data used for fine-tuning the Code Alpaca model.
### LoRa config
```py
config = LoraConfig(
r=32,
lora_alpha=64,
target_modules=[
"Wqkv",
"fc1",
"fc2",
"out_proj"
],
bias="none",
lora_dropout=0.05,
task_type="CAUSAL_LM",
)
```
### Training hyperparameters βš™
```py
per_device_train_batch_size=4,
gradient_accumulation_steps=32,
num_train_epochs=2,
learning_rate=2.5e-5,
optim="paged_adamw_8bit",
seed=66,
load_best_model_at_end=True,
save_strategy="steps",
save_steps=50,
evaluation_strategy="steps",
eval_steps=50,
```
### Training results πŸ—’οΈ
| Step | Training Loss | Validation Loss |
|------|----------|----------|
| 50 | 0.624400 | 0.600070 |
| 100 | 0.634100 | 0.592757 |
| 150 | 0.545800 | 0.586652 |
| 200 | 0.572500 | 0.577525 |
| 250 | 0.528000 | 0.590118 |
### HumanEval results πŸ“Š
WIP
### Example of usage πŸ‘©β€πŸ’»
```py
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "mrm8488/phi-2-coder"
tokenizer = AutoTokenizer.from_pretrained(model_id, add_bos_token=True, trust_remote_code=True, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True, torch_dtype=torch.float16, device="auto")
def generate(
instruction,
max_new_tokens=128,
temperature=0.1,
top_p=0.75,
top_k=40,
num_beams=2,
**kwargs,
):
prompt = "Instruct: " + instruction + "\nOutput:"
print(prompt)
inputs = tokenizer(prompt, return_tensors="pt")
input_ids = inputs["input_ids"].to("cuda")
attention_mask = inputs["attention_mask"].to("cuda")
with torch.no_grad():
generation_output = model.generate(
input_ids=input_ids,
attention_mask=attention_mask,
max_new_tokens=max_new_tokens,
eos_token_id = tokenizer.eos_token_id,
use_cache=True,
early_stopping=True
)
output = tokenizer.decode(generation_output[0])
return output.split("\nOutput:")[1].lstrip("\n")
instruction = "Design a class for representing a person in Python."
print(generate(instruction))
```