metadata

license: other
library_name: peft
tags:
  - generated_from_trainer
base_model: microsoft/phi-2
model-index:
  - name: phi-2-FCRL-v0.1
    results: []

phi-2-FCRL-v0.1

This model is a fine-tuned version of microsoft/phi-2 on vicgalle/alpaca-gpt4, nRuaif/OpenOrca-GPT3.5, sahil2801/CodeAlpaca-20k

Quick start

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("npvinHnivqn/phi-2-FCRL-v0.1", trust_remote_code=True, torch_dtype=torch.float32)
tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-2-FCRL-v0.1", trust_remote_code=True)
inputs = tokenizer('''<SYSTEM>: You are a very good and helpful chatbot, you can answer almost every questions. <|USER|>: Write a short story about a curious cat <|BOT|>:''', return_tensors="pt", return_attention_mask=False)

outputs = model.generate(**inputs, max_length=512)
text = tokenizer.batch_decode(outputs)[0]
print(text)

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 2
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
num_epochs: 1

Framework versions

PEFT 0.7.1
Transformers 4.36.0
Pytorch 2.0.0
Datasets 2.15.0
Tokenizers 0.15.0