|
--- |
|
license: apache-2.0 |
|
language: |
|
- en |
|
pipeline_tag: summarization |
|
widget: |
|
- text: What is the peak phase of T-eV? |
|
example_title: Question Answering |
|
tags: |
|
- arxiv |
|
--- |
|
# Table of Contents |
|
|
|
0. [TL;DR](#TL;DR) |
|
1. [Model Details](#model-details) |
|
2. [Usage](#usage) |
|
3. [Uses](#uses) |
|
4. [Citation](#citation) |
|
|
|
# TL;DR |
|
|
|
This is a Phi-1_5 model trained on [meta-math/MetaMathQA](https://huggingface.co/datasets/meta-math/MetaMathQA). This model is for research purposes only and ***should not be used in production settings***. |
|
|
|
|
|
## Model Description |
|
|
|
|
|
- **Model type:** Language model |
|
- **Language(s) (NLP):** English |
|
- **License:** Apache 2.0 |
|
- **Related Models:** [Phi-1_5](https://huggingface.co/microsoft/phi-1_5) |
|
|
|
# Usage |
|
|
|
Find below some example scripts on how to use the model in `transformers`: |
|
|
|
## Using the Pytorch model |
|
|
|
```python |
|
|
|
from huggingface_hub import notebook_login |
|
from datasets import load_dataset, Dataset |
|
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer |
|
|
|
model = "ArtifactAI/phi-metamath" |
|
|
|
model = AutoModelForCausalLM.from_pretrained(base_model, trust_remote_code= True) |
|
tokenizer = AutoTokenizer.from_pretrained(base_model, trust_remote_code=True) |
|
|
|
def generate(prompt): |
|
inputs = tokenizer(f'''Below is an instruction that describes a task. Write a response that appropriately completes the request If you are adding additional white spaces, stop writing".\n\n### Instruction:\n{prompt}.\n\n### Response:\n ''', return_tensors="pt", return_attention_mask=False) |
|
streamer = TextStreamer(tokenizer, skip_prompt= True) |
|
_ = model.generate(**inputs, streamer=streamer, max_new_tokens=500) |
|
|
|
generate("What are the common techniques used in identifying a new species, and how can scientists accurately categorize it within the existing taxonomy system?") |
|
``` |
|
|
|
## Training Data |
|
|
|
The model was trained on [meta-math/MetaMathQA](https://huggingface.co/datasets/meta-math/MetaMathQA), a dataset of question/answer pairs. |
|
|
|
|
|
## Training procedure |
|
|
|
|
|
The following `bitsandbytes` quantization config was used during training: |
|
- quant_method: bitsandbytes |
|
- load_in_8bit: False |
|
- load_in_4bit: True |
|
- llm_int8_threshold: 6.0 |
|
- llm_int8_skip_modules: None |
|
- llm_int8_enable_fp32_cpu_offload: False |
|
- llm_int8_has_fp16_weight: False |
|
- bnb_4bit_quant_type: nf4 |
|
- bnb_4bit_use_double_quant: True |
|
- bnb_4bit_compute_dtype: float16 |
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.6.2 |
|
## Training procedure |
|
|
|
|
|
The following `bitsandbytes` quantization config was used during training: |
|
- quant_method: bitsandbytes |
|
- load_in_8bit: False |
|
- load_in_4bit: True |
|
- llm_int8_threshold: 6.0 |
|
- llm_int8_skip_modules: None |
|
- llm_int8_enable_fp32_cpu_offload: False |
|
- llm_int8_has_fp16_weight: False |
|
- bnb_4bit_quant_type: nf4 |
|
- bnb_4bit_use_double_quant: True |
|
- bnb_4bit_compute_dtype: float16 |
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.6.2 |
|
|
|
# Citation |
|
|
|
``` |
|
@misc{phi-metamath, |
|
title={phi-metamath}, |
|
author={Matthew Kenney}, |
|
year={2023} |
|
} |
|
``` |
