groupuser/phi-1_5
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Gustavo de Rosa 2023-12-13 22:44:59 +00:00 committed by huggingface-web
parent a286f5c1de
commit 80c0ba9f8e
1 changed files with 41 additions and 39 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

80
README.md
View File

@ -6,21 +6,24 @@ license_link: https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20L
language:
- en
pipeline_tag: text-generation
tags:
- nlp
- code
---
## Model Summary
The language model phi-1.5 is a Transformer with **1.3 billion** parameters. It was trained using the same data sources as [phi-1](https://huggingface.co/microsoft/phi-1), augmented with a new data source that consists of various NLP synthetic texts. When assessed against benchmarks testing common sense, language understanding, and logical reasoning, phi-1.5 demonstrates a nearly state-of-the-art performance among models with less than 10 billion parameters.
The language model Phi-1.5 is a Transformer with **1.3 billion** parameters. It was trained using the same data sources as [phi-1](https://huggingface.co/microsoft/phi-1), augmented with a new data source that consists of various NLP synthetic texts. When assessed against benchmarks testing common sense, language understanding, and logical reasoning, Phi-1.5 demonstrates a nearly state-of-the-art performance among models with less than 10 billion parameters.
We **did not** fine-tune phi-1.5 either for **instruction following or through reinforcement learning from human feedback**. The intention behind crafting this open-source model is to provide the research community with a non-restricted small model to explore vital safety challenges, such as reducing toxicity, understanding societal biases, enhancing controllability, and more.
We **did not** fine-tune Phi-1.5 either for **instruction following or through reinforcement learning from human feedback**. The intention behind crafting this open-source model is to provide the research community with a non-restricted small model to explore vital safety challenges, such as reducing toxicity, understanding societal biases, enhancing controllability, and more.
For a safer model release, we exclude generic web-crawl data sources such as common-crawl from the training. This strategy prevents direct exposure to potentially harmful online content, enhancing the model's safety without RLHF. However, the model is still vulnerable to generating harmful content. We hope the model can help the research community to further study the safety of language models.
phi-1.5 can write poems, draft emails, create stories, summarize texts, write Python code (such as downloading a Hugging Face transformer model), etc.
Phi-1.5 can write poems, draft emails, create stories, summarize texts, write Python code (such as downloading a Hugging Face transformer model), etc.
## Intended Uses
Given the nature of the training data, phi-1.5 is best suited for prompts using the QA format, the chat format, and the code format. Note that phi-1.5, being a base model, often produces irrelevant text following the main answer. In the following example, we've truncated the answer for illustrative purposes only.
Given the nature of the training data, Phi-1.5 is best suited for prompts using the QA format, the chat format, and the code format. Note that Phi-1.5, being a base model, often produces irrelevant text following the main answer. In the following example, we've truncated the answer for illustrative purposes only.
#### QA format:
### QA Format:
```markdown
Write a detailed analogy between mathematics and a lighthouse.
@ -29,7 +32,7 @@ Answer: Mathematics is like a lighthouse, guiding us through the vast ocean of n
```
where the model generates the text after "Answer:".
#### Chat format:
### Chat Format:
```markdown
Alice: I don't know why, I'm struggling to maintain focus while studying. Any suggestions?
@ -52,7 +55,8 @@ Bob: Yeah, and remember that it's okay to ask for help if you need it. We're her
```
where the model generates the text after the first "Bob:".
#### Code format:
### Code Format:
```python
def print_prime(n):
"""
@ -72,10 +76,36 @@ def print_prime(n):
where the model generates the text after the comments.
**Notes**
* phi-1.5 is intended for research purposes. The model-generated text/code should be treated as a starting point rather than a definitive solution for potential use cases. Users should be cautious when employing these models in their applications.
* Direct adoption for production tasks is out of the scope of this research project. As a result, phi-1.5 has not been tested to ensure that it performs adequately for any production-level application. Please refer to the limitation sections of this document for more details.
* Phi-1.5 is intended for research purposes. The model-generated text/code should be treated as a starting point rather than a definitive solution for potential use cases. Users should be cautious when employing these models in their applications.
* Direct adoption for production tasks is out of the scope of this research project. As a result, Phi-1.5 has not been tested to ensure that it performs adequately for any production-level application. Please refer to the limitation sections of this document for more details.
* If you are using `transformers>=4.36.0`, always load the model with `trust_remote_code=True` to prevent side-effects.
## Limitations of phi-1.5
## Sample Code
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
torch.set_default_device("cuda")
model = AutoModelForCausalLM.from_pretrained("microsoft/phi-1_5", torch_dtype="auto", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-1_5", trust_remote_code=True)
inputs = tokenizer('''```python
def print_prime(n):
"""
Print all primes between 1 and n
"""''', return_tensors="pt", return_attention_mask=False)
outputs = model.generate(**inputs, max_length=200)
text = tokenizer.batch_decode(outputs)[0]
print(text)
```
**Remark.** In the generation function, our model currently does not support beam search (`num_beams > 1`).
Furthermore, in the forward pass of the model, we currently do not support outputting hidden states or attention values, or using custom input embeddings.
## Limitations of Phi-1.5
* Generate Inaccurate Code and Facts: The model often produces incorrect code snippets and statements. Users should treat these outputs as suggestions or starting points, not as definitive or accurate solutions.
* Limited Scope for code: If the model generates Python scripts that utilize uncommon packages or scripts in other languages, we strongly recommend users manually verify all API uses.
@ -97,39 +127,11 @@ where the model generates the text after the comments.
### Software
* [PyTorch](https://github.com/pytorch/pytorch)
* [DeepSpeed](https://github.com/microsoft/DeepSpeed)
* [flash-attention](https://github.com/HazyResearch/flash-attention)
* [Flash-Attention](https://github.com/HazyResearch/flash-attention)
### License
The model is licensed under the [Research License](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx).
### Sample Code
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
torch.set_default_device("cuda")
model = AutoModelForCausalLM.from_pretrained("microsoft/phi-1_5", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-1_5", trust_remote_code=True)
inputs = tokenizer('''```python
def print_prime(n):
"""
Print all primes between 1 and n
"""''', return_tensors="pt", return_attention_mask=False)
outputs = model.generate(**inputs, max_length=200)
text = tokenizer.batch_decode(outputs)[0]
print(text)
```
If you need to use the model in a lower precision (e.g., FP16), please wrap the model's forward pass with `torch.autocast()`, as follows:
```python
with torch.autocast(model.device.type, dtype=torch.float16, enabled=True):
outputs = model.generate(**inputs, max_length=200)
```
**Remark.** In the generation function, our model currently does not support beam search (`num_beams` > 1).
Furthermore, in the forward pass of the model, we currently do not support outputting hidden states or attention values, or using custom input embeddings (instead of the model's).
### Citation
You can find the paper at https://arxiv.org/abs/2309.05463