|
--- |
|
license: apache-2.0 |
|
language: |
|
- en |
|
datasets: |
|
- Waterhorse/chess_data |
|
- anon8231489123/ShareGPT_Vicuna_unfiltered |
|
- OpenAssistant/oasst1 |
|
- vicgalle/alpaca-gpt4 |
|
--- |
|
|
|
# Chessgpt-Chat-v1 |
|
|
|
Chessgpt-Chat-v1 is the sft-tuned model of Chessgpt-Base-v1. |
|
|
|
- Base Model: [Chessgpt-base-v1](https://huggingface.co/Waterhorse/chessgpt-base-v1) |
|
- Chat Version: [Chessgpt-chat-v1](https://huggingface.co/Waterhorse/chessgpt-chat-v1) |
|
|
|
Also, we are actively working on the development of the next-generation model, ChessGPT-V2. We welcome any contribution, especially on chess related dataset. For related matters, please contact xidong.feng.20@ucl.ac.uk. |
|
|
|
## Model Details |
|
- **Model type**: Language Model |
|
- **Language(s)**: English |
|
- **License**: Apache 2.0 |
|
- **Model Description**: A 2.8B parameter pretrained language model in Chess. |
|
|
|
## GPU Inference |
|
|
|
This requires a GPU with 8GB memory. |
|
|
|
```python |
|
import torch |
|
import transformers |
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
MIN_TRANSFORMERS_VERSION = '4.25.1' |
|
|
|
# check transformers version |
|
assert transformers.__version__ >= MIN_TRANSFORMERS_VERSION, f'Please upgrade transformers to version {MIN_TRANSFORMERS_VERSION} or higher.' |
|
|
|
# init |
|
tokenizer = AutoTokenizer.from_pretrained("Waterhorse/chessgpt-chat-v1") |
|
model = AutoModelForCausalLM.from_pretrained("Waterhorse/chessgpt-chat-v1", torch_dtype=torch.float16) |
|
model = model.to('cuda:0') |
|
|
|
# infer |
|
# Conversation between two |
|
prompt = "A friendly, helpful chat between some humans.<|endoftext|>Human 0: 1.e4 c5, what is the name of this opening?<|endoftext|>Human 1:" |
|
# Conversation between more than two |
|
#prompt = "A friendly, helpful chat between some humans.<|endoftext|>Human 0: 1.e4 c5, what is the name of this opening?<|endoftext|>Human 1: Sicilian defense.<|endoftext|>Human 2:" |
|
|
|
inputs = tokenizer(prompt, return_tensors='pt').to(model.device) |
|
input_length = inputs.input_ids.shape[1] |
|
outputs = model.generate( |
|
**inputs, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.7, top_k=50, return_dict_in_generate=True, |
|
) |
|
token = outputs.sequences[0, input_length:] |
|
output_str = tokenizer.decode(token) |
|
print(output_str) |
|
``` |
|
|
|
# Uses |
|
|
|
Excluded uses are described below. |
|
|
|
### Direct Use |
|
|
|
`chessgpt-chat-v1` is mainly for research on large language model, especially for those research about policy learning and language modeling. |
|
|
|
#### Out-of-Scope Use |
|
|
|
`chessgpt-chat-v1` is a language model trained on chess related data and may not perform well for other use cases beyond chess domain. |
|
|
|
#### Bias, Risks, and Limitations |
|
|
|
Just as with any language model, chessgpt-chat-v1 carries inherent limitations that necessitate careful consideration. Specifically, it may occasionally generate responses that are irrelevant or incorrect, particularly when tasked with interpreting complex or ambiguous queries. Additionally, given that its training is rooted in online data, the model may inadvertently reflect and perpetuate common online stereotypes and biases. |
|
|
|
# Evaluation |
|
Please refer to our [paper](https://arxiv.org/abs/2306.09200) and [code](https://github.com/waterhorse1/ChessGPT)for benchmark results. |
|
|
|
# Citation Information |
|
```bash |
|
@article{feng2023chessgpt, |
|
title={ChessGPT: Bridging Policy Learning and Language Modeling}, |
|
author={Feng, Xidong and Luo, Yicheng and Wang, Ziyan and Tang, Hongrui and Yang, Mengyue and Shao, Kun and Mguni, David and Du, Yali and Wang, Jun}, |
|
journal={arXiv preprint arXiv:2306.09200}, |
|
year={2023} |
|
} |
|
``` |
