nbertagnolli / counsel-chat Goto Github PK
View Code? Open in Web Editor NEWThis repository holds the code for working with data from counselchat.com
License: MIT License
This repository holds the code for working with data from counselchat.com
License: MIT License
Please add a readme to how to run this repository
Hello,
I recently came across your article and found it to be an amazing piece. I had some questions about copyright issues regarding the usage of this data. I was reading the TOS on counselchat and they strictly prohibit crawling data from their website. Therefore, I wanted to ask if you had any problems with copyright during this project. I also wanted to ask about whether it was possible to collect more data from this website, given that your data was collected last year, and if so, who I can contact.
Thank you!
Thank you for your detailed explanation. I am trying to replicate your results to understand how I can perform transfer learning on convai model. However, after cloning this repo I am unable to run the code using the below script. Actually, the GitHub repo doesn't have the train.py file.
python3 train.py --dataset_path counsel_chat_250-tokens.json --gradient_accumulation_steps=4 --lm_coef=2.0 --max_history=1 --n_epochs=3 --num_candidates=4 --train_batch_size=2
If I am running this script using the hugging face repo and modifying the code which you mentioned in the blog, I keep on getting one or the other error.
Since I want to look at the code and play around with it, I am not running this chunk of code:
make build
make interact CHECKPOINT_DIR=counselchat_convai
Thank you in advance.
INFO:interact.py:Get pretrained model and tokenizer
ftfy or spacy is not installed using BERT BasicTokenizer instead of SpaCy & ftfy.
Some weights of the model checkpoint at /tmp/tmpyfepv9pj were not used when initializing OpenAIGPTLMHeadModel: ['multiple_choice_head.summary.weight', 'multiple_choice_head.summary.bias']
- This IS expected if you are initializing OpenAIGPTLMHeadModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing OpenAIGPTLMHeadModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
INFO:interact.py:Sample a personality
2021-01-30 15:41:11.147627: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.10.1
INFO:interact.py:Selected personality:
>>> i am stuck
[[249, 1048, 3029]]
CausalLMOutput(loss=None, logits=tensor([[[ -8.6809, -6.6040, -13.2421, ..., -0.3766, -0.2954, -2.8872],
[ -6.4764, -5.8869, -12.1966, ..., -0.5273, -0.7109, -3.7030],
[ -8.2790, -7.2821, -13.0864, ..., -0.7790, -0.6198, -3.7207],
[ -8.1779, -6.7467, -12.0495, ..., -0.6559, -0.5704, -3.2958],
[-10.7485, -8.1295, -16.9996, ..., -1.5298, -0.8893, -4.5471],
[ -6.8998, -6.9460, -13.6065, ..., -0.9634, -0.8269, -3.9406]]]), hidden_states=None, attentions=None)
Traceback (most recent call last):
File "interact.py", line 242, in <module>
run()
File "interact.py", line 233, in run
out_ids = sample_sequence(personality, history, tokenizer, model, args)
File "interact.py", line 140, in sample_sequence
logits = logits[0, -1, :] / args.temperature
File "/usr/local/lib/python3.6/dist-packages/transformers/file_utils.py", line 1418, in __getitem__
return self.to_tuple()[k]
TypeError: tuple indices must be integers or slices, not tuple```
Traceback (most recent call last):
File "utils_test.py", line 19, in test_sample_candidates
df = pd.DataFrame(data, columns=["questionID", "answerText", 'split'])
File "/home/aqib/.local/lib/python3.8/site-packages/pandas/core/frame.py", line 468, in init
raise ValueError('DataFrame constructor not properly called!')
ValueError: DataFrame constructor not properly called!
please help i have tried different solutions but nothing worked
Hi, My name is Hojin Yang, and our group is trying to make counseling services using NLP. I saw this dataset from your medium posts, and I want to ask if I can use this data to improve our counseling model. I'm currently in Hackathon.
Hello again,
I emailed counselchat support as well as Eric but I haven't received any replies so far. Do you have any suggestions about ways to contact them other than by email? Thank you in advance.
I downloaded the file and unzip it. However I am confused where to run the make build and make interact commands.
I ran the commands in command prompt(windows) and got error saying make is not a keyword in docker.
Can you please guide us to know how to run these files on windows.
Thank you !
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.