Prateek Gupta
In the decode features, why are we passing the one hot encoded values of the categorical variables? ``` self.decode_features = tf.concat([ tf.one_hot(decode_idx, self.num_decode_steps), tf.tile(tf.reshape(self.log_x_encode_mean, (-1, 1, 1)), (1, self.num_decode_steps, 1)),...
zero_loss = 2.0*tf.ones_like(smape) nonzero_loss = smape smape = tf.where(tf.logical_or(tf.equal(y, 0.0), tf.equal(y_hat, 0.0)), zero_loss, nonzero_loss) There is 'or' condition. What if y !=0.0 and y_hat=0.0. Sequence smape will still give value...
**Describe the bug** I have downloaded Wizard coder and it is not displaying the results correctly. I have added the screenshot. **Steps to reproduce** Steps to reproduce the behavior: 1....
**Problem** I am using it to create notes. A notebook containing threads and threads containing tags would be useful to filter. **Success Criteria** Ability to summarize notes from the notebook/tags....
### What happened? I tried using llama 3 and phi-3. Performance is good for both of these models in Jan UI and ollama. However, when using within obsidian, it takes...