Merge pull request #40 from YosefLab/valehvpa/fix_nb_typo

Fix `total_counts` to `total_count` in the module_user_guide

Author: adamgayoso

module_user_guide.ipynb

@@ -411,7 +411,7 @@
     "        # the pytorch NB distribution uses a different parameterization\n",
     "        # so we must apply a quick transformation (included in scvi-tools, but here we use the pytorch code)\n",
     "        nb_logits = (px_rate + 1e-4).log() - (theta + 1e-4).log()\n",
-    "        log_lik = NegativeBinomial(total_counts=theta, total=nb_logits).log_prob(x).sum(dim=-1)    \n",
+    "        log_lik = NegativeBinomial(total_count=theta, logits=nb_logits).log_prob(x).sum(dim=-1)    \n",
     "\n",
     "        # term 2\n",
     "        prior_dist = Normal(torch.zeros_like(qz_m), torch.ones_like(qz_v))\n",