Uploading VAE in neuro-symbolic-ai/eb-langvae-bert-base-cased-Qwen2.5-3B-l128

README.md

@@ -0,0 +1,13 @@
+---
+language: en
+tags:
+- pythae
+license: apache-2.0
+---
+
+### Downloading this model from the Hub
+This model was trained with pythae. It can be downloaded or reloaded using the method `load_from_hf_hub`
+```python
+>>> from pythae.models import AutoModel
+>>> model = AutoModel.load_from_hf_hub(hf_hub_path="your_hf_username/repo_name")
+```

decoder.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31ea5fb3b6d5ef612d7e61146b6c2cf926497902733056125dcf21311e57fd46
+size 156952702

decoder_cfg.json

@@ -0,0 +1 @@
+{"model_path": "Qwen/Qwen2.5-3B", "latent_size": 128, "max_len": 32, "conditional": false, "device_map": null}

encoder.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d88d1e1d98ebe021d308462ab9bbf71bc33af537ff9363bc6210e5333f1dbdc0
+size 787740

encoder_cfg.json

@@ -0,0 +1 @@
+{"model_path": "bert-base-cased", "latent_size": 128, "automodel_preset": {"cls": "AutoModelForTextEncoding", "pooling_method": "mean", "normalize": false}, "caching": true}

environment.json

@@ -0,0 +1 @@
+{"name": "EnvironmentConfig", "python_version": "3.11"}

model_config.json

@@ -0,0 +1 @@
+{"name": "VAEConfig", "input_dim": null, "latent_dim": 128, "uses_default_encoder": false, "uses_default_decoder": false, "reconstruction_loss": "mse"}