Add new ColBERT model

2_Dense/config.json

@@ -0,0 +1,7 @@
+{
+    "in_features": 128,
+    "out_features": 768,
+    "bias": false,
+    "activation_function": "torch.nn.modules.linear.Identity",
+    "use_residual": false
+}

2_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b9aa25fbcb8a9175185ee625fa7d0460cf409797116efe226b55473c8e034ba
+size 196696

README.md

@@ -24,7 +24,7 @@ library_name: PyLate
 
 # Redis fine-tuned late-interaction ColBERT model for semantic caching on LangCache
 
-This is a [PyLate](https://github.com/lightonai/pylate) model finetuned from [lightonai/GTE-ModernColBERT-v1](https://huggingface.co/lightonai/GTE-ModernColBERT-v1) on the [LangCache Sentence Pairs (subsets=['all'], train+val=True)](https://huggingface.co/datasets/redis/langcache-sentencepairs-v1) dataset. It maps sentences & paragraphs to sequences of 128-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator.
+This is a [PyLate](https://github.com/lightonai/pylate) model finetuned from [lightonai/GTE-ModernColBERT-v1](https://huggingface.co/lightonai/GTE-ModernColBERT-v1) on the [LangCache Sentence Pairs (subsets=['all'], train+val=True)](https://huggingface.co/datasets/redis/langcache-sentencepairs-v1) dataset. It maps sentences & paragraphs to sequences of 768-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator.
 
 ## Model Details
 
@@ -33,7 +33,7 @@ This is a [PyLate](https://github.com/lightonai/pylate) model finetuned from [li
 - **Base model:** [lightonai/GTE-ModernColBERT-v1](https://huggingface.co/lightonai/GTE-ModernColBERT-v1) <!-- at revision 6605e431bed9b582d3eff7699911d2b64e8ccd3f -->
 - **Document Length:** 512 tokens
 - **Query Length:** 512 tokens
-- **Output Dimensionality:** 128 tokens
+- **Output Dimensionality:** 768 tokens
 - **Similarity Function:** MaxSim
 - **Training Dataset:**
     - [LangCache Sentence Pairs (subsets=['all'], train+val=True)](https://huggingface.co/datasets/redis/langcache-sentencepairs-v1)
@@ -52,6 +52,7 @@ This is a [PyLate](https://github.com/lightonai/pylate) model finetuned from [li
 ColBERT(
   (0): Transformer({'max_seq_length': 511, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
   (1): Dense({'in_features': 768, 'out_features': 128, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity', 'use_residual': False})
+  (2): Dense({'in_features': 128, 'out_features': 768, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity', 'use_residual': False})
 )
 ```
 

modules.json

@@ -10,5 +10,11 @@
     "name": "1",
     "path": "1_Dense",
     "type": "pylate.models.Dense.Dense"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Dense",
+    "type": "pylate.models.Dense.Dense"
   }
 ]