Trimmed Granite Embedding 107M for Czech

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,47 @@
+---
+pipeline_tag: feature-extraction
+language: ces
+tags:
+  - trimmed
+  - embeddings
+library_name: transformers
+base_model: ibm-granite/granite-embedding-107m-multilingual
+base_model_relation: quantized
+datasets:
+  - Lumberjackk/fineweb-2-trimming
+---
+
+# granite-embedding-107m-ces-32767
+
+This model is a 78.0% smaller version of [ibm-granite/granite-embedding-107m-multilingual](https://huggingface.co/ibm-granite/granite-embedding-107m-multilingual) 
+optimized for Czech language via vocabulary trimming mined on [Lumberjackk/fineweb-2-trimming](https://huggingface.co/datasets/Lumberjackk/fineweb-2-trimming).
+
+## Model Statistics
+- **Original vocabulary size:** 250,002 tokens 
+- **Trimmed vocabulary size:** 32,768 tokens
+- **Vocabulary reduction:** 86.9%
+- **Original model size:** 106,994,304 parameters  
+- **Trimmed model size:** 23,576,448 parameters  
+- **Size reduction:** 78.0% 
+
+
+## Usage
+
+```python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer("lbourdois/granite-embedding-107m-ces-32767")
+
+query = "My query"
+documents = [
+    "Chunk 1",
+    "Chunk 2",
+    "Chunk 3",
+]
+query_embeddings = model.encode(query)
+document_embeddings = model.encode(documents)
+print(query_embeddings.shape, document_embeddings.shape)
+
+similarities = model.similarity(query_embeddings, document_embeddings)
+print(similarities)
+```

config.json

@@ -0,0 +1,29 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32768
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e268b7e04623a26ea2a25b169c5c2ecb0218825ea78c17a8a7a278c055cdb881
+size 94317104

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>",
+  "sep_token": "</s>",
+  "pad_token": "<pad>",
+  "cls_token": "<s>",
+  "mask_token": {
+    "content": "<mask>",
+    "single_word": false,
+    "lstrip": true,
+    "rstrip": false,
+    "normalized": true
+  }
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": true,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}