granite-embedding-30m-r1.1 (#7)

- Upload 12 files (975e6c6327805f806a4cced6530fcd96a88aeca8)

README.md

@@ -1,16 +1,4 @@
----
-language:
-- en
-license: apache-2.0
-library_name: sentence-transformers
-tags:
-- language
-- granite
-- embeddings
-- mteb
-- transformers
-pipeline_tag: sentence-similarity
----
+
 # Granite-Embedding-30m-English (revision r1.1)
 
 **News:** 

config.json

@@ -20,7 +20,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.15.0",
+  "transformers_version": "4.48.0",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 50265

merges.txt

@@ -1,4 +1,4 @@
-#version: 0.2 - Trained by `huggingface/tokenizers`
+#version: 0.2
 Ġ t
 Ġ a
 h e

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c8fffb9eed339923271999acc56019c9382db20234fa4a0e9c41c417c2c17b
-size 60630897
+oid sha256:9aafc4c906ec32a70a6a47aa6ff446b3b9b27a737c54fa07cbed13ce853298b8
+size 60605052

special_tokens_map.json

@@ -1 +1,51 @@
-{"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": false}}
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -1 +1,59 @@
-{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "added_tokens_decoder": {"0": {"content": "<s>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": true}, "1": {"content": "<pad>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": true}, "2": {"content": "</s>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": true}, "3": {"content": "<unk>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": true}, "50264": {"content": "<mask>", "lstrip": true, "normalized": true, "rstrip": false, "single_word": false, "special": true}}, "additional_special_tokens": [], "clean_up_tokenization_spaces": true, "model_max_length": 512, "special_tokens_map_file": "special_tokens_map.json", "name_or_path": "granite-embedding-30m-english", "tokenizer_class": "RobertaTokenizer"}
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}