feat: add tokenizer to repo

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+sentencepiece.bpe.model filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -45,7 +45,7 @@ import torch
 import torch.nn.functional as F
 from transformers import AutoTokenizer, AutoModel
 
-tokenizer = AutoTokenizer.from_pretrained("facebook/nllb-200-distilled-600M")
+tokenizer = AutoTokenizer.from_pretrained("fdschmidt93/NLLB-LLM2Vec-Meta-Llama-31-8B-Instruct-mntp-unsup-simcse")
 model = AutoModel.from_pretrained(
     "fdschmidt93/NLLB-LLM2Vec-Meta-Llama-31-8B-Instruct-mntp-unsup-simcse",
     trust_remote_code=True,

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14bb8dfb35c0ffdea7bc01e56cea38b9e3d5efcdcb9c251d6b40538e1aab555a
+size 4852054

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e316b82de11d0f951f370943b3c438311629547285129b0b81dadabd01bca665
+size 17331176

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "additional_special_tokens": null,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1024,
+  "name_or_path": "facebook/nllb-200-distilled-600M",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "src_lang": null,
+  "tgt_lang": null,
+  "tokenizer_class": "NllbTokenizer",
+  "unk_token": "<unk>"
+}