Upload 5 files

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "umise/vector_test",
+  "_name_or_path": "umisetokikaze/vectorizen-1",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -10,7 +10,7 @@
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
-  "max_position_embeddings": 32768,
+  "max_position_embeddings": 4096,
   "model_type": "mistral",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
@@ -19,8 +19,8 @@
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.40.0",
-  "use_cache": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
   "vocab_size": 32000
 }

special_tokens_map.json

@@ -1,30 +1,5 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,7 +1,6 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
-  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -33,9 +32,8 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,
-  "model_max_length": 8192,
-  "pad_token": "<unk>",
-  "padding_side": "right",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",