Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "unsloth/Meta-Llama-3.1-8B",
+  "_name_or_path": "meta-llama/Meta-Llama-3.1-8B",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -7,6 +7,7 @@
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
   "eos_token_id": 128001,
+  "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -30,8 +31,8 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.44.2",
-  "unsloth_version": "2024.9",
+  "transformers_version": "4.49.0.dev0",
+  "unsloth_fixed": true,
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -7,5 +7,5 @@
   "pad_token_id": 128004,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.44.2"
+  "transformers_version": "4.49.0.dev0"
 }

special_tokens_map.json

@@ -13,5 +13,11 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|finetune_right_pad_id|>"
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,4 +1,5 @@
 {
+  "add_bos_token": true,
   "added_tokens_decoder": {
     "128000": {
       "content": "<|begin_of_text|>",
@@ -2052,6 +2053,7 @@
   "bos_token": "<|begin_of_text|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
   "model_input_names": [
     "input_ids",
     "attention_mask"
@@ -2059,5 +2061,6 @@
   "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
   "padding_side": "left",
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": null
 }