(Trained with Unsloth)

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "_name_or_path": "EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-0.001-128K-auto",
   "architectures": [
     "LlamaForCausalLM"
   ],

pytorch_model-00001-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5766346e356646e838cc329b205e607bf5056f0a89d7d075b63054ce6648692
+oid sha256:4e3fec71b6442d10ee1a8fc050a7193e186f0eb94d4c90f21c69fd5350167fb0
 size 4976718466

pytorch_model-00002-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caf5a71430c9cd9059a5703d8a13d33ea9577c6c2fab593c8fa68830b5ed60d7
+oid sha256:782a25784ad07db6aff7ed284d624fc667fbb2ecd13babff05a8c23624382613
 size 4999826950

pytorch_model-00003-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff6d1febe71cc409bfa543321939d535cccf62b63dd2571bf909e15c6f52a75d
+oid sha256:ed0a931de841cf1976fcdde98a15c89296cc6faa376834a63a79c1022fd60f45
 size 4915939082

pytorch_model-00004-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32764ce6af72d9f2ecf1a774d937d20d5a4f876db087471d4818ceeb8c1e507a
+oid sha256:559b72e54b967f06c1cc7e2610c6b0eccbff92c04e536ba1401eee8d1632d514
 size 1168140873

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

@@ -2054,6 +2054,7 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|eot_id|>",
   "extra_special_tokens": {},
+  "max_length": 128000,
   "model_input_names": [
     "input_ids",
     "attention_mask"
@@ -2061,5 +2062,8 @@
   "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
   "padding_side": "left",
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first"
 }