(Trained with Unsloth)

config.json

@@ -1,31 +1,32 @@
 {
   "architectures": [
-    "Qwen2ForCausalLM"
+    "LlamaForCausalLM"
   ],
+  "attention_bias": false,
   "attention_dropout": 0.0,
-  "eos_token_id": 151643,
+  "bos_token_id": 1,
+  "eos_token_id": 11,
+  "head_dim": 256,
   "hidden_act": "silu",
-  "hidden_size": 3584,
+  "hidden_size": 3072,
   "initializer_range": 0.02,
-  "intermediate_size": 18944,
-  "max_position_embeddings": 131072,
-  "max_window_layers": 28,
-  "model_type": "qwen2",
-  "num_attention_heads": 28,
+  "intermediate_size": 23040,
+  "max_position_embeddings": 32768,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
   "num_hidden_layers": 28,
   "num_key_value_heads": 4,
-  "pad_token_id": 151654,
+  "pad_token_id": 131072,
+  "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 1000000.0,
-  "sliding_window": null,
+  "rope_theta": 1000042,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.52.4",
-  "unsloth_fixed": true,
-  "unsloth_version": "2025.6.2",
+  "transformers_version": "4.53.0",
+  "unsloth_optimized": true,
+  "unsloth_version": "2025.6.12",
   "use_cache": true,
-  "use_mrope": false,
-  "use_sliding_window": false,
-  "vocab_size": 152064
+  "vocab_size": 131073
 }

generation_config.json

@@ -1,8 +1,8 @@
 {
-  "bos_token_id": 151643,
-  "eos_token_id": 151643,
-  "max_length": 131072,
-  "max_new_tokens": 2048,
-  "pad_token_id": 151654,
-  "transformers_version": "4.52.4"
+  "_from_model_config": true,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "max_length": 32768,
+  "pad_token_id": 131072,
+  "transformers_version": "4.53.0"
 }

special_tokens_map.json

@@ -1,18 +1,28 @@
 {
   "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>"
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>EMAIL_ADDRESS<<",
+    ">>IP_ADDRESS<<",
+    "<|startoftext|>",
+    ">>IP_ADDRESS_0<<",
+    ">>IP_ADDRESS_1<<",
+    ">>IP_ADDRESS_2<<",
+    ">>IP_ADDRESS_3<<",
+    ">>IP_ADDRESS_4<<",
+    ">>IP_ADDRESS_5<<",
+    ">>IP_ADDRESS_6<<",
+    ">>IP_ADDRESS_7<<",
+    ">>IP_ADDRESS_8<<",
+    ">>IP_ADDRESS_9<<",
+    ">>PASSWORD<<",
+    ">>KEY<<"
   ],
   "eos_token": {
     "content": "<|endoftext|>",
@@ -21,11 +31,5 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<|vision_pad|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<|PAD_TOKEN|>"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
-size 11421896
+oid sha256:902807d87496a739869b5a41f76e8ea256e979f107a5716c7321bade51619426
+size 9780960