Rollback

config.json

@@ -4,27 +4,29 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 32001,
-  "head_dim": 32,
+  "bos_token_id": 0,
+  "eos_token_id": 3,
+  "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 256,
-  "initializer_range": 0.02,
-  "intermediate_size": 1024,
-  "max_position_embeddings": 8192,
+  "hidden_size": 576,
+  "initializer_range": 0.041666666666666664,
+  "intermediate_size": 1536,
+  "is_llama_config": true,
+  "max_position_embeddings": 4096,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 12,
-  "num_key_value_heads": 2,
-  "pad_token_id": 32003,
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pad_token_id": 1,
   "pretraining_tp": 1,
-  "rms_norm_eps": 1e-06,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
+  "rope_theta": 100000,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.52.4",
   "use_cache": true,
-  "vocab_size": 32018
+  "vocab_size": 32000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9e511a89a68110f896a7373f812fd6041629cc471887aabcda85447c7031f28
-size 78437072
+oid sha256:aaaf5bd62a28c1e2ea35ce725cd2e608c582aac986ca5bba4639e77aa9701515
+size 498572168

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f24e35414c22e483b892df074f22186bcbfd1b1c1f183ef4c8f4990f826ff30
-size 2869924
+oid sha256:a36c3ff5b839a44b064837a12b832e61cab245c31d1618d03c85d1314cc07911
+size 2846439

tokenizer_config.json

@@ -1,143 +1,143 @@
 {
   "added_tokens_decoder": {
-    "32000": {
-      "content": "<|im_start|>",
+    "0": {
+      "content": "<|unk_token|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32001": {
-      "content": "<|im_end|>",
+    "1": {
+      "content": "<|pad_token|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32002": {
-      "content": "<|unk_token|>",
+    "2": {
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32003": {
-      "content": "<|pad_token|>",
+    "3": {
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32004": {
+    "4": {
       "content": "<tool_call>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "32005": {
+    "5": {
       "content": "</tool_call>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "32006": {
+    "6": {
       "content": "<think>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "32007": {
+    "7": {
       "content": "</think>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "32008": {
-      "content": "<|unused_special_token_0|>",
+    "8": {
+      "content": "<|unused_token_0|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32009": {
-      "content": "<|unused_special_token_1|>",
+    "9": {
+      "content": "<|unused_token_1|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32010": {
-      "content": "<|unused_special_token_2|>",
+    "10": {
+      "content": "<|unused_token_2|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32011": {
-      "content": "<|unused_special_token_3|>",
+    "11": {
+      "content": "<|unused_token_3|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32012": {
-      "content": "<|unused_special_token_4|>",
+    "12": {
+      "content": "<|unused_token_4|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32013": {
-      "content": "<|unused_special_token_5|>",
+    "13": {
+      "content": "<|unused_token_5|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32014": {
-      "content": "<|unused_special_token_6|>",
+    "14": {
+      "content": "<|unused_token_6|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32015": {
-      "content": "<|unused_special_token_7|>",
+    "15": {
+      "content": "<|unused_token_7|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32016": {
-      "content": "<|unused_special_token_8|>",
+    "16": {
+      "content": "<|unused_token_8|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32017": {
-      "content": "<|unused_special_token_9|>",
+    "17": {
+      "content": "<|unused_token_9|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -148,7 +148,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "extra_special_tokens": {},
-  "model_max_length": 4096,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|pad_token|>",
   "tokenizer_class": "PreTrainedTokenizer",
   "unk_token": "<|unk_token|>"

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b9edc82518a3363d37477942c413c134ab6b8f4032a4f60942c01d82a0577ef
+oid sha256:02a35e277ab5aa892680510168973e0c935efdcd186a619b19b5aaf90d144b98
 size 5713