Upload full model and tokenizer trained from scratch

.gitattributes

@@ -33,3 +33,5 @@ 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
+tokenizer_config.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -9,21 +9,21 @@
   "eos_token_id": 2,
   "head_dim": 96,
   "hidden_act": "silu",
-  "hidden_size": 192,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 1024,
+  "intermediate_size": 3072,
   "max_position_embeddings": 1024,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 2,
-  "num_hidden_layers": 1,
-  "num_key_value_heads": 1,
+  "num_attention_heads": 8,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 8,
   "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
+  "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "transformers_version": "4.57.1",
   "use_cache": false,
-  "vocab_size": 32000
+  "vocab_size": 282454
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d4f2cbd84ad3474e6a608194a0226512c068780ae315a30500202934c9ae8c9
-size 51957256
+oid sha256:4ae99f9be087936a8eb78d6a64ee0943473ae23e0ae12afcc0589a87f3f6a676
+size 2641542424

special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a11cbf577f7fa6ab99247e2a6b919fe9d7fe79dd171998154948dbc9a5001cbd
+size 49835349

tokenizer_config.json

@@ -1,44 +1,3 @@
-{
-  "add_bos_token": true,
-  "add_eos_token": true,
-  "add_prefix_space": true,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "extra_special_tokens": {},
-  "legacy": true,
-  "model_max_length": 2048,
-  "pad_token": "</s>",
-  "padding_side": "left",
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:e344412418aba9ab8fcc04ba55cf0c6dc4cffbe373a3b084a8a115283ad30205
+size 43712771

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0f4c0b7b71289e21a825e25f1b3bae1af68cb77e8002c6cb71394aedf7207fa
+oid sha256:a8e94f51e961be2729b2ec8db6868e10ddaa3b1cadfc5a12b98888bd0a4b6a2f
 size 5841