🚀 Update RadonSAI-Small with real weights

config.json

@@ -1,13 +1,17 @@
 {
-  "vocab_size": 8192,
-  "hidden_size": 512,
+  "model_name": "radon",
+  "model_type": "gpt2",
+  "vocab_size": 32000,
+  "hidden_size": 256,
   "num_layers": 6,
   "num_attention_heads": 8,
-  "num_kv_heads": 2,
   "intermediate_size": 1024,
-  "max_position_embeddings": 2048,
-  "sliding_window": 1024,
-  "rope_theta": 10000.0,
-  "rms_norm_eps": 1e-06,
-  "torch_dtype": "float16"
+  "max_position_embeddings": 512,
+  "dropout": 0.1,
+  "attention_dropout": 0.1,
+  "activation_function": "gelu",
+  "layer_norm_eps": 1e-05,
+  "initializer_range": 0.02,
+  "use_cache": true,
+  "torch_dtype": "float32"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1112d3835309460d01234a91ceacd8cbac3954b2c96c42cfc9e247fe13f66fe4
-size 43535376
+oid sha256:d2c53c4c481761135c7ccad0edccb589e5e17d628a695332d3d527228c38dd03
+size 90721296

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}