Step 500

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "AlinlightForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "alinlight",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "vocab_size": 128000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6b2fe8f052c670f51fe69ed24752c60e2dc2dda2420bf657df6de94fdac8aed
+size 3032738375

special_tokens_map.json

@@ -1,6 +1,30 @@
 {
-  "bos_token": "<BOS>",
-  "eos_token": "<EOS>",
-  "pad_token": "<PAD>",
-  "unk_token": "<UNK>"
+  "bos_token": {
+    "content": "<BOS>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<EOS>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<UNK>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d526559046f1e90fa94add973fedc7ccab2b5019d0a69525bd94f6fb448f598f
-size 11391088
+oid sha256:a0839415819a5b37239153cf30aadd092116f0bb1b8e5aa0cc1169c79572f13d
+size 11391355