FastPlus125m Geodesic Backup checkpoint-98600 at global step 98600

checkpoint-98600/config.json

@@ -0,0 +1,20 @@
+{
+  "architectures": [
+    "FastPlus125mForCausalLM"
+  ],
+  "dtype": "float32",
+  "hidden_size": 768,
+  "hyperbolic_dim": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "kd_alpha": 0.4,
+  "kd_temperature": 2.5,
+  "max_position_embeddings": 512,
+  "model_type": "fastplus_125m",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 16,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.13.1",
+  "use_cache": false,
+  "vocab_size": 32704
+}

checkpoint-98600/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.13.1"
+}

checkpoint-98600/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": [
+    "<|user|>",
+    "<|assistant|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}