Upload folder using huggingface_hub

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "SnowflakeCoreG1"
+  ],
+  "model_type": "snowflake_core",
+  "vocab_size": 50257,
+  "embed_dim": 1024,
+  "num_heads": 16,
+  "num_layers": 24,
+  "max_length": 2048,
+  "ffn_dim": 4096,
+  "pad_token_id": 50256,
+  "eos_token_id": 50256,
+  "bos_token_id": 50256,
+  "unk_token_id": 50256,
+  "training_config": {
+    "epochs": 2,
+    "actual_epochs": 0,
+    "batch_size": 1,
+    "learning_rate": 0.0002,
+    "grad_accum_steps": 32,
+    "max_length": 2048,
+    "val_split_ratio": 0.1,
+    "early_stopping": {
+      "patience": 3,
+      "min_delta": 0.001,
+      "triggered": false
+    }
+  },
+  "training_metrics": {
+    "final_train_loss": null,
+    "final_train_perplexity": null,
+    "final_val_loss": null,
+    "final_val_perplexity": null,
+    "best_val_loss": Infinity,
+    "best_val_perplexity": null
+  }
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "do_sample": true,
+  "temperature": 1.0,
+  "top_p": 0.9,
+  "top_k": 50,
+  "max_new_tokens": 50,
+  "pad_token_id": 50256,
+  "eos_token_id": 50256,
+  "bos_token_id": 50256
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cadb8ff7738041e381ef3c4357276bbf95f64f0e8824f3be6f57bafc812e0159
+size 1629367568

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eb12b0b69c5f1eaf5df0bae4b3bafde76cf24d3ea2df003fdbf298f7b034427
+size 1629446071

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_metrics.json

@@ -0,0 +1,30 @@
+{
+  "epochs": [],
+  "train_losses": [],
+  "train_perplexities": [],
+  "val_losses": [],
+  "val_perplexities": [],
+  "early_stopping": {
+    "triggered": false,
+    "patience": 3,
+    "min_delta": 0.001,
+    "best_val_loss": Infinity,
+    "epochs_completed": 0,
+    "epochs_planned": 2
+  },
+  "training_config": {
+    "epochs": 2,
+    "actual_epochs": 0,
+    "batch_size": 1,
+    "learning_rate": 0.0002,
+    "grad_accum_steps": 32,
+    "max_length": 2048,
+    "val_split_ratio": 0.1,
+    "model_size": {
+      "embed_dim": 1024,
+      "num_heads": 16,
+      "num_layers": 24,
+      "ffn_dim": 4096
+    }
+  }
+}