Upload 7 files

README.md

@@ -1,3 +1,33 @@
----
-license: apache-2.0
----
+# Snowflake-G0-Release
+
+This is the initial release of the Snowflake series language models, trained on the DialogMLM-50K dataset with optimized memory usage.
+
+## Model details
+- Architecture: SnowflakeCore
+- Hidden size: 384
+- Number of attention heads: 6
+- Number of layers: 4
+- Feed-forward dimension: 768
+- Maximum sequence length: 384
+- Vocabulary size: 30522
+
+## HuggingFace Transformers Compatibility
+This model is fully compatible with the HuggingFace Transformers library. You can load it using:
+
+```python
+from transformers import AutoConfig, AutoModel, AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("path/to/snowflake_g0_release")
+config = AutoConfig.from_pretrained("path/to/snowflake_g0_release")
+model = AutoModel.from_pretrained("path/to/snowflake_g0_release")
+```
+
+## Memory Optimization Techniques
+- Mixed precision training
+- Gradient accumulation (4 steps)
+- Fused QKV projection
+- Pre-norm architecture
+- Weight tying between embedding and output layers
+- Half-precision model storage
+
+The model weights are stored in both PyTorch (.bin) and safetensors format for improved security, loading efficiency, and compatibility.

config.json

@@ -0,0 +1,12 @@
+{
+  "architectures": [
+    "SnowflakeCore"
+  ],
+  "hidden_size": 384,
+  "intermediate_size": 768,
+  "max_position_embeddings": 384,
+  "num_attention_heads": 6,
+  "num_hidden_layers": 4,
+  "transformers_version": "4.51.3",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71cc42d8dfe014ef49409730a63eb30e085822c768360f8263b9c0428372086d
+size 33274540

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bb569d5315b86cd6109c43c565f3400e3127765ffa7fe7c8ca9f53b757377a1
+size 66559270

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}