Wilai-Reasoning

README.md

@@ -0,0 +1,55 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: Wilai-Reasoning
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Wilai-Reasoning
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0005
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.2.2+cu121
+- Datasets 4.0.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,20 @@
+{
+  "architectures": [
+    "ReasoningModel"
+  ],
+  "hidden_size": 768,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 2048,
+  "model_type": "OpenThaiWilaiReasoning",
+  "num_experts": 4,
+  "num_heads": 8,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 8,
+  "num_layers": 8,
+  "pad_token_id": 0,
+  "rope": true,
+  "top_k": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "vocab_size": 119547
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b53788ed897c344b0bc046e34c98b90d6be3f9c28e91503bee55bf9a9bc584
+size 1054126358

runs/Sep07_22-13-30_d45f344fd312/events.out.tfevents.1757283223.d45f344fd312.418.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30a1ecb9f38421aebb4e8e6988f273bf7289fde7f7935293556663b024ab311f
+size 6212

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 +1,55 @@
+{
+  "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_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdef3671defdbc009b6630ee05dda4e8849012d2427c5de7cba3c8a5cb53a31e
+size 5176