Upload folder using huggingface_hub

README.md

@@ -0,0 +1,29 @@
+
+---
+language: en
+license: mit
+base_model: BikoRiko/GPT-2.4-High-Pro
+tags:
+- gpt2
+- math
+- fine-tuned
+---
+
+# GPT-2.5-Math
+
+GPT-2.5-Math is an upgraded version of **BikoRiko/GPT-2.4-High-Pro**, featuring an expanded architecture and specialized fine-tuning on mathematical reasoning.
+
+## Model Details
+- **Architecture:** GPT-2 with 6 additional layers (Total parameters ~0.2B).
+- **Training Hardware:** NVIDIA H100 (via Modal.com).
+- **Dataset:** 5% subset of `microsoft/orca-math-word-problems-200k`.
+- **Objective:** Fine-tuned to solve math word problems and logical queries.
+
+## Performance
+The model is trained for mathematical reasoning. While it is a 0.2B parameter model, it demonstrates the beginning of logical grounding for basic word problems.
+
+## Training Details
+- **Optimizer:** AdamW
+- **Precision:** Mixed Precision (torch.amp)
+- **Epochs:** 3
+- **Learning Rate:** 5e-5

config.json

@@ -0,0 +1,41 @@
+{
+  "activation_function": "gelu_new",
+  "add_cross_attention": false,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 18,
+  "n_positions": 2048,
+  "pad_token_id": null,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.8.1",
+  "use_cache": false,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.8.1",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81eb10c958e28a8515f1c01579a363e7edc93e6fab22004e787fd663a64f7c19
+size 671036264

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "max_length": 128,
+  "model_max_length": 1024,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "stride": 0,
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>"
+}