Upload folder using huggingface_hub

README.md

@@ -0,0 +1,37 @@
+
+# GPT-2.5-Code
+
+GPT-2.5-Code is a 0.5B parameter causal language model specialized for Python coding tasks. It was created by fine-tuning the [BikoRiko/GPT-2.5-Math](https://huggingface.co/BikoRiko/GPT-2.5-Math) base model.
+
+## Model Details
+- **Developed by:** BikoRiko
+- **Model type:** GPT-2 architecture
+- **Language(s):** Python, English
+- **License:** MIT
+- **Fine-tuned from model:** BikoRiko/GPT-2.5-Math
+
+## Training Procedure
+- **Infrastructure:** NVIDIA H100 GPU via Modal.com
+- **Dataset:** `flytech/python-codes-25k` (Specialized subset)
+- **Epochs:** 5
+- **Learning Rate:** 1e-4 (Cosine schedule)
+- **Batch Size:** 4 with Gradient Accumulation (4 steps)
+
+## Intended Use
+This model is designed for short-form Python code generation and completion tasks. It has been transitioned from a mathematical reasoning focus to a structured programming focus.
+
+## How to use
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("BikoRiko/GPT-2.5-Code")
+model = AutoModelForCausalLM.from_pretrained("BikoRiko/GPT-2.5-Code")
+
+instruction = "Write a python function to calculate the area of a circle."
+prompt = f"Instruction: {instruction}
+Output:"
+inputs = tokenizer(prompt, return_tensors="pt")
+
+outputs = model.generate(**inputs, max_new_tokens=128)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```

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 sha256:99535411af61a0e1fbaae734560a3cfdc3ff609e7574459159c82828edf1688c
+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|>"
+}