Upload Pytho 25M model files (Safetensors + GGUF + Model Card)

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytho25m_Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,108 @@
 ---
-license: apache-2.0
+language:
+- en
+- code
+license: mit
+library_name: transformers
+tags:
+- code
+- python
+- pytho25m
+- tiny-llm
+- gguf
+- text-generation
+pipeline_tag: text-generation
+inference: true
+datasets:
+- iamtarun/python_code_instructions_18k_alpaca
+model_format:
+- safetensors
+- gguf
+params: 25103232
 ---
+
+# 🚀 Pytho 25M (Python Code Assistant)
+
+**Pytho 25M** (`Sayansantra/pytho25M`) is an ultra-compact ~25 Million parameter language model designed specifically for Python code generation and instruction following. Trained on 18,000 Python Alpaca instructions, Pytho 25M delivers fast Python code generation while using **under 30 MB of RAM**.
+
+Available in both **unquantized PyTorch Safetensors** and **4-bit quantized GGUF format**.
+
+---
+
+## 📊 Model Architecture Specs
+
+| Property | Value |
+|---|---|
+| **Model Name** | **Pytho 25M** (`Sayansantra/pytho25M`) |
+| **Parameters** | **25.10 Million** (25,103,232) |
+| **Architecture** | Custom Causal LM |
+| **Layers** | 14 Hidden Layers |
+| **Hidden Size (`d_model`)** | 384 |
+| **Intermediate Size (`mlp`)** | 1024 |
+| **Attention Heads** | 6 (Grouped-Query Attention w/ 2 KV Heads) |
+| **Vocabulary Size** | 8,000 (Custom Byte-Level BPE) |
+| **Max Context Length** | 512 Tokens |
+| **Special Tokens** | `<s>`, `<pad>`, `</s>`, `<unk>`, `<|system|>`, `<|user|>`, `<|assistant|>` |
+| **PyTorch Size** | 95.77 MB (FP32 Safetensors) |
+| **GGUF Q4_K_M Size** | 17.71 MB |
+
+---
+
+## ⚡ Quickstart Code Examples
+
+### 1. PyTorch / Transformers Usage
+
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_id = "Sayansantra/pytho25M"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float32)
+
+prompt = "<|system|>\nYou are an expert Python coding assistant.</s>\n<|user|>\nWrite a python function to check if a number is prime.</s>\n<|assistant|>\n"
+
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=60,
+    do_sample=True,
+    temperature=0.7,
+    pad_token_id=tokenizer.eos_token_id
+)
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+### 2. GGUF Usage with `llama-cpp-python`
+
+```python
+from llama_cpp import Llama
+
+llm = Llama.from_pretrained(
+    repo_id="Sayansantra/pytho25M",
+    filename="pytho25m_Q4_K_M.gguf",
+    verbose=False
+)
+
+prompt = "<|system|>\nYou are an expert Python coding assistant.</s>\n<|user|>\nWrite a python function to reverse a string.</s>\n<|assistant|>\n"
+response = llm(prompt, max_tokens=50)
+print(response["choices"][0]["text"])
+```
+
+---
+
+## 🏋️ Training Details
+
+- **Dataset:** 18,000 Python Alpaca instructions (`iamtarun/python_code_instructions_18k_alpaca`)
+- **Optimizer:** AdamW (`lr=8e-4`, `weight_decay=0.01`)
+- **Epochs:** 10 Epochs
+- **Batch Size:** 32 (Effective batch size)
+- **Precision:** Mixed FP16
+
+---
+
+## 📜 Citation & License
+
+Developed by **Sayan Santra**. Released under the **MIT License**.

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 14,
+  "num_key_value_heads": 2,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 8000
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 1,
+  "transformers_version": "5.0.0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b0dee43cbbb1dceef9b8015ec05efb213f22a8f9c712e5f7a07921f7d522e40
+size 100426920

pytho25m_Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af3ed17e53c5292cce6732b9c7305d6cf6746a2a93552637ee9a815131d09b40
+size 18573600

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "merges_file": "custom_python_tokenizer/merges.txt",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}