Upload folder using huggingface_hub

README.md

@@ -0,0 +1,49 @@
+---
+language:
+- en
+license: mit
+library_name: transformers
+tags:
+- gemma
+- text-generation
+- transformer
+datasets:
+- karpathy/tiny_shakespeare
+metrics:
+- cross_entropy
+---
+
+scaled down version of the **Gemma** architecture trained on the **Tiny Shakespeare** dataset.
+
+## Model 
+
+- **Architecture**: Gemma (Transformer Decoder)
+- **Attention**: Multi Query Attention (MQA)
+- **Hidden Size**: 768
+- **Number of Layers**: 12
+- **Number of Query Heads**: 2
+- **Number of KV Heads**: 1
+- **Sequence Length**: 128 (Block Size)
+- **Vocabulary Size**: 65 (Character-level encoding)
+- **Total Training Steps**: 3,500
+
+## Architecture 
+
+1. **RMSNorm**
+2. **GeGLU**
+3. **RoPE**
+4. **Embedding Scaling**
+
+## Usage
+
+You can load this model directly using the Hugging Face `transformers` library:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("parkneurals/Gemma")
+
+# Note: This model uses a custom character-level tokenizer. 
+# You can use the provided char_map.json for encoding/decoding.
+# This model also has slow inference (as I made it only for learning purposes; please bear if anyone using)
+```

char_map.json

@@ -0,0 +1 @@
+{"\n": 0, " ": 1, "!": 2, "$": 3, "&": 4, "'": 5, ",": 6, "-": 7, ".": 8, "3": 9, ":": 10, ";": 11, "?": 12, "A": 13, "B": 14, "C": 15, "D": 16, "E": 17, "F": 18, "G": 19, "H": 20, "I": 21, "J": 22, "K": 23, "L": 24, "M": 25, "N": 26, "O": 27, "P": 28, "Q": 29, "R": 30, "S": 31, "T": 32, "U": 33, "V": 34, "W": 35, "X": 36, "Y": 37, "Z": 38, "a": 39, "b": 40, "c": 41, "d": 42, "e": 43, "f": 44, "g": 45, "h": 46, "i": 47, "j": 48, "k": 49, "l": 50, "m": 51, "n": 52, "o": 53, "p": 54, "q": 55, "r": 56, "s": 57, "t": 58, "u": 59, "v": 60, "w": 61, "x": 62, "y": 63, "z": 64}

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "dtype": "float32",
+  "eos_token_id": 1,
+  "head_dim": 768,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.4.0",
+  "use_bidirectional_attention": null,
+  "use_cache": true,
+  "vocab_size": 65
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.4.0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae8880de3aed81718d81f53b79293aed3dbcfef366ec7e131d717808d68d647
+size 509896616