Upload 8 files

README.md

@@ -1,3 +1,59 @@
----
-license: apache-2.0
----
+---
+language:
+- tr
+license: apache-2.0
+library_name: transformers
+tags:
+- llama-3
+- turkish
+- tiny-llama
+- scratch-build
+datasets:
+- TFLai/Turkish-Alpaca
+metrics:
+- loss
+model_type: llama
+---
+
+# Llama-TR-Mini (9M Parameters)
+
+Llama-TR-Mini is an experimental, ultra-lightweight Turkish language model with **134 million parameters**, trained from scratch using the Llama 3 architecture. 
+
+This project was developed to explore the limits of small-scale language modeling and to understand the end-to-end pre-training/fine-tuning pipeline on consumer-grade hardware (Apple Silicon).
+
+## Model Specifications
+- **Architecture:** Llama 3
+- **Parameters:** 134,105,856
+- **Hidden Size:** 768
+- **Intermediate Size:** 2048
+- **Number of Layers:** 12
+- **Attention Heads:** 12
+- **Vocabulary Size:** 32,000 (Custom Turkish Tokenizer)
+- **Training Epochs:** 30
+- **Device:** MacBook Pro (MPS - Metal Performance Shaders)
+
+## Training Data
+The model was trained on the [Turkish-Alpaca](https://huggingface.co/datasets/TFLai/Turkish-Alpaca) dataset, which contains approximately 52K instruction-following pairs translated into Turkish.
+
+## Intended Use & Limitations
+**Important Note:** Due to its extremely small size (134M parameters), this model is prone to significant hallucinations and may produce nonsensical or repetitive outputs. 
+
+- **Purpose:** Educational purposes, understanding LLM mechanics.
+- **Not Suited For:** Production environments, factual information retrieval, or complex reasoning tasks.
+- **Format:** Optimized for the Llama 3 Instruct template (`<|start_header_id|>user<|end_header_id|>`).
+
+## How to Use
+You can load this model using the `transformers` library:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "k12tr/mini-tr-134M"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+prompt = "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\nTürkiye'nin başkenti neresidir?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"
+inputs = tokenizer(prompt, return_tensors="pt")
+output = model.generate(**inputs, max_new_tokens=50, temperature=0.1, repetition_penalty=1.5)
+
+print(tokenizer.decode(output[0], skip_special_tokens=True))

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "float32",
+  "eos_token_id": 4,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 12,
+  "pad_token_id": 5,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 4,
+  "pad_token_id": 5,
+  "transformers_version": "4.57.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c2880cc28f92adafdb8c694b5c2324945fa1e879cb1c9ab73976559b4185814
+size 536435744

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|begin_of_text|>",
+  "eos_token": "<|eot_id|>",
+  "pad_token": "<|pad_id|>"
+}

tokenizer_config.json

@@ -0,0 +1,83 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "user",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "assistant",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "system",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db1de2c1756a32865c18d5f930b20304a0da41bb717379ca539d89aba61e56b0
+size 5777