Upload folder using huggingface_hub

README.md

@@ -0,0 +1,32 @@
+
+# smollm-turkish-base
+
+Turkish base model with early stopped training
+
+## Model Description
+
+- **Model Type:** LLaMA Architecture
+- **Training Framework:** Nanotron
+- **Base Tokenizer:** bonur/gpt2-turkish-tokenizer
+- **Context Length:** 4096
+- **Vocab Size:** 52000
+- **Hidden Size:** 576
+- **Number of Layers:** 30
+- **Number of Attention Heads:** 9
+- **Number of Key/Value Heads:** 3
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("bonur/smollm-turkish-base")
+tokenizer = AutoTokenizer.from_pretrained("bonur/smollm-turkish-base")
+
+# Example usage
+text = "Your prompt here"
+inputs = tokenizer(text, return_tensors="pt")
+outputs = model.generate(inputs.input_ids, max_new_tokens=100)
+result = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(result)
+```

config.json

@@ -0,0 +1,23 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-05,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.0",
+  "use_cache": true,
+  "vocab_size": 52000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "pad_token_id": null,
+  "transformers_version": "4.33.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e604212afb10efdd6104d9bd780bfe46ad59ee8e4f7853fa755da5935f1bac20
+size 544685154

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}