Upload 9 files

.gitattributes

@@ -1,35 +1,2 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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
+model.bin filter=lfs diff=lfs merge=lfs -text
+tokenizer.model filter=lfs diff=lfs merge=lfs -text

README.md

@@ -126,4 +126,4 @@ MIT License - See the [LICENSE](LICENSE) file for details.
 
 - Model architecture and training code adapted from [llama2.c](https://github.com/karpathy/llama2.c) by Andrej Karpathy
 - Trained on the [TinyStories dataset](https://huggingface.co/datasets/roneneldan/TinyStories) by Ronen Eldan and Yuanzhi Li
-- Based on the Llama 2 architecture by Meta AI
+- Based on the Llama 2 architecture by Meta AI

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 48,
+  "hidden_act": "silu",
+  "hidden_size": 288,
+  "initializer_range": 0.02,
+  "intermediate_size": 768,
+  "max_position_embeddings": 256,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 6,
+  "num_key_value_heads": 6,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": null,
+  "do_sample": true,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 0.9,
+  "max_length": 256,
+  "transformers_version": "4.46.3"
+}

inference_example.py

@@ -0,0 +1,52 @@
+"""
+Example script for running inference with the Hugging Face model.
+"""
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+import warnings
+
+# Suppress the TypedStorage deprecation warning
+warnings.filterwarnings('ignore', category=UserWarning, message='.*TypedStorage is deprecated.*')
+
+def main():
+    model_path = "."  # Path to the model, or use "YOUR_USERNAME/YOUR_MODEL_NAME" for HF Hub
+
+    print("Loading model and tokenizer...")
+    model = AutoModelForCausalLM.from_pretrained(model_path)
+    tokenizer = AutoTokenizer.from_pretrained(model_path)
+
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+    model = model.to(device)
+    model.eval()
+
+    print(f"Model loaded on {device}")
+    print(f"Model parameters: {sum(p.numel() for p in model.parameters()):,}")
+
+    prompts = [
+        "Once upon a time",
+        "The quick brown fox",
+    ]
+
+    for prompt in prompts:
+        print(f"\n{'='*60}")
+        print(f"Prompt: {prompt}")
+        print(f"{'='*60}")
+
+        inputs = tokenizer(prompt, return_tensors="pt").to(device)
+
+        with torch.no_grad():
+            outputs = model.generate(
+                **inputs,
+                max_length=100,
+                temperature=1.0,
+                top_k=50,
+                top_p=0.9,
+                do_sample=True,
+                pad_token_id=tokenizer.eos_token_id
+            )
+
+        generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        print(f"\nGenerated:\n{generated_text}")
+
+if __name__ == "__main__":
+    main()

model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cbe0e5ebe492cc9cb3de5808b3630ff39e3cb8896924dd9ca6cebf9f1e7482a
+size 60784601

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 256,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}