config.json

{
  "model_type": "gpt2",
  "architectures": [
    "GPT2LMHeadModel"
  ],
  "vocab_size": 16000,
  "d_model": 576,
  "num_layers": 13,
  "num_heads": 16,
  "d_ff": 1280,
  "max_seq_len": 1024,
  "dropout": 0.1,
  "pad_token_id": 0,
  "eos_token_id": 1,
  "unk_token_id": 2,
  "torch_dtype": "float32",
  "transformers_version": "4.36.0",
  "task": "text-generation",
  "pipeline_tag": "text-generation",
  "library_name": "transformers",
  "license": "apache-2.0",
  "language": ["en", "code"],
  "tags": [
    "transformers",
    "pytorch",
    "safetensors",
    "text-generation",
    "code-generation",
    "python",
    "javascript",
    "coding",
    "programming",
    "sagemaker",
    "amazon-sagemaker",
    "cpu",
    "compact",
    "efficient",
    "nvdya-kit",
    "death-legion",
    "vllm",
    "sglang",
    "llama-cpp",
    "ollama",
    "lm-studio",
    "year-2026",
    "next-gen"
  ],
  "datasets": ["the-stack-v2"],
  "metrics": ["perplexity", "accuracy"],
  "inference": {
    "parameters": {
      "temperature": 0.8,
      "top_p": 0.95,
      "top_k": 50,
      "max_new_tokens": 200
    }
  },
  "sagemaker": {
    "sdk_version": "2.200.0",
    "instance_type": "ml.m5.large",
    "instance_count": 1,
    "container_image": "huggingface-pytorch-inference:2.0.0-transformers4.28.1-cpu-py310-ubuntu20.04-v1.0"
  }
}