config.json

{
  "_name_or_path": "zaydzuhri/vanilla-340M-4096-model",
  "architectures": [
    "TransformerForCausalLM"
  ],
  "attention_bias": false,
  "attn_impl": "parallel_attn",
  "bos_token_id": 1,
  "elementwise_affine": true,
  "eos_token_id": 2,
  "fuse_cross_entropy": true,
  "fuse_norm": true,
  "fuse_swiglu": true,
  "hidden_act": "swish",
  "hidden_ratio": 4,
  "hidden_size": 1024,
  "initializer_range": 0.006,
  "intermediate_size": null,
  "max_position_embeddings": 8192,
  "model_type": "transformer",
  "norm_eps": 1e-06,
  "num_heads": 16,
  "num_hidden_layers": 24,
  "num_kv_heads": null,
  "qk_norm": false,
  "qkv_bias": false,
  "quantization_config": {
    "quant_config": {
      "offload_meta": false,
      "scale_quant_params": null,
      "weight_quant_params": {
        "axis": 1,
        "channel_wise": true,
        "group_size": 64,
        "nbits": 2,
        "optimize": true,
        "round_zero": false,
        "view_as_float": false
      },
      "zero_quant_params": null
    },
    "quant_method": "hqq",
    "skip_modules": [
      "lm_head"
    ]
  },
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.47.1",
  "use_cache": true,
  "vocab_size": 32000,
  "window_size": null
}