config.json

{
  "_name_or_path": "fla-hub/gla-1.3B-100B",
  "architectures": [
    "GLAForCausalLM"
  ],
  "attn_mode": "fused_chunk",
  "bos_token_id": 1,
  "clamp_min": null,
  "conv_size": 4,
  "eos_token_id": 2,
  "expand_k": 0.5,
  "expand_v": 1,
  "fuse_cross_entropy": true,
  "fuse_norm": true,
  "hidden_act": "swish",
  "hidden_ratio": 4,
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": null,
  "max_position_embeddings": 2048,
  "model_type": "gla",
  "num_heads": 4,
  "num_hidden_layers": 24,
  "rms_norm_eps": 1e-06,
  "share_conv_kernel": true,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.39.1",
  "use_cache": true,
  "use_gk": true,
  "use_gv": false,
  "use_short_conv": false,
  "vocab_size": 32000
}