{
  "activation_checkpointing": true,
  "architecture": "fabric",
  "architectures": [
    "FabricForCausalLM"
  ],
  "attention_backend": "auto",
  "attention_chunk_size": 1024,
  "auto_map": {
    "AutoConfig": "configuration_fabric.FabricConfig",
    "AutoModelForCausalLM": "modeling_fabric.FabricForCausalLM"
  },
  "bos_token_id": 2,
  "checkpoint_dtype": "float16",
  "checkpoint_note": "Model-only Fabric complete checkpoint; optimizer state is excluded.",
  "checkpoint_sha256": "a8d12a687fe5eaa05b601ab2803ca2c14b9cc2c14d754110ca4569b061af2bf1",
  "checkpoint_size_gib": 1.383114,
  "chunked_cross_entropy": true,
  "continued_pretraining_tokens": 5000134656,
  "cumulative_pretraining_tokens": 23000514560,
  "eos_token_id": 7,
  "export_kind": "model_only_inference_fp16",
  "head_dim": 64,
  "hidden_size": 1536,
  "intermediate_size": 4096,
  "license": "fabric-ai-open-1.0",
  "local_attention_window": 2048,
  "loss_chunk_size": 1024,
  "max_position_embeddings": 32768,
  "memory_chunk_size": 512,
  "model_name": "Fabric1.5-0.7B-Instruct",
  "model_type": "fabric",
  "num_attention_heads": 24,
  "num_hidden_layers": 24,
  "num_key_value_heads": 6,
  "num_kv_heads": 6,
  "num_layers": 24,
  "num_parameters": 742528520,
  "num_query_heads": 24,
  "original_pretraining_tokens": 18000379904,
  "pad_token_id": 0,
  "posttraining_supervised_tokens": 318879711,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "sequence_length": 32768,
  "summaries_per_chunk": 4,
  "tie_word_embeddings": true,
  "torch_dtype": "float16",
  "transformers_version": "custom",
  "use_cache": false,
  "vocab_size": 65536
}