config.json

{
  "vocab_size": 151936,
  "max_position_embeddings": 131072,
  "hidden_size": 1536,
  "intermediate_size": 8960,
  "num_hidden_layers": 28,
  "num_attention_heads": 12,
  "use_sliding_window": false,
  "sliding_window": 32768,
  "max_window_layers": 28,
  "num_key_value_heads": 2,
  "hidden_act": "silu",
  "initializer_range": 0.02,
  "rms_norm_eps": 1e-06,
  "use_cache": true,
  "rope_theta": 1000000.0,
  "rope_scaling": null,
  "attention_dropout": 0.0,
  "return_dict": true,
  "output_hidden_states": false,
  "output_attentions": false,
  "torchscript": false,
  "torch_dtype": "bfloat16",
  "use_bfloat16": false,
  "tf_legacy_loss": false,
  "pruned_heads": {},
  "tie_word_embeddings": true,
  "chunk_size_feed_forward": 0,
  "is_encoder_decoder": false,
  "is_decoder": false,
  "cross_attention_hidden_size": null,
  "add_cross_attention": false,
  "tie_encoder_decoder": false,
  "max_length": 20,
  "min_length": 0,
  "do_sample": false,
  "early_stopping": false,
  "num_beams": 1,
  "num_beam_groups": 1,
  "diversity_penalty": 0.0,
  "temperature": 1.0,
  "top_k": 50,
  "top_p": 1.0,
  "typical_p": 1.0,
  "repetition_penalty": 1.0,
  "length_penalty": 1.0,
  "no_repeat_ngram_size": 0,
  "encoder_no_repeat_ngram_size": 0,
  "bad_words_ids": null,
  "num_return_sequences": 1,
  "output_scores": false,
  "return_dict_in_generate": false,
  "forced_bos_token_id": null,
  "forced_eos_token_id": null,
  "remove_invalid_values": false,
  "exponential_decay_length_penalty": null,
  "suppress_tokens": null,
  "begin_suppress_tokens": null,
  "architectures": [
    "IsomQwen25CoderForCausalLM"
  ],
  "finetuning_task": null,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1"
  },
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1
  },
  "tokenizer_class": null,
  "prefix": null,
  "bos_token_id": 151643,
  "pad_token_id": null,
  "eos_token_id": 151645,
  "sep_token_id": null,
  "decoder_start_token_id": null,
  "task_specific_params": null,
  "problem_type": null,
  "_name_or_path": "Qwen/Qwen2.5-Coder-1.5B-Instruct",
  "_attn_implementation_autoset": false,
  "transformers_version": "4.49.0",
  "model_type": "isom_qwen25_coder",
  "auto_map": {
    "AutoConfig": "modeling_isom_qwen25_coder.IsomQwen25CoderConfig",
    "AutoModelForCausalLM": "modeling_isom_qwen25_coder.IsomQwen25CoderForCausalLM"
  },
  "use_isom_cache": true,
  "isom_budget": 8192,
  "quantize_int8": true,
  "enable_radix": true,
  "enable_holographic_revival": true,
  "use_isom_r2_svd": true,
  "isom_r2_window_length": 2048,
  "isom_r2_sink_tokens": 64,
  "isom_r2_num_retrieved_chunks": 4,
  "isom_r2_micro_window_size": 512,
  "isom_r2_chunk_size": 2048,
  "isom_r2_max_context": 1048576,
  "prefill_chunk_size": 2048,
  "saliency_threshold": 0.45,
  "vault_saliency_threshold": 0.8,
  "vault_max_slots": 36000,
  "vault_evict_batch": 1000,
  "vault_topk_retrieval": 64,
  "omega_min": 5.992112e-06,
  "polar_reprojection_interval": 5000,
  "tier2_vault_enabled": true,
  "tier2_vault_device": "cpu",
  "tier2_vault_dtype": "float16",
  "three_path_attention": true,
  "vault_gate_bias_init": -5.0,
  "use_yarn": false
}