{ "architectures": [ "Eagle3DeepseekV2ForCausalLM" ], "model_type": "kimi_k2", "hidden_size": 7168, "intermediate_size": 18432, "num_hidden_layers": 1, "num_attention_heads": 64, "num_key_value_heads": 64, "q_lora_rank": 1536, "kv_lora_rank": 512, "qk_nope_head_dim": 128, "qk_rope_head_dim": 64, "v_head_dim": 128, "hidden_act": "silu", "rms_norm_eps": 1e-05, "vocab_size": 163840, "draft_vocab_size": 163840, "torch_dtype": "bfloat16", "rope_theta": 50000.0, "rope_scaling": { "beta_fast": 1.0, "beta_slow": 1.0, "factor": 64.0, "mscale": 1.0, "mscale_all_dim": 1.0, "original_max_position_embeddings": 4096, "type": "yarn" }, "eagle_config": { "eagle_aux_hidden_state_layer_ids": [ 2, 30, 58 ], "use_aux_hidden_state": true, "use_input_layernorm_in_first_layer": true, "use_last_layernorm": true, "use_mtp_layernorm": false }, "bos_token_id": 163584, "eos_token_id": 163585, "pad_token_id": 0, "_torchspec_version": "0.1.0", "max_position_embeddings": 262144, "quantization_config": { "quant_method": "compressed-tensors", "format": "float-quantized", "quantization_status": "compressed", "global_compression_ratio": null, "kv_cache_scheme": null, "ignore": [ "lm_head", "re:.*kv_b_proj.*" ], "config_groups": { "group_0": { "targets": [ "Linear" ], "weights": { "num_bits": 8, "type": "float", "strategy": "channel", "symmetric": true, "dynamic": false, "group_size": null, "block_structure": null, "actorder": null, "observer": "minmax", "observer_kwargs": {} }, "input_activations": { "num_bits": 8, "type": "float", "strategy": "token", "symmetric": true, "dynamic": true, "group_size": null, "block_structure": null, "actorder": null, "observer": null, "observer_kwargs": {} }, "output_activations": null } } } }