| { | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bias_removal": true, | |
| "bos_token_id": 128000, | |
| "censorship": false, | |
| "eos_token_id": [ | |
| 128001, | |
| 128008, | |
| 128009 | |
| ], | |
| "fused_tensor_size": 3212749824, | |
| "generation_tuning": { | |
| "max_length": 20, | |
| "max_new_tokens": 100, | |
| "min_length": 0, | |
| "min_new_tokens": null, | |
| "early_stopping": false, | |
| "max_time": null, | |
| "stop_strings": null, | |
| "do_sample": true, | |
| "num_beams": 1, | |
| "num_beam_groups": 1, | |
| "penalty_alpha": null, | |
| "dola_layers": null, | |
| "use_cache": true, | |
| "cache_implementation": null, | |
| "cache_config": null, | |
| "return_legacy_cache": null, | |
| "prefill_chunk_size": null, | |
| "temperature": 0.7, | |
| "top_k": 50, | |
| "top_p": 0.9, | |
| "min_p": null, | |
| "typical_p": 1.0, | |
| "epsilon_cutoff": 0.0, | |
| "eta_cutoff": 0.0, | |
| "diversity_penalty": 0.0, | |
| "repetition_penalty": 1.2, | |
| "encoder_repetition_penalty": 1.0, | |
| "length_penalty": 1.0, | |
| "no_repeat_ngram_size": 3, | |
| "bad_words_ids": null, | |
| "force_words_ids": null, | |
| "renormalize_logits": false, | |
| "constraints": null, | |
| "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, | |
| "forced_decoder_ids": null, | |
| "sequence_bias": null, | |
| "token_healing": false, | |
| "guidance_scale": null, | |
| "low_memory": null, | |
| "watermarking_config": null, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "output_logits": null, | |
| "return_dict_in_generate": false, | |
| "pad_token_id": null, | |
| "bos_token_id": null, | |
| "eos_token_id": null, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "decoder_start_token_id": null, | |
| "is_assistant": false, | |
| "num_assistant_tokens": 20, | |
| "num_assistant_tokens_schedule": "constant", | |
| "assistant_confidence_threshold": 0.4, | |
| "prompt_lookup_num_tokens": null, | |
| "max_matching_ngram_size": null, | |
| "assistant_early_exit": null, | |
| "assistant_lookbehind": 10, | |
| "target_lookbehind": 10, | |
| "disable_compile": false, | |
| "generation_kwargs": {}, | |
| "_from_model_config": false, | |
| "transformers_version": "4.51.3" | |
| }, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 3072, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 8000, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 24, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 128004, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 32.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| }, | |
| "rope_theta": 500000.0, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.51.3", | |
| "unsloth_version": "2025.2.15", | |
| "use_cache": true, | |
| "vocab_size": 128256, | |
| "fusion": { | |
| "layers_merged": 28 | |
| }, | |
| "tensor_fusion": true, | |
| "decode_functions": [ | |
| "decode_tokens", | |
| "decode_parameters", | |
| "decode_responses", | |
| "decode_layers", | |
| "decode_neurons", | |
| "decode_tensors", | |
| "decode_architecture", | |
| "decode_fused_tensor" | |
| ], | |
| "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n---\n<|start_header_id|>system<|end_header_id|>\nCutting Knowledge Date: December 2025\nToday Date: {{ date_string }}\n---\n{{ system_message }}\n<|eot_id|>\n<|start_header_id|>assistant<|end_header_id|>\n# Mecanismos incluidos:\n- Fusi\u00f3n de todas las capas en 1 (eliminando las originales)\n- Fusi\u00f3n de todos los tensores en uno\n- Eliminaci\u00f3n de bias y censura\n- Muestreo (`do_sample=True`), temp=0.7, top_p=0.9, penalidad=1.2\n- Logging detallado de cada paso\n- Funciones de decodificaci\u00f3n completas\n---\n<|eot_id|>" | |
| } |