Text Generation
Transformers
Safetensors
PyTorch
English
nemotron-nas
llama-3
llama
nvidia-nemotron
nemotron-ultra
fine-tuned
conversational-ai
large-language-model
huggingface
open-source-llm
generative-ai
nvidia
meta-llama
instruct-tuning
chat-model
llm
artificial-intelligence
deep-learning
tensorrt-llm
gpu-optimized
multilingual
instruction-following
conversational
custom_code
{ | |
"_name_or_path": "llama_nemotron_ultra", | |
"architectures": [ | |
"DeciLMForCausalLM" | |
], | |
"attention_bias": false, | |
"attention_dropout": 0.0, | |
"auto_map": { | |
"AutoConfig": "configuration_decilm.DeciLMConfig", | |
"AutoModelForCausalLM": "modeling_decilm.DeciLMForCausalLM" | |
}, | |
"block_configs": [ | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 0.4875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 0.975, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 1.4625, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 1.4625, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 1.4625, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 1.4625, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 1.4625, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 1.4625, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 1.95, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 1.95, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 1.95, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 1.95, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 2.4375, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 1.95, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 1.95, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 1.95, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 1.95, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 3.4125, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 3.4125, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 3.4125, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 2.925, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 2.4375, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 2.4375, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 2.4375, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 2.4375, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 2.4375, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 2.4375, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 2.4375, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 2.4375, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 2.4375, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 2.4375, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 2.4375, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 2.4375, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 2.4375, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 2.4375, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 2.925, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 36.5625, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 39.0, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 31.40625, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 27.5625, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 1.95, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 1.95, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 2.4375, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": null, | |
"no_op": true, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": null, | |
"no_op": true, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 2.4375, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 2.4375, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 3.4125, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 4.875, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
}, | |
{ | |
"attention": { | |
"n_heads_in_group": 16, | |
"no_op": false, | |
"num_sink_tokens": null, | |
"replace_with_linear": false, | |
"sparsify": null, | |
"unshifted_sink": false, | |
"use_prefill_window_in_sink_attention": false, | |
"window_length": null | |
}, | |
"ffn": { | |
"ffn_mult": 2.4375, | |
"no_op": false, | |
"replace_with_linear": false, | |
"sparsify": null | |
} | |
} | |
], | |
"bos_token_id": 128000, | |
"eos_token_id": [ | |
128001, | |
128008, | |
128009 | |
], | |
"hidden_act": "silu", | |
"hidden_size": 16384, | |
"initializer_range": 0.02, | |
"intermediate_size": null, | |
"max_position_embeddings": 131072, | |
"mlp_bias": false, | |
"model_type": "nemotron-nas", | |
"num_attention_heads": 128, | |
"num_hidden_layers": 162, | |
"num_key_value_heads": null, | |
"pretraining_tp": 1, | |
"rms_norm_eps": 1e-05, | |
"rope_scaling": { | |
"factor": 16.0, | |
"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": false, | |
"torch_dtype": "bfloat16", | |
"transformers_version": "4.45.1", | |
"use_cache": true, | |
"vocab_size": 128256 | |
} | |