|
{ |
|
"_name_or_path": "normalcomputing/extended-mind-llama-2-7b", |
|
"architectures": [ |
|
"ExtendedLlamaForCausalLM" |
|
], |
|
"auto_map": { |
|
"AutoConfig": "configuration.ExtendedLlamaConfig", |
|
"AutoModel": "modeling.ExtendedLlamaModel", |
|
"AutoModelFor<Task>": "modeling.ExtendedLlamaForCausalLM", |
|
}, |
|
"bos_token_id": 1, |
|
"eos_token_id": 2, |
|
"hidden_act": "silu", |
|
"hidden_size": 4096, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 11008, |
|
"mask_by_sim": false, |
|
"max_position_embeddings": 4096, |
|
"memory_device": "cpu", |
|
"memory_type": "manual", |
|
"model_type": "extended-llama", |
|
"num_attention_heads": 32, |
|
"num_hidden_layers": 32, |
|
"num_key_value_heads": 32, |
|
"pretraining_tp": 1, |
|
"remove_special_ids": true, |
|
"rms_norm_eps": 1e-05, |
|
"rope_scaling": null, |
|
"rope_theta": 10000.0, |
|
"sim_threshold": 0.25, |
|
"tie_word_embeddings": false, |
|
"tokenizer_all_special_ids": [ |
|
0, |
|
1, |
|
2 |
|
], |
|
"topk": 10, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.33.0", |
|
"use_cache": true, |
|
"use_external_mind": true, |
|
"use_external_mind_by_layer": [ |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true |
|
], |
|
"vocab_size": 32000 |
|
} |
|
|