|
{ |
|
"_name_or_path": "/Users/dawn/git/models/Starling-LM-7B-beta", |
|
"architectures": [ |
|
"MixtralForCausalLM" |
|
], |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 1, |
|
"eos_token_id": 32000, |
|
"hidden_act": "silu", |
|
"hidden_size": 4096, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 14336, |
|
"max_position_embeddings": 8192, |
|
"model_type": "mixtral", |
|
"num_attention_heads": 32, |
|
"num_experts_per_tok": 2, |
|
"num_hidden_layers": 32, |
|
"num_key_value_heads": 8, |
|
"num_local_experts": 2, |
|
"output_router_logits": false, |
|
"pad_token_id": 32000, |
|
"rms_norm_eps": 1e-05, |
|
"rope_theta": 10000.0, |
|
"router_aux_loss_coef": 0.001, |
|
"sliding_window": null, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.39.3", |
|
"use_cache": true, |
|
"vocab_size": 32002 |
|
} |
|
|