|
{ |
|
"_name_or_path": "final_checkpoint", |
|
"architectures": [ |
|
"MistralForCausalLM" |
|
], |
|
"attention_bias": false, |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 1, |
|
"eos_token_id": 32000, |
|
"hidden_act": "silu", |
|
"hidden_size": 2048, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 5632, |
|
"max_position_embeddings": 4096, |
|
"model_type": "llama", |
|
"num_attention_heads": 32, |
|
"num_hidden_layers": 22, |
|
"num_key_value_heads": 4, |
|
"pretraining_tp": 1, |
|
"rms_norm_eps": 1e-05, |
|
"rope_scaling": null, |
|
"rope_theta": 10000.0, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.35.2", |
|
"use_cache": false, |
|
"vocab_size": 32002 |
|
} |
|
|