|
{ |
|
"_name_or_path": "erfanzar/llama-2-jax", |
|
"architectures": [ |
|
"LlamaForCausalLM" |
|
], |
|
"auto_map": { |
|
"AutoConfig": "model.LlamaConfig", |
|
"FlaxAutoModel": "model.FlaxLlamaModel", |
|
"FlaxAutoModelForCausalLM": "model.FlaxLlamaForCausalLM" |
|
}, |
|
"bos_token_id": 1, |
|
"eos_token_id": 2, |
|
"gradient_checkpointing": "nothing_saveable", |
|
"hidden_act": "silu", |
|
"hidden_size": 4096, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 11008, |
|
"max_sequence_length": 32768, |
|
"model_type": "llama", |
|
"num_attention_heads": 32, |
|
"num_hidden_layers": 32, |
|
"pad_token_id": 0, |
|
"rms_norm_eps": 1e-05, |
|
"tie_word_embeddings": false, |
|
"transformers_version": "4.31.0", |
|
"use_cache": false, |
|
"vocab_size": 32000, |
|
"rope_scaling": { |
|
"factor": 8.0, |
|
"type": "linear" |
|
} |
|
} |