|
{ |
|
"_name_or_path": "NousResearch/Nous-Hermes-2-Mistral-7B-DPO", |
|
"architectures": [ |
|
"MistralForCausalLM" |
|
], |
|
"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": 32768, |
|
"model_type": "mistral", |
|
"neuron": { |
|
"auto_cast_type": "fp16", |
|
"batch_size": 1, |
|
"checkpoint_id": "NousResearch/Nous-Hermes-2-Mistral-7B-DPO", |
|
"checkpoint_revision": "ebec0a691037d38955727d6949798429a63929dd", |
|
"compiler_type": "neuronx-cc", |
|
"compiler_version": "2.14.227.0+2d4f85be", |
|
"num_cores": 8, |
|
"sequence_length": 2048, |
|
"task": "text-generation" |
|
}, |
|
"num_attention_heads": 32, |
|
"num_hidden_layers": 32, |
|
"num_key_value_heads": 8, |
|
"rms_norm_eps": 1e-05, |
|
"rope_theta": 10000.0, |
|
"sliding_window": 4096, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.41.1", |
|
"use_cache": false, |
|
"vocab_size": 32002 |
|
} |
|
|