|
{ |
|
"_name_or_path": "abacusai/Smaug-Llama-3-70B-Instruct", |
|
"architectures": [ |
|
"LlamaForCausalLM" |
|
], |
|
"attention_bias": false, |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 128000, |
|
"eos_token_id": 128001, |
|
"hidden_act": "silu", |
|
"hidden_size": 8192, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 28672, |
|
"max_position_embeddings": 8192, |
|
"model_type": "llama", |
|
"num_attention_heads": 64, |
|
"num_hidden_layers": 80, |
|
"num_key_value_heads": 8, |
|
"pretraining_tp": 1, |
|
"quantization_config": { |
|
"bits": 8, |
|
"checkpoint_format": "gptq", |
|
"damp_percent": 0.01, |
|
"desc_act": true, |
|
"group_size": 128, |
|
"model_file_base_name": null, |
|
"model_name_or_path": null, |
|
"quant_method": "gptq", |
|
"static_groups": false, |
|
"sym": true, |
|
"true_sequential": true |
|
}, |
|
"rms_norm_eps": 1e-05, |
|
"rope_scaling": null, |
|
"rope_theta": 500000.0, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.40.1", |
|
"use_cache": true, |
|
"use_flash_attention_2": true, |
|
"vocab_size": 128256 |
|
} |
|
|