{ | |
"_name_or_path": "decapoda-research/llama-65b-hf", | |
"architectures": [ | |
"LlamaForCausalLM" | |
], | |
"bos_token_id": 0, | |
"custom_pipelines": { | |
"text-generation": { | |
"impl": "h2oai_pipeline.H2OTextGenerationPipeline", | |
"pt": "AutoModelForCausalLM" | |
} | |
}, | |
"eos_token_id": 1, | |
"hidden_act": "silu", | |
"hidden_size": 8192, | |
"initializer_range": 0.02, | |
"intermediate_size": 22016, | |
"max_position_embeddings": 2048, | |
"max_sequence_length": 2048, | |
"model_type": "llama", | |
"num_attention_heads": 64, | |
"num_hidden_layers": 80, | |
"pad_token_id": -1, | |
"rms_norm_eps": 1e-05, | |
"tie_word_embeddings": false, | |
"torch_dtype": "float16", | |
"transformers_version": "4.30.1", | |
"use_cache": true, | |
"vocab_size": 32000, | |
"quantization_config": { | |
"bits": 4, | |
"group_size": -1, | |
"damp_percent": 0.01, | |
"desc_act": true, | |
"sym": true, | |
"true_sequential": true, | |
"model_file_base_name": "model", | |
"quant_method": "gptq" | |
} | |
} |