|
{ |
|
"_name_or_path": "TheBloke/Llama-2-7B-fp16", |
|
"architectures": ["LlamaForCausalLM"], |
|
"bos_token_id": 1, |
|
"eos_token_id": 2, |
|
"hidden_act": "silu", |
|
"hidden_size": 4096, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 11008, |
|
"max_position_embeddings": 2048, |
|
"model_type": "llama", |
|
"num_attention_heads": 32, |
|
"num_hidden_layers": 32, |
|
"num_key_value_heads": 32, |
|
"pad_token_id": 0, |
|
"pretraining_tp": 1, |
|
"rms_norm_eps": 1e-05, |
|
"rope_scaling": null, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.31.0", |
|
"use_cache": true, |
|
"vocab_size": 32000, |
|
"auto_mapping": null, |
|
"base_model_name_or_path": "TinyPixel/Llama-2-7B-bf16-sharded", |
|
"bias": "none", |
|
"fan_in_fan_out": false, |
|
"inference_mode": true, |
|
"init_lora_weights": true, |
|
"layers_pattern": null, |
|
"layers_to_transform": null, |
|
"lora_alpha": 16, |
|
"lora_dropout": 0.1, |
|
"modules_to_save": null, |
|
"peft_type": "LORA", |
|
"r": 64, |
|
"revision": null, |
|
"target_modules": [ |
|
"q_proj", |
|
"v_proj" |
|
], |
|
"task_type": "CAUSAL_LM" |
|
} |