File size: 1,166 Bytes
a79fd77 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 |
{
"_name_or_path": "./LLaMA-Efficient-Tuning/basic_prompt_french",
"alpha_pattern": {},
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"auto_mapping": null,
"base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
"bias": "none",
"bos_token_id": 1,
"eos_token_id": 2,
"fan_in_fan_out": false,
"hidden_act": "silu",
"hidden_size": 4096,
"inference_mode": true,
"init_lora_weights": true,
"initializer_range": 0.02,
"intermediate_size": 11008,
"layers_pattern": null,
"layers_to_transform": null,
"lora_alpha": 16.0,
"lora_dropout": 0.1,
"max_position_embeddings": 2048,
"model_type": "llama",
"modules_to_save": null,
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"peft_type": "LORA",
"pretraining_tp": 1,
"r": 8,
"rank_pattern": {},
"revision": null,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"target_modules": [
"v_proj",
"q_proj"
],
"task_type": "CAUSAL_LM",
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.35.2",
"use_cache": true,
"vocab_size": 32000
}
|