Llama3_kw_gen_base / config.json
NiCEtmtm's picture
Update config.json
29ac941 verified
{
"model_type": "llama",
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": "unsloth/llama-3-8b-bnb-4bit",
"bias": "none",
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 16,
"lora_dropout": 0,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": [
"lm_head",
"embed_tokens"
],
"peft_type": "LORA",
"r": 16,
"rank_pattern": {},
"revision": "unsloth",
"target_modules": [
"k_proj",
"gate_proj",
"q_proj",
"up_proj",
"o_proj",
"down_proj",
"v_proj"
],
"task_type": "CAUSAL_LM",
"use_dora": false,
"use_rslora": false,
"hidden_size": 4096,
"num_attention_heads": 32,
"num_hidden_layers": 24,
"intermediate_size": 16384,
"max_position_embeddings": 512,
"vocab_size": 32000,
"layer_norm_eps": 1e-5,
"initializer_range": 0.02,
"train_batch_size": 2,
"gradient_accumulation_steps": 4,
"warmup_steps": 5,
"max_steps": 60,
"learning_rate": 0.0002,
"fp16": true,
"bf16": false,
"logging_steps": 1,
"optim": "adamw_8bit",
"weight_decay": 0.01,
"lr_scheduler_type": "linear",
"seed": 3407,
"output_dir": "outputs"
}