llama_2_7b_aside / config.json
egorzverev's picture
Upload LlamaForCausalLMForwardRot
5ecbca6 verified
raw
history blame contribute delete
962 Bytes
{
"_name_or_path": "./models/llama_2_7b/forward_rot/train_checkpoints/SFTv110/from_base_run_6/last",
"add_linear_shift": false,
"architectures": [
"LlamaForCausalLMForwardRot"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"gradual_rotation": false,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"learned_rotation": false,
"max_position_embeddings": 4096,
"mlp_bias": false,
"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,
"rope_theta": 10000.0,
"rotation_alpha": 1.57079633,
"rotation_direction": "right",
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.47.1",
"use_cache": false,
"vocab_size": 32000
}