pico-60 / config.json
Banaxi-Tech's picture
Upload pico-60 checkpoint
230327a verified
Raw
History Blame Contribute Delete
1.21 kB
{
"vocab_size": 384,
"hidden_size": 96,
"num_hidden_layers": 6,
"num_attention_heads": 6,
"num_key_value_heads": 2,
"head_dim": 16,
"intermediate_size": 380,
"refresh_layers": [
3,
5
],
"refresh_kernel_size": 9,
"refresh_alpha_init": 0.0,
"max_position_embeddings": 4096,
"rope_theta": 100000.0,
"rms_norm_eps": 1e-06,
"initializer_range": 0.02,
"use_cache": true,
"transformers_version": "5.15.0",
"architectures": [
"BananaMind2PicoForCausalLM"
],
"output_hidden_states": false,
"return_dict": true,
"dtype": null,
"chunk_size_feed_forward": 0,
"is_encoder_decoder": false,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"problem_type": null,
"_name_or_path": "Banaxi-Tech/pico-test",
"tie_word_embeddings": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"unk_token_id": 3,
"model_type": "bananamind2_pico",
"output_attentions": false,
"auto_map": {
"AutoConfig": "configuration_bananamind2pico.BananaMind2PicoConfig",
"AutoModelForCausalLM": "modeling_bananamind2pico.BananaMind2PicoForCausalLM"
},
"torch_dtype": "float32"
}