OpenELM-1_1B-SFT / config.json
CharlesLi's picture
End of training
c775190 verified
{
"_name_or_path": "apple/OpenELM-1_1B",
"activation_fn_name": "swish",
"architectures": [
"OpenELMForCausalLM"
],
"auto_map": {
"AutoConfig": "apple/OpenELM-1_1B--configuration_openelm.OpenELMConfig",
"AutoModelForCausalLM": "apple/OpenELM-1_1B--modeling_openelm.OpenELMForCausalLM"
},
"bos_token_id": 1,
"eos_token_id": 2,
"ffn_dim_divisor": 256,
"ffn_multipliers": [
0.5,
0.63,
0.76,
0.89,
1.02,
1.15,
1.28,
1.41,
1.54,
1.67,
1.8,
1.93,
2.06,
2.19,
2.31,
2.44,
2.57,
2.7,
2.83,
2.96,
3.09,
3.22,
3.35,
3.48,
3.61,
3.74,
3.87,
4.0
],
"ffn_with_glu": true,
"head_dim": 64,
"initializer_range": 0.02,
"max_context_length": 2048,
"model_dim": 2048,
"model_type": "openelm",
"normalization_layer_name": "rms_norm",
"normalize_qk_projections": true,
"num_gqa_groups": 4,
"num_kv_heads": [
4,
4,
4,
5,
5,
5,
5,
5,
5,
5,
6,
6,
6,
6,
6,
6,
6,
6,
7,
7,
7,
7,
7,
7,
8,
8,
8,
8
],
"num_query_heads": [
16,
16,
16,
20,
20,
20,
20,
20,
20,
20,
24,
24,
24,
24,
24,
24,
24,
24,
28,
28,
28,
28,
28,
28,
32,
32,
32,
32
],
"num_transformer_layers": 28,
"qkv_multipliers": [
0.5,
1.0
],
"rope_freq_constant": 10000,
"rope_max_length": 4096,
"share_input_output_layers": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.44.2",
"use_cache": true,
"vocab_size": 32000
}