alpha-brain's picture
Upload OpenELMForCausalLM
d1dd0f3 verified
{
"_name_or_path": "apple/OpenELM-450M-Instruct",
"activation_fn_name": "swish",
"architectures": [
"OpenELMForCausalLM"
],
"auto_map": {
"AutoConfig": "apple/OpenELM-450M-Instruct--configuration_openelm.OpenELMConfig",
"AutoModelForCausalLM": "apple/OpenELM-450M-Instruct--modeling_openelm.OpenELMForCausalLM"
},
"bos_token_id": 1,
"eos_token_id": 2,
"ffn_dim_divisor": 256,
"ffn_multipliers": [
0.5,
0.68,
0.87,
1.05,
1.24,
1.42,
1.61,
1.79,
1.97,
2.16,
2.34,
2.53,
2.71,
2.89,
3.08,
3.26,
3.45,
3.63,
3.82,
4.0
],
"ffn_with_glu": true,
"head_dim": 64,
"initializer_range": 0.02,
"max_context_length": 2048,
"model_dim": 1536,
"model_type": "openelm",
"normalization_layer_name": "rms_norm",
"normalize_qk_projections": true,
"num_gqa_groups": 4,
"num_kv_heads": [
3,
3,
3,
4,
4,
4,
4,
4,
4,
4,
5,
5,
5,
5,
5,
5,
6,
6,
6,
6
],
"num_query_heads": [
12,
12,
12,
16,
16,
16,
16,
16,
16,
16,
20,
20,
20,
20,
20,
20,
24,
24,
24,
24
],
"num_transformer_layers": 20,
"qkv_multipliers": [
0.5,
1.0
],
"rope_freq_constant": 10000,
"rope_max_length": 4096,
"share_input_output_layers": true,
"torch_dtype": "float32",
"transformers_version": "4.39.3",
"use_cache": false,
"vocab_size": 32000
}