Text Generation
Transformers
PyTorch
Safetensors
English
stripedhyena
custom_code
StripedHyena-Nous-7B / config.json
Zymrael's picture
fix: key in config to match fa flag
d8a5c9f verified
{
"_commit_hash": "9ae63354fd42cc1e14334bba246276540c8b9017",
"_name_or_path": "togethercomputer/StripedHyena-Nous-7B",
"model_type": "stripedhyena",
"architectures": [
"StripedHyenaModelForCausalLM"
],
"attn_layer_idxs": [
1,
3,
5,
7,
9,
11,
13,
15,
17,
19,
21,
23,
25,
27,
29,
31
],
"auto_map": {
"AutoConfig": "togethercomputer/StripedHyena-Nous-7B--configuration_hyena.StripedHyenaConfig",
"AutoModelForCausalLM": "togethercomputer/StripedHyena-Nous-7B--modeling_hyena.StripedHyenaModelForCausalLM"
},
"column_split": false,
"column_split_hyena": true,
"eps": 1e-05,
"final_norm": true,
"hidden_size": 4096,
"hyena_filter_groups": 1,
"hyena_layer_idxs": [
0,
2,
4,
6,
8,
10,
12,
14,
16,
18,
20,
22,
24,
26,
28,
30,
32
],
"inference_mode": false,
"inner_mlp_size": 14336,
"log_intermediate_values": false,
"make_vocab_size_divisible_by": 8,
"max_seqlen": 32768,
"mha_out_proj_bias": false,
"model_parallel_size": 1,
"num_attention_heads": 32,
"num_filters": 4096,
"num_layers": 32,
"pipe_parallel_size": 1,
"prefill_style": "fft",
"proj_groups": 4,
"qkv_proj_bias": false,
"rotary_emb_base": 500000,
"short_filter_bias": true,
"short_filter_length": 3,
"smeared_gqa": false,
"split_k0": true,
"state_size": 2,
"tie_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": null,
"use_cache": true,
"use_flash_attn": true,
"use_flash_depthwise": false,
"use_flash_rmsnorm": true,
"use_flashfft": false,
"vocab_size": 32000
}