| { |
| "_commit_hash": "6d7baa4482172f2c451ca4b36c87d50c8359a134", |
| "_name_or_path": "togethercomputer/evo-1-8k-base", |
| "architectures": [ |
| "StripedHyenaModelForCausalLM" |
| ], |
| "attn_layer_idxs": [ |
| 8, |
| 16, |
| 24 |
| ], |
| "auto_map": { |
| "AutoConfig": "togethercomputer/evo-1-131k-base--configuration_hyena.StripedHyenaConfig", |
| "AutoModelForCausalLM": "togethercomputer/evo-1-131k-base--modeling_hyena.StripedHyenaModelForCausalLM", |
| "AutoTokenizer": "Hack90/virus_pythia_31_1024" |
| }, |
| "bos_token_id": 0, |
| "column_split": false, |
| "column_split_hyena": true, |
| "eos_token_id": 0, |
| "eps": 1e-06, |
| "final_norm": true, |
| "hidden_size": 128, |
| "hyena_filter_groups": 1, |
| "hyena_layer_idxs": [ |
| 0, |
| 1, |
| 2, |
| 3, |
| 4, |
| 5, |
| 6, |
| 7, |
| 9, |
| 10, |
| 11, |
| 12, |
| 13, |
| 14, |
| 15, |
| 17, |
| 18, |
| 19, |
| 20, |
| 21, |
| 22, |
| 23, |
| 25, |
| 26, |
| 27, |
| 28, |
| 29, |
| 30, |
| 31 |
| ], |
| "inference_mode": false, |
| "inner_mlp_size": 1024, |
| "log_intermediate_values": false, |
| "make_vocab_size_divisible_by": 8, |
| "max_seqlen": 1024, |
| "mha_out_proj_bias": true, |
| "mlp_activation": "gelu", |
| "model_parallel_size": 1, |
| "model_type": "stripedhyena", |
| "num_attention_heads": 32, |
| "num_filters": 128, |
| "num_layers": 32, |
| "pipe_parallel_size": 1, |
| "prefill_style": "fft", |
| "proj_groups": 1, |
| "qkv_proj_bias": true, |
| "rotary_emb_base": 10000, |
| "rotary_emb_scaling_factor": 1, |
| "short_filter_bias": true, |
| "short_filter_length": 3, |
| "smeared_gqa": false, |
| "split_k0": true, |
| "state_size": 8, |
| "tie_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": null, |
| "use_cache": true, |
| "use_flash_attention_2": true, |
| "use_flash_attn": true, |
| "use_flash_depthwise": false, |
| "use_flash_rmsnorm": false, |
| "use_flashfft": false, |
| "use_interpolated_rotary_pos_emb": false, |
| "vocab_size": 8 |
| } |
|
|