|
{ |
|
"architectures": [ |
|
"Grok1ForCausalLM" |
|
], |
|
"embedding_multiplier_scale": 90.50966799187809, |
|
"output_multiplier_scale": 0.5, |
|
"vocab_size": 131072, |
|
"hidden_size": 8192, |
|
"intermediate_size": 32768, |
|
"moe_intermediate_size": 16384, |
|
"max_position_embeddings": 131072, |
|
"num_experts_per_tok": 2, |
|
"num_local_experts": 8, |
|
"residual_moe": true, |
|
"num_attention_heads": 64, |
|
"num_key_value_heads": 8, |
|
"num_hidden_layers": 64, |
|
"head_dim": 128, |
|
"rms_norm_eps": 1e-05, |
|
"final_logit_softcapping": 50, |
|
"attn_logit_softcapping": 30.0, |
|
"router_logit_softcapping": 30.0, |
|
"rope_theta": 208533496, |
|
"attn_temperature_len": 1024, |
|
"sliding_window_size": -1, |
|
"global_attn_every_n": 1, |
|
"model_type": "mixtral", |
|
"torch_dtype": "bfloat16", |
|
"rope_type": "original", |
|
"original_max_position_embeddings": 8192, |
|
"scaling_factor": 16.0, |
|
"extrapolation_factor": 1.0, |
|
"attn_factor": 1.0, |
|
"beta_fast": 8, |
|
"beta_slow": 1 |
|
} |