Text Generation
Transformers
Safetensors
English
mixtral
conversational
Inference Endpoints
text-generation-inference
Minueza-32Mx2-Chat / config.json
Felladrin's picture
Initial commit
79ede1f
{
"architectures": ["MixtralForCausalLM"],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 32000,
"hidden_act": "silu",
"hidden_size": 312,
"initializer_range": 0.02,
"intermediate_size": 1092,
"max_position_embeddings": 2048,
"model_type": "mixtral",
"num_attention_heads": 12,
"num_experts_per_tok": 2,
"num_hidden_layers": 10,
"num_key_value_heads": 4,
"num_local_experts": 2,
"output_router_logits": false,
"rms_norm_eps": 1e-6,
"rope_theta": 10000.0,
"router_aux_loss_coef": 0.001,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.38.2",
"use_cache": true,
"vocab_size": 32002
}