Text Generation
Transformers
Safetensors
English
mistral
conversational
Eval Results
Inference Endpoints
text-generation-inference
Minueza-32M-Chat / config.json
Felladrin's picture
Initial commit
32a710d
raw history blame
No virus
590 Bytes
{
"architectures": ["MistralForCausalLM"],
"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": "mistral",
"num_attention_heads": 12,
"num_hidden_layers": 10,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-6,
"rope_theta": 10000.0,
"sliding_window": 1024,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.38.0.dev0",
"use_cache": true,
"vocab_size": 32002
}