seslami-pplx's picture
Update readme and config (#2)
9fa192e
{
"architectures": [
"PPLXQwen3Model"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration.PPLXQwen3Config",
"AutoModel": "modeling.PPLXQwen3ContextualModel"
},
"bos_token_id": 151643,
"dtype": "float32",
"eos_token_id": 151643,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 9728,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 32768,
"max_window_layers": 36,
"model_type": "bidirectional_pplx_qwen3",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000,
"rope_type": "default"
},
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "5.0.0.dev0",
"use_cache": false,
"use_sliding_window": false,
"attn_implementation": "sdpa",
"vocab_size": 151936,
"use_bidirectional_attention": true
}