goofspiel / config.json
curli12's picture
Upload folder using huggingface_hub
2162a2b verified
{
"vocab_size": 151936,
"max_position_embeddings": 40960,
"hidden_size": 5120,
"intermediate_size": 25600,
"num_hidden_layers": 64,
"num_attention_heads": 64,
"use_sliding_window": false,
"sliding_window": null,
"max_window_layers": 64,
"num_key_value_heads": 8,
"head_dim": 128,
"hidden_act": "silu",
"initializer_range": 0.02,
"rms_norm_eps": 1e-06,
"use_cache": true,
"attention_bias": false,
"attention_dropout": 0.0,
"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",
"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"
],
"pad_token_id": 151643,
"bos_token_id": 151643,
"eos_token_id": 151645,
"tie_word_embeddings": false,
"rope_parameters": {
"rope_theta": 1000000,
"rope_type": "default"
},
"return_dict": true,
"output_hidden_states": false,
"dtype": "bfloat16",
"chunk_size_feed_forward": 0,
"is_encoder_decoder": false,
"architectures": [
"Qwen3ForCausalLM"
],
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"problem_type": null,
"_name_or_path": "base_model_1",
"transformers_version": "5.3.0",
"model_type": "qwen3",
"output_attentions": false,
"torch_dtype": "bfloat16"
}