neutts-2e / config.json
eeleeleel's picture
Duplicate from neuphonic/qwen3-0.2b-en-emotional-grpo-500-16-06-26
47eb7d6
Raw
History Blame Contribute Delete
1.67 kB
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": null,
"dtype": "bfloat16",
"eos_token_id": 151674,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 512,
"initializer_range": 0.02,
"intermediate_size": 1536,
"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"
],
"max_position_embeddings": 32768,
"max_window_layers": 28,
"model_type": "qwen3",
"neuphonic": {
"input_format": "BPE",
"supported_langs": [
"en-us"
],
"use_cfg": false,
"use_lang_token": false,
"supported_emotions": [
"angry", "disgusted", "sad", "happy", "fearful", "neutral", "surprised"
]
},
"num_attention_heads": 12,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"pad_token_id": 151645,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 10000.0,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "5.1.0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 217232
}