STReasoner-8B / config.json
Time-HD-Anonymous's picture
Upload folder using huggingface_hub
05b4aba verified
{
"architectures": [
"Qwen3TSForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_qwen3_ts.Qwen3TSConfig",
"AutoModel": "modeling_qwen3_ts.Qwen3TSForCausalLM",
"AutoModelForCausalLM": "modeling_qwen3_ts.Qwen3TSForCausalLM",
"AutoProcessor": "processing_qwen3_ts.Qwen3TSProcessor"
},
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"ignore_index": -100,
"initializer_range": 0.02,
"intermediate_size": 12288,
"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": 40960,
"max_window_layers": 36,
"model_type": "qwen3ts",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "4.57.0",
"ts": {
"embedding_dim": 16,
"hidden_size": 4096,
"max_length": 32768,
"max_sequence_length": 32768,
"num_features": 2,
"num_layers": 5,
"patch_size": 8,
"use_layer_norm": false,
"use_position_embedding": true,
"use_position_idx": false
},
"ts_token_end_index": 151670,
"ts_token_start_index": 151669,
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}