w32zhong's picture
Upload folder using huggingface_hub
1727c4f verified
{
"_base_model_config": "{\n \"architectures\": [\n \"Qwen3ForCausalLM\"\n ],\n \"attention_bias\": false,\n \"attention_dropout\": 0.0,\n \"auto_map\": {\n \"AutoModelForCausalLM\": \"modeling_speculative_qwen3.SpeculativeQwen3ForCausalLM\"\n },\n \"bos_token_id\": 151643,\n \"draft_layers\": 9,\n \"dtype\": \"float32\",\n \"eos_token_id\": 151645,\n \"head_dim\": 128,\n \"hidden_act\": \"silu\",\n \"hidden_size\": 2560,\n \"initializer_range\": 0.02,\n \"intermediate_size\": 9728,\n \"layer_types\": [\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\",\n \"full_attention\"\n ],\n \"max_position_embeddings\": 262144,\n \"max_window_layers\": 36,\n \"model_type\": \"qwen3\",\n \"num_attention_heads\": 32,\n \"num_hidden_layers\": 0,\n \"num_hidden_layers_free\": 36,\n \"num_key_value_heads\": 8,\n \"ploss_w\": 0.1,\n \"rms_norm_eps\": 1e-06,\n \"rope_scaling\": null,\n \"rope_theta\": 5000000,\n \"skip_first_input_layernorm\": true,\n \"skip_output_norm\": true,\n \"sliding_window\": null,\n \"speculative_decoding_algorithm\": \"EagleV2\",\n \"speculative_decoding_base_model_path\": \"Qwen/Qwen3-4B-Instruct-2507\",\n \"speculative_decoding_draft_model\": \"Qwen3Drafter\",\n \"tie_word_embeddings\": true,\n \"transformers_version\": \"4.56.1\",\n \"use_cache\": true,\n \"use_sliding_window\": false,\n \"vloss_w\": 1.0,\n \"vocab_size\": 151936\n}\n",
"architectures": [
"Qwen3DrafterForSGLang",
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "bfloat16",
"eos_token_id": 151645,
"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": 262144,
"max_window_layers": 36,
"model_type": "qwen3",
"num_attention_heads": 32,
"num_hidden_layers": 9,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 5000000,
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "4.56.1",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}