86 lines
1.7 KiB
JSON
86 lines
1.7 KiB
JSON
{
|
|
"architectures": [
|
|
"Qwen3ForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 151643,
|
|
"eos_token_id": 151645,
|
|
"head_dim": 128,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 2560,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 9728,
|
|
"max_position_embeddings": 262144,
|
|
"max_window_layers": 36,
|
|
"model_type": "qwen3",
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 36,
|
|
"num_key_value_heads": 8,
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_scaling": null,
|
|
"rope_theta": 5000000,
|
|
"sliding_window": null,
|
|
"tie_word_embeddings": true,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.51.0",
|
|
"use_cache": true,
|
|
"use_sliding_window": false,
|
|
"vocab_size": 151936,
|
|
"genetic_merge_info": {
|
|
"run_id": "20250813_033307",
|
|
"task": "gpqa_diamond_zeroshot",
|
|
"best_fitness": 0.43434343434343436,
|
|
"improvement_percentage": 19.444444444444446,
|
|
"source_models": [
|
|
"Qwen/Qwen3-4B-Thinking-2507",
|
|
"Qwen/Qwen3-4B-Thinking-2507-FP8",
|
|
"unsloth/Qwen3-4B-Thinking-2507",
|
|
"ertghiu256/Qwen3-4b-tcomanr-merge-v2",
|
|
"huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated",
|
|
"janhq/Jan-v1-4B",
|
|
"BRlkl/BingoGuard-qwen3-4B-pt-grpo",
|
|
"fireworks1231/agentic-4b-2607-sft",
|
|
"sequelbox/Qwen3-4B-Thinking-2507-DAG-Reasoning",
|
|
"ReallyFloppyPenguin/Mastermind-2x4b-thinking"
|
|
],
|
|
"configuration": [
|
|
4,
|
|
0,
|
|
4,
|
|
2,
|
|
9,
|
|
6,
|
|
0,
|
|
0,
|
|
2,
|
|
2,
|
|
7,
|
|
3,
|
|
8,
|
|
2,
|
|
3,
|
|
9,
|
|
7,
|
|
7,
|
|
2,
|
|
8,
|
|
3,
|
|
9,
|
|
4,
|
|
3,
|
|
5,
|
|
6,
|
|
3,
|
|
6,
|
|
3,
|
|
0,
|
|
8,
|
|
6,
|
|
6,
|
|
2,
|
|
0,
|
|
3
|
|
]
|
|
}
|
|
} |