QwQ-32B-FP8 / config.json
ZMC2019's picture
Upload folder using huggingface_hub
ee54941 verified
{
"_name_or_path": "Qwen/QwQ-32B",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 27648,
"max_position_embeddings": 40960,
"max_window_layers": 64,
"model_type": "qwen2",
"num_attention_heads": 40,
"num_hidden_layers": 64,
"num_key_value_heads": 8,
"quantization_config": {
"activation_scale_ub": 1200.0,
"modules_to_not_convert": [
"lm_head",
"model.layers.0.self_attn.k_proj",
"model.layers.0.self_attn.o_proj",
"model.layers.0.self_attn.q_proj",
"model.layers.0.self_attn.v_proj",
"model.layers.1.self_attn.k_proj",
"model.layers.1.self_attn.o_proj",
"model.layers.1.self_attn.q_proj",
"model.layers.1.self_attn.v_proj",
"model.layers.2.self_attn.k_proj",
"model.layers.2.self_attn.o_proj",
"model.layers.2.self_attn.q_proj",
"model.layers.2.self_attn.v_proj",
"model.layers.3.self_attn.k_proj",
"model.layers.3.self_attn.o_proj",
"model.layers.3.self_attn.q_proj",
"model.layers.3.self_attn.v_proj",
"model.layers.4.self_attn.k_proj",
"model.layers.4.self_attn.o_proj",
"model.layers.4.self_attn.q_proj",
"model.layers.4.self_attn.v_proj",
"model.layers.5.self_attn.k_proj",
"model.layers.5.self_attn.o_proj",
"model.layers.5.self_attn.q_proj",
"model.layers.5.self_attn.v_proj",
"model.layers.6.self_attn.k_proj",
"model.layers.6.self_attn.o_proj",
"model.layers.6.self_attn.q_proj",
"model.layers.6.self_attn.v_proj",
"model.layers.7.self_attn.k_proj",
"model.layers.7.self_attn.o_proj",
"model.layers.7.self_attn.q_proj",
"model.layers.7.self_attn.v_proj",
"model.layers.8.self_attn.k_proj",
"model.layers.8.self_attn.o_proj",
"model.layers.8.self_attn.q_proj",
"model.layers.8.self_attn.v_proj",
"model.layers.9.self_attn.k_proj",
"model.layers.9.self_attn.o_proj",
"model.layers.9.self_attn.q_proj",
"model.layers.9.self_attn.v_proj",
"model.layers.10.self_attn.k_proj",
"model.layers.10.self_attn.o_proj",
"model.layers.10.self_attn.q_proj",
"model.layers.10.self_attn.v_proj",
"model.layers.11.self_attn.k_proj",
"model.layers.11.self_attn.o_proj",
"model.layers.11.self_attn.q_proj",
"model.layers.11.self_attn.v_proj",
"model.layers.12.self_attn.k_proj",
"model.layers.12.self_attn.o_proj",
"model.layers.12.self_attn.q_proj",
"model.layers.12.self_attn.v_proj",
"model.layers.13.self_attn.k_proj",
"model.layers.13.self_attn.o_proj",
"model.layers.13.self_attn.q_proj",
"model.layers.13.self_attn.v_proj",
"model.layers.14.self_attn.k_proj",
"model.layers.14.self_attn.o_proj",
"model.layers.14.self_attn.q_proj",
"model.layers.14.self_attn.v_proj",
"model.layers.15.self_attn.k_proj",
"model.layers.15.self_attn.o_proj",
"model.layers.15.self_attn.q_proj",
"model.layers.15.self_attn.v_proj",
"model.layers.16.self_attn.k_proj",
"model.layers.16.self_attn.o_proj",
"model.layers.16.self_attn.q_proj",
"model.layers.16.self_attn.v_proj",
"model.layers.17.self_attn.k_proj",
"model.layers.17.self_attn.o_proj",
"model.layers.17.self_attn.q_proj",
"model.layers.17.self_attn.v_proj",
"model.layers.18.self_attn.k_proj",
"model.layers.18.self_attn.o_proj",
"model.layers.18.self_attn.q_proj",
"model.layers.18.self_attn.v_proj",
"model.layers.19.self_attn.k_proj",
"model.layers.19.self_attn.o_proj",
"model.layers.19.self_attn.q_proj",
"model.layers.19.self_attn.v_proj",
"model.layers.20.self_attn.k_proj",
"model.layers.20.self_attn.o_proj",
"model.layers.20.self_attn.q_proj",
"model.layers.20.self_attn.v_proj",
"model.layers.21.self_attn.k_proj",
"model.layers.21.self_attn.o_proj",
"model.layers.21.self_attn.q_proj",
"model.layers.21.self_attn.v_proj",
"model.layers.22.self_attn.k_proj",
"model.layers.22.self_attn.o_proj",
"model.layers.22.self_attn.q_proj",
"model.layers.22.self_attn.v_proj",
"model.layers.23.self_attn.k_proj",
"model.layers.23.self_attn.o_proj",
"model.layers.23.self_attn.q_proj",
"model.layers.23.self_attn.v_proj",
"model.layers.24.self_attn.k_proj",
"model.layers.24.self_attn.o_proj",
"model.layers.24.self_attn.q_proj",
"model.layers.24.self_attn.v_proj",
"model.layers.25.self_attn.k_proj",
"model.layers.25.self_attn.o_proj",
"model.layers.25.self_attn.q_proj",
"model.layers.25.self_attn.v_proj",
"model.layers.26.self_attn.k_proj",
"model.layers.26.self_attn.o_proj",
"model.layers.26.self_attn.q_proj",
"model.layers.26.self_attn.v_proj",
"model.layers.27.self_attn.k_proj",
"model.layers.27.self_attn.o_proj",
"model.layers.27.self_attn.q_proj",
"model.layers.27.self_attn.v_proj",
"model.layers.28.self_attn.k_proj",
"model.layers.28.self_attn.o_proj",
"model.layers.28.self_attn.q_proj",
"model.layers.28.self_attn.v_proj",
"model.layers.29.self_attn.k_proj",
"model.layers.29.self_attn.o_proj",
"model.layers.29.self_attn.q_proj",
"model.layers.29.self_attn.v_proj",
"model.layers.30.self_attn.k_proj",
"model.layers.30.self_attn.o_proj",
"model.layers.30.self_attn.q_proj",
"model.layers.30.self_attn.v_proj",
"model.layers.31.self_attn.k_proj",
"model.layers.31.self_attn.o_proj",
"model.layers.31.self_attn.q_proj",
"model.layers.31.self_attn.v_proj",
"model.layers.32.self_attn.k_proj",
"model.layers.32.self_attn.o_proj",
"model.layers.32.self_attn.q_proj",
"model.layers.32.self_attn.v_proj",
"model.layers.33.self_attn.k_proj",
"model.layers.33.self_attn.o_proj",
"model.layers.33.self_attn.q_proj",
"model.layers.33.self_attn.v_proj",
"model.layers.34.self_attn.k_proj",
"model.layers.34.self_attn.o_proj",
"model.layers.34.self_attn.q_proj",
"model.layers.34.self_attn.v_proj",
"model.layers.35.self_attn.k_proj",
"model.layers.35.self_attn.o_proj",
"model.layers.35.self_attn.q_proj",
"model.layers.35.self_attn.v_proj",
"model.layers.36.self_attn.k_proj",
"model.layers.36.self_attn.o_proj",
"model.layers.36.self_attn.q_proj",
"model.layers.36.self_attn.v_proj",
"model.layers.37.self_attn.k_proj",
"model.layers.37.self_attn.o_proj",
"model.layers.37.self_attn.q_proj",
"model.layers.37.self_attn.v_proj",
"model.layers.38.self_attn.k_proj",
"model.layers.38.self_attn.o_proj",
"model.layers.38.self_attn.q_proj",
"model.layers.38.self_attn.v_proj",
"model.layers.39.self_attn.k_proj",
"model.layers.39.self_attn.o_proj",
"model.layers.39.self_attn.q_proj",
"model.layers.39.self_attn.v_proj",
"model.layers.40.self_attn.k_proj",
"model.layers.40.self_attn.o_proj",
"model.layers.40.self_attn.q_proj",
"model.layers.40.self_attn.v_proj",
"model.layers.41.self_attn.k_proj",
"model.layers.41.self_attn.o_proj",
"model.layers.41.self_attn.q_proj",
"model.layers.41.self_attn.v_proj",
"model.layers.42.self_attn.k_proj",
"model.layers.42.self_attn.o_proj",
"model.layers.42.self_attn.q_proj",
"model.layers.42.self_attn.v_proj",
"model.layers.43.self_attn.k_proj",
"model.layers.43.self_attn.o_proj",
"model.layers.43.self_attn.q_proj",
"model.layers.43.self_attn.v_proj",
"model.layers.44.self_attn.k_proj",
"model.layers.44.self_attn.o_proj",
"model.layers.44.self_attn.q_proj",
"model.layers.44.self_attn.v_proj",
"model.layers.45.self_attn.k_proj",
"model.layers.45.self_attn.o_proj",
"model.layers.45.self_attn.q_proj",
"model.layers.45.self_attn.v_proj",
"model.layers.46.self_attn.k_proj",
"model.layers.46.self_attn.o_proj",
"model.layers.46.self_attn.q_proj",
"model.layers.46.self_attn.v_proj",
"model.layers.47.self_attn.k_proj",
"model.layers.47.self_attn.o_proj",
"model.layers.47.self_attn.q_proj",
"model.layers.47.self_attn.v_proj",
"model.layers.48.self_attn.k_proj",
"model.layers.48.self_attn.o_proj",
"model.layers.48.self_attn.q_proj",
"model.layers.48.self_attn.v_proj",
"model.layers.49.self_attn.k_proj",
"model.layers.49.self_attn.o_proj",
"model.layers.49.self_attn.q_proj",
"model.layers.49.self_attn.v_proj",
"model.layers.50.self_attn.k_proj",
"model.layers.50.self_attn.o_proj",
"model.layers.50.self_attn.q_proj",
"model.layers.50.self_attn.v_proj",
"model.layers.51.self_attn.k_proj",
"model.layers.51.self_attn.o_proj",
"model.layers.51.self_attn.q_proj",
"model.layers.51.self_attn.v_proj",
"model.layers.52.self_attn.k_proj",
"model.layers.52.self_attn.o_proj",
"model.layers.52.self_attn.q_proj",
"model.layers.52.self_attn.v_proj",
"model.layers.53.self_attn.k_proj",
"model.layers.53.self_attn.o_proj",
"model.layers.53.self_attn.q_proj",
"model.layers.53.self_attn.v_proj",
"model.layers.54.self_attn.k_proj",
"model.layers.54.self_attn.o_proj",
"model.layers.54.self_attn.q_proj",
"model.layers.54.self_attn.v_proj",
"model.layers.55.self_attn.k_proj",
"model.layers.55.self_attn.o_proj",
"model.layers.55.self_attn.q_proj",
"model.layers.55.self_attn.v_proj",
"model.layers.56.self_attn.k_proj",
"model.layers.56.self_attn.o_proj",
"model.layers.56.self_attn.q_proj",
"model.layers.56.self_attn.v_proj",
"model.layers.57.self_attn.k_proj",
"model.layers.57.self_attn.o_proj",
"model.layers.57.self_attn.q_proj",
"model.layers.57.self_attn.v_proj",
"model.layers.58.self_attn.k_proj",
"model.layers.58.self_attn.o_proj",
"model.layers.58.self_attn.q_proj",
"model.layers.58.self_attn.v_proj",
"model.layers.59.self_attn.k_proj",
"model.layers.59.self_attn.o_proj",
"model.layers.59.self_attn.q_proj",
"model.layers.59.self_attn.v_proj",
"model.layers.60.self_attn.k_proj",
"model.layers.60.self_attn.o_proj",
"model.layers.60.self_attn.q_proj",
"model.layers.60.self_attn.v_proj",
"model.layers.61.self_attn.k_proj",
"model.layers.61.self_attn.o_proj",
"model.layers.61.self_attn.q_proj",
"model.layers.61.self_attn.v_proj",
"model.layers.62.self_attn.k_proj",
"model.layers.62.self_attn.o_proj",
"model.layers.62.self_attn.q_proj",
"model.layers.62.self_attn.v_proj",
"model.layers.63.self_attn.k_proj",
"model.layers.63.self_attn.o_proj",
"model.layers.63.self_attn.q_proj",
"model.layers.63.self_attn.v_proj"
],
"quant_method": "fbgemm_fp8"
},
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.48.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 152064
}