f562a6df4b
Model: SicariusSicariiStuff/Assistant_Pepe_32B_GPTQ_AR_4-bit-128 Source: Original Platform
118 lines
2.6 KiB
JSON
118 lines
2.6 KiB
JSON
{
|
|
"_name_or_path": "SicariusSicariiStuff/Assistant_Pepe_32B",
|
|
"architectures": [
|
|
"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": 5120,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 25600,
|
|
"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",
|
|
"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": 64,
|
|
"model_type": "qwen3",
|
|
"num_attention_heads": 64,
|
|
"num_hidden_layers": 64,
|
|
"num_key_value_heads": 8,
|
|
"pad_token_id": null,
|
|
"quantization_config": {
|
|
"autoround_version": "0.12.0",
|
|
"batch_size": 1,
|
|
"bits": 4,
|
|
"damp_percent": 0.01,
|
|
"data_type": "int",
|
|
"desc_act": false,
|
|
"group_size": 128,
|
|
"lm_head": false,
|
|
"nsamples": 64,
|
|
"provider": "auto-round",
|
|
"quant_method": "gptq",
|
|
"seqlen": 512,
|
|
"sym": true,
|
|
"true_sequential": false
|
|
},
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_parameters": {
|
|
"rope_theta": 1000000,
|
|
"rope_type": "default"
|
|
},
|
|
"sliding_window": null,
|
|
"tie_word_embeddings": false,
|
|
"transformers_version": "5.5.4",
|
|
"use_cache": true,
|
|
"use_sliding_window": false,
|
|
"vocab_size": 151936,
|
|
"torch_dtype": "float16"
|
|
}
|