Files
Impish_LLAMA_4B_GPTQ_4-bit-128/config.json
ModelHub XC e688de00ff 初始化项目,由ModelHub XC社区提供模型
Model: SicariusSicariiStuff/Impish_LLAMA_4B_GPTQ_4-bit-128
Source: Original Platform
2026-05-22 01:48:12 +08:00

60 lines
1.4 KiB
JSON

{
"_name_or_path": "SicariusSicariiStuff/Impish_LLAMA_4B_V2",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": 128019,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 3072,
"initializer_range": 0.02,
"intermediate_size": 9216,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"quantization_config": {
"bits": 4,
"checkpoint_format": "gptq",
"desc_act": true,
"group_size": 128,
"lm_head": false,
"meta": {
"damp_auto_increment": 0.0025,
"damp_percent": 0.01,
"mse": 0.0,
"quantizer": [
"gptqmodel:3.1.0-dev"
],
"static_groups": false,
"true_sequential": true,
"uri": "https://github.com/modelcloud/gptqmodel",
"v2": false,
"v2_alpha": 0.25
},
"pack_dtype": "int32",
"quant_method": "gptq",
"sym": true
},
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 8.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.3",
"use_cache": false,
"vocab_size": 128256
}