INC4AI's picture
Upload quantized model experiment024b-AutoRound-W4A16-RTN
7f57627 verified
Raw
History Blame Contribute Delete
1.08 kB
{
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"dtype": "bfloat16",
"eos_token_id": 2,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 32768,
"max_position_embeddings": 131072,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 40,
"num_key_value_heads": 8,
"pad_token_id": 11,
"quantization_config": {
"autoround_version": "0.13.1",
"bits": 4,
"block_name_to_quantize": "model.layers",
"data_type": "int",
"enable_quanted_input": false,
"group_size": 128,
"iters": 0,
"low_gpu_mem_usage": true,
"packing_format": "auto_round:auto_gptq",
"quant_method": "auto-round",
"sym": true
},
"rms_norm_eps": 1e-05,
"rope_parameters": {
"rope_theta": 1000000000.0,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "5.12.1",
"unsloth_version": "2025.12.5",
"use_cache": false,
"vocab_size": 131072
}