File size: 1,206 Bytes
319e649 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 |
{
"_name_or_path": "aya-expanse-32b-gptqmodel-4bit",
"architectures": [
"CohereForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 5,
"eos_token_id": 255001,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 24576,
"layer_norm_eps": 1e-05,
"logit_scale": 0.0625,
"max_position_embeddings": 8192,
"model_type": "cohere",
"num_attention_heads": 64,
"num_hidden_layers": 40,
"num_key_value_heads": 8,
"pad_token_id": 0,
"quantization_config": {
"bits": 4,
"checkpoint_format": "gptq",
"desc_act": true,
"dynamic": null,
"group_size": 128,
"lm_head": false,
"meta": {
"damp_auto_increment": 0.0025,
"damp_percent": 0.01,
"mse": 0.0,
"quantizer": [
"gptqmodel:1.7.4-dev"
],
"static_groups": false,
"true_sequential": true,
"uri": "https://github.com/modelcloud/gptqmodel"
},
"quant_method": "gptq",
"sym": true
},
"rope_scaling": null,
"rope_theta": 4000000,
"torch_dtype": "float16",
"transformers_version": "4.48.1",
"use_cache": true,
"use_qk_norm": false,
"vocab_size": 256000
}
|