57 lines
1.3 KiB
JSON
57 lines
1.3 KiB
JSON
{
|
|
"architectures": [
|
|
"GraniteForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"attention_multiplier": 0.0078125,
|
|
"bos_token_id": 0,
|
|
"embedding_multiplier": 12.0,
|
|
"eos_token_id": 0,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 4096,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 12800,
|
|
"logits_scaling": 16.0,
|
|
"max_position_embeddings": 131072,
|
|
"mlp_bias": false,
|
|
"model_type": "granite",
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 40,
|
|
"num_key_value_heads": 8,
|
|
"pad_token_id": 0,
|
|
"quantization_config": {
|
|
"bits": 4,
|
|
"checkpoint_format": "gptq",
|
|
"desc_act": true,
|
|
"group_size": 64,
|
|
"lm_head": false,
|
|
"meta": {
|
|
"damp_auto_increment": 0.0025,
|
|
"damp_percent": 0.01,
|
|
"mse": 0.0,
|
|
"quantized_by": "jeffcookio",
|
|
"quantizer": [
|
|
"gptqmodel:3.0.0-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
|
|
},
|
|
"residual_multiplier": 0.22,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_scaling": null,
|
|
"rope_theta": 10000000.0,
|
|
"tie_word_embeddings": true,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.52.0.dev0",
|
|
"use_cache": true,
|
|
"vocab_size": 49159
|
|
}
|