saiga_nemo_12b-GPTQ / config.json
NightForger's picture
Upload 6 files
d479b46 verified
{
"_attn_implementation_autoset": true,
"_name_or_path": "IlyaGusev/saiga_nemo_12b",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 1024000,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 40,
"num_key_value_heads": 8,
"pad_token_id": 10,
"quantization_config": {
"bits": 4,
"damp_percent": 0.01,
"desc_act": false,
"group_size": 128,
"is_marlin_format": false,
"model_file_base_name": null,
"model_name_or_path": null,
"quant_method": "gptq",
"static_groups": false,
"sym": true,
"true_sequential": true
},
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.46.1",
"unsloth_version": "2024.8",
"use_cache": true,
"vocab_size": 131072
}