Aya23-35B-hok-v3-4bit / config.json
tsbiosky's picture
Upload CohereForCausalLM
7e3e29d verified
{
"_name_or_path": "/local_disk0/model/aya_35b/aya_35b",
"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": 22528,
"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": 64,
"pad_token_id": 0,
"quantization_config": {
"_load_in_4bit": true,
"_load_in_8bit": false,
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_quant_storage": "uint8",
"bnb_4bit_quant_type": "nf4",
"bnb_4bit_use_double_quant": true,
"llm_int8_enable_fp32_cpu_offload": false,
"llm_int8_has_fp16_weight": false,
"llm_int8_skip_modules": null,
"llm_int8_threshold": 6.0,
"load_in_4bit": true,
"load_in_8bit": false,
"quant_method": "bitsandbytes"
},
"rope_theta": 8000000.0,
"torch_dtype": "bfloat16",
"transformers_version": "4.41.1",
"use_cache": false,
"use_qk_norm": false,
"vocab_size": 256000
}