1024m's picture
Trained with Unsloth
45bdd20 verified
{
"_name_or_path": "unsloth/gemma-7b-bnb-4bit",
"architectures": [
"GemmaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 2,
"eos_token_id": 1,
"head_dim": 256,
"hidden_act": "gelu",
"hidden_activation": null,
"hidden_size": 3072,
"initializer_range": 0.02,
"intermediate_size": 24576,
"max_position_embeddings": 8192,
"model_type": "gemma",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 16,
"pad_token_id": 0,
"quantization_config": {
"bnb_4bit_compute_dtype": "bfloat16",
"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"
},
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"torch_dtype": "bfloat16",
"transformers_version": "4.40.0",
"unsloth_version": "2024.4",
"use_cache": true,
"vocab_size": 256000
}