STEMerald-2b-4bit / config.json
matsant01's picture
Upload GemmaForCausalLM
2ee569f verified
raw
history blame
1.19 kB
{
"_name_or_path": "matsant01/STEMerald-2b",
"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": "gelu_pytorch_tanh",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 16384,
"max_position_embeddings": 8192,
"model_type": "gemma",
"num_attention_heads": 8,
"num_hidden_layers": 18,
"num_key_value_heads": 1,
"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": false,
"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": "float16",
"transformers_version": "4.41.2",
"use_cache": true,
"vocab_size": 256000
}