OrHaifler3/bloom1b-forms
019
1{2 "_name_or_path": "bloom1b-forms",3 "apply_residual_connection_post_layernorm": false,4 "architectures": [5 "BloomForCausalLM"6 ],7 "attention_dropout": 0.0,8 "attention_softmax_in_fp32": true,9 "bias_dropout_fusion": true,10 "bos_token_id": 1,11 "eos_token_id": 2,12 "hidden_dropout": 0.0,13 "hidden_size": 1536,14 "initializer_range": 0.02,15 "layer_norm_epsilon": 1e-05,16 "masked_softmax_fusion": true,17 "model_type": "bloom",18 "n_head": 16,19 "n_inner": null,20 "n_layer": 24,21 "offset_alibi": 100,22 "pad_token_id": 3,23 "pretraining_tp": 1,24 "quantization_config": {25 "bnb_4bit_compute_dtype": "float32",26 "bnb_4bit_quant_type": "fp4",27 "bnb_4bit_use_double_quant": false,28 "llm_int8_enable_fp32_cpu_offload": false,29 "llm_int8_has_fp16_weight": false,30 "llm_int8_skip_modules": null,31 "llm_int8_threshold": 6.0,32 "load_in_4bit": false,33 "load_in_8bit": true34 },35 "skip_bias_add": true,36 "skip_bias_add_qkv": false,37 "slow_but_exact": false,38 "torch_dtype": "float16",39 "transformers_version": "4.31.0",40 "unk_token_id": 0,41 "use_cache": true,42 "vocab_size": 25088043}44 