| { | |
| "_name_or_path": "bigscience-small-testing", | |
| "apply_residual_connection_post_layernorm": false, | |
| "architectures": [ | |
| "BloomForCausalLM" | |
| ], | |
| "attention_dropout": 0.1, | |
| "bias_dropout_fusion": true, | |
| "bos_token_id": 0, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 0, | |
| "hidden_dropout": 0.1, | |
| "hidden_size": 64, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "masked_softmax_fusion": true, | |
| "model_type": "bloom", | |
| "n_head": 8, | |
| "n_inner": null, | |
| "n_layer": 2, | |
| "pretraining_tp": 2, | |
| "quantization_config": { | |
| "_load_in_4bit": true, | |
| "_load_in_8bit": false, | |
| "bnb_4bit_compute_dtype": "float32", | |
| "bnb_4bit_quant_storage": "uint8", | |
| "bnb_4bit_quant_type": "fp4", | |
| "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" | |
| }, | |
| "seq_length": 20, | |
| "skip_bias_add": true, | |
| "slow_but_exact": true, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.39.3", | |
| "use_cache": false, | |
| "vocab_size": 250880 | |
| } | |