| { | |
| "_name_or_path": "/tmp/tmp1qm4ts6t", | |
| "alibi": false, | |
| "apply_residual_connection_post_layernorm": false, | |
| "architectures": [ | |
| "RWForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_RW.RWConfig", | |
| "AutoModel": "OpenAssistant/falcon-7b-sft-top1-696--modelling_RW.RWModel", | |
| "AutoModelForCausalLM": "modelling_RW.RWForCausalLM", | |
| "AutoModelForQuestionAnswering": "OpenAssistant/falcon-7b-sft-top1-696--modelling_RW.RWForQuestionAnswering", | |
| "AutoModelForSequenceClassification": "OpenAssistant/falcon-7b-sft-top1-696--modelling_RW.RWForSequenceClassification", | |
| "AutoModelForTokenClassification": "OpenAssistant/falcon-7b-sft-top1-696--modelling_RW.RWForTokenClassification" | |
| }, | |
| "bias": false, | |
| "bos_token_id": 11, | |
| "eos_token_id": 11, | |
| "hidden_dropout": 0.0, | |
| "hidden_size": 4544, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "RefinedWebModel", | |
| "multi_query": true, | |
| "n_head": 71, | |
| "n_layer": 32, | |
| "parallel_attn": true, | |
| "quantization_config": { | |
| "bnb_4bit_compute_dtype": "bfloat16", | |
| "bnb_4bit_quant_type": "fp4", | |
| "bnb_4bit_use_double_quant": true, | |
| "llm_int8_enable_fp32_cpu_offload": false, | |
| "llm_int8_has_fp16_weight": false, | |
| "llm_int8_skip_modules": [ | |
| "lm_head" | |
| ], | |
| "llm_int8_threshold": 6.0, | |
| "load_in_4bit": true, | |
| "load_in_8bit": false, | |
| "quant_method": "bitsandbytes" | |
| }, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.37.1", | |
| "use_cache": true, | |
| "vocab_size": 65040 | |
| } | |