{ "_name_or_path": "/tmp/tmpcnp83ya5", "alibi": false, "apply_residual_connection_post_layernorm": false, "architectures": [ "RWForCausalLM" ], "attention_dropout": 0.0, "attention_probs_dropout_prob": 0.0, "auto_map": { "AutoConfig": "configuration_RW.RWConfig", "AutoModel": "h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2--modelling_RW.RWModel", "AutoModelForCausalLM": "modelling_RW.RWForCausalLM", "AutoModelForQuestionAnswering": "h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2--modelling_RW.RWForQuestionAnswering", "AutoModelForSequenceClassification": "h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2--modelling_RW.RWForSequenceClassification", "AutoModelForTokenClassification": "h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2--modelling_RW.RWForTokenClassification" }, "bias": false, "bos_token_id": 11, "custom_pipelines": { "text-generation": { "impl": "h2oai_pipeline.H2OTextGenerationPipeline", "pt": "AutoModelForCausalLM" } }, "eos_token_id": 11, "hidden_dropout": 0.0, "hidden_dropout_prob": 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": false, "load_in_8bit": true, "quant_method": "bitsandbytes" }, "torch_dtype": "float16", "transformers_version": "4.37.1", "use_cache": true, "vocab_size": 65024 }