{ "_name_or_path": "/covalent/.cache/models/tmpxj5dpfq01e32vm31", "_remove_final_layer_norm": false, "activation_function": "relu", "architectures": [ "OPTForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 2, "do_layer_norm_before": true, "dropout": 0.1, "enable_bias": true, "eos_token_id": 2, "ffn_dim": 3072, "hidden_size": 8, "init_std": 0.02, "intermediate_size": 32, "layer_norm_elementwise_affine": true, "layerdrop": 0.0, "max_position_embeddings": 2048, "model_type": "opt", "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 2, "pad_token_id": 1, "quantization_config": { "_load_in_4bit": false, "_load_in_8bit": true, "bnb_4bit_compute_dtype": "bfloat16", "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": [ "lm_head" ], "llm_int8_threshold": 6.0, "load_in_4bit": false, "load_in_8bit": true, "quant_method": "bitsandbytes" }, "torch_dtype": "float16", "transformers_version": "4.46.2", "use_cache": true, "vocab_size": 50267, "word_embed_proj_dim": 8, "api_key": null }