| { |
| "architectures": [ |
| "GPTNeoXForCausalLM" |
| ], |
| "attention_bias": true, |
| "attention_dropout": 0.0, |
| "bos_token_id": 0, |
| "classifier_dropout": 0.1, |
| "dtype": "float16", |
| "eos_token_id": 0, |
| "hidden_act": "gelu", |
| "hidden_dropout": 0.0, |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 20480, |
| "is_decoder": false, |
| "layer_norm_eps": 1e-05, |
| "max_position_embeddings": 2048, |
| "model_type": "gpt_neox", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 36, |
| "pad_token_id": null, |
| "quantization_config": { |
| "_load_in_4bit": true, |
| "_load_in_8bit": false, |
| "bnb_4bit_compute_dtype": "bfloat16", |
| "bnb_4bit_quant_storage": "uint8", |
| "bnb_4bit_quant_type": "nf4", |
| "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", |
| "multi_modal_projector", |
| "merger", |
| "modality_projection" |
| ], |
| "llm_int8_threshold": 6.0, |
| "load_in_4bit": true, |
| "load_in_8bit": false, |
| "quant_method": "bitsandbytes" |
| }, |
| "rope_parameters": { |
| "partial_rotary_factor": 0.25, |
| "rope_theta": 10000, |
| "rope_type": "default" |
| }, |
| "tie_word_embeddings": false, |
| "transformers_version": "5.1.0", |
| "use_cache": true, |
| "use_parallel_residual": true, |
| "vocab_size": 50688 |
| } |
|
|
