RichardErkhov/bigcode_-_gpt_bigcode-santacoder-8bits

1{2  "_name_or_path": "gpt_bigcode-santacoder",3  "activation_function": "gelu_pytorch_tanh",4  "architectures": [5    "GPTBigCodeForCausalLM"6  ],7  "attention_softmax_in_fp32": true,8  "attn_pdrop": 0.1,9  "bos_token_id": 49152,10  "embd_pdrop": 0.1,11  "eos_token_id": 49152,12  "initializer_range": 0.02,13  "layer_norm_epsilon": 1e-05,14  "model_type": "gpt_bigcode",15  "multi_query": true,16  "n_embd": 2048,17  "n_head": 16,18  "n_inner": 8192,19  "n_layer": 24,20  "n_positions": 2048,21  "quantization_config": {22    "_load_in_4bit": false,23    "_load_in_8bit": true,24    "bnb_4bit_compute_dtype": "float32",25    "bnb_4bit_quant_storage": "uint8",26    "bnb_4bit_quant_type": "fp4",27    "bnb_4bit_use_double_quant": false,28    "llm_int8_enable_fp32_cpu_offload": false,29    "llm_int8_has_fp16_weight": false,30    "llm_int8_skip_modules": null,31    "llm_int8_threshold": 6.0,32    "load_in_4bit": false,33    "load_in_8bit": true,34    "quant_method": "bitsandbytes"35  },36  "resid_pdrop": 0.1,37  "runner_max_sequence_length": null,38  "scale_attention_softmax_in_fp32": true,39  "scale_attn_weights": true,40  "summary_activation": null,41  "summary_first_dropout": 0.1,42  "summary_proj_to_labels": true,43  "summary_type": "cls_index",44  "summary_use_proj": true,45  "torch_dtype": "float16",46  "transformers_version": "4.44.2",47  "use_cache": true,48  "vocab_size": 4928049}50