| { | |
| "_attn_implementation_autoset": true, | |
| "_name_or_path": "/tmp/models/tmplpybyqsd/tmp6_jl07az", | |
| "architectures": [ | |
| "Starcoder2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.1, | |
| "bos_token_id": 0, | |
| "embedding_dropout": 0.1, | |
| "eos_token_id": 0, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 3072, | |
| "initializer_range": 0.018042, | |
| "intermediate_size": 12288, | |
| "max_position_embeddings": 16384, | |
| "mlp_type": "default", | |
| "model_type": "starcoder2", | |
| "norm_epsilon": 1e-05, | |
| "norm_type": "layer_norm", | |
| "num_attention_heads": 24, | |
| "num_hidden_layers": 30, | |
| "num_key_value_heads": 2, | |
| "quantization_config": { | |
| "quant_config": { | |
| "offload_meta": false, | |
| "scale_quant_params": null, | |
| "weight_quant_params": { | |
| "axis": 1, | |
| "channel_wise": true, | |
| "group_size": 64, | |
| "nbits": 8, | |
| "optimize": true, | |
| "round_zero": false, | |
| "view_as_float": false | |
| }, | |
| "zero_quant_params": null | |
| }, | |
| "quant_method": "hqq", | |
| "skip_modules": [ | |
| "lm_head" | |
| ] | |
| }, | |
| "residual_dropout": 0.1, | |
| "rope_scaling": null, | |
| "rope_theta": 999999.4420358813, | |
| "sliding_window": 4096, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.48.2", | |
| "use_bias": true, | |
| "use_cache": true, | |
| "vocab_size": 49152 | |
| } | |