TechxGenus/starcoder2-7b-AWQ
12.8k
1{2 "_name_or_path": "bigcode/starcoder2-7b",3 "activation_function": "gelu",4 "architectures": [5 "Starcoder2ForCausalLM"6 ],7 "attention_dropout": 0.0,8 "attention_softmax_in_fp32": true,9 "bos_token_id": 0,10 "embedding_dropout": 0.0,11 "eos_token_id": 0,12 "hidden_act": "gelu_pytorch_tanh",13 "hidden_size": 4608,14 "initializer_range": 0.018042,15 "intermediate_size": 18432,16 "layer_norm_epsilon": 1e-05,17 "max_position_embeddings": 16384,18 "mlp_type": "default",19 "model_type": "starcoder2",20 "norm_epsilon": 1e-05,21 "norm_type": "layer_norm",22 "num_attention_heads": 36,23 "num_hidden_layers": 32,24 "num_key_value_heads": 4,25 "quantization_config": {26 "bits": 4,27 "group_size": 128,28 "modules_to_not_convert": null,29 "quant_method": "awq",30 "version": "gemm",31 "zero_point": true32 },33 "residual_dropout": 0.0,34 "rope_theta": 1000000,35 "scale_attention_softmax_in_fp32": true,36 "scale_attn_weights": true,37 "sliding_window": 4096,38 "torch_dtype": "float16",39 "transformers_version": "4.39.3",40 "use_bias": true,41 "use_cache": true,42 "vocab_size": 4915243}44 