Himanshi Sinha

model config used: { "_name_or_path": "/app/mnt/models_cache/bigcode/starcoder2-7b", "activation_function": "gelu", "architectures": [ "Starcoder2ForCausalLM" ], "attention_dropout": 0.1, "attention_softmax_in_fp32": true, "bos_token_id": 0, "embedding_dropout": 0.1, "eos_token_id": 0, "hidden_act": "gelu_pytorch_tanh", "hidden_size": 4608, "initializer_range": 0.018042, "intermediate_size": 18432,...