nobita
nobita
Hi, I'm using deepctr-torch 0.2.9. In my code I'm using EarlyStopping as follow: ```python es = EarlyStopping(monitor='loss', min_delta=0, verbose=1, patience=5, mode='min', restore_best_weights=True) mdckpt = ModelCheckpoint(filepath='model/model.ckpt', monitor='val_mse', verbose=1, save_best_only=True, mode='min') history...
Hi, I have run your test example and gotten error when run teacher_force mode in Seq2Seq. tensorflow.python.framework.errors_impl.InvalidArgumentError: The node 'recurrent_sequential_2/while_1/Variable_1/Assign' has inputs from different frames. The input 'recurrent_sequential_2/while_1/Const_1' is in...
Hi @abetlen, I checked the parameters in both ```__call__``` and ```create_completion``` method but did not see ```penalty_alpha``` param which represents **contrastive search** decoding. Can you update the decoding strategy soon...
I load the model to GPU like this: ```python llm = AutoModelForCausalLM.from_pretrained("LLM-model", model_file="vinallama-7b-chat_q5_0.gguf", config=config, torch_dtype=torch.float16, hf=True, gpu_layers = 100, device_map='cuda') ``` and generate code like this: ```python generated_ids = llm.generate(**model_inputs,...
I have merged two Mistral-base models that have different vocab sizes and I have simultaneously used both two configs: ```embed_slerp: true``` and ```tokenizer_source: union```. But in the output folder has...
I installed ```llama-cpp-python``` on the system with: **CPU AMD EPYC 7542** **GPU V100** But it raised the exception shown in the image below:
From `Pytorch` version **2.6.0** it changed the default value of the `weights_only` argument in `torch.load` from `False` to `True` leading to an exception in the `offload_input_embeddings` function. Please update the...