Delete SpydazWebAI_Examples.py

SpydazWebAI_Examples.py

@@ -1,235 +0,0 @@
-
-
-
-
-
-
-
-
-
-################################  language examples ##############################
-
-## LlamaTokenizerFast
-tokenizer = MistralTokenizerFast.from_pretrained("mistralai/Mistral-7B-v0.1")
-tokenizer.encode("Hello this is a test")
-
-################################ INITIALIZE Mistral MODEL ##############################
-## INITIALIZE MistralStarConfig
-
-# Initializing a Mistral 7B style configuration
-configuration = MistralStarConfig()
-
-# Initializing a model from the Mistral 7B style configuration
-model = MistralModel(configuration)
-
-# Accessing the model configuration
-configuration = model.config
-
-## INITIALIZE MistralStarConfig
-
-# Initializing a Mistral 7B style configuration
-configuration = MistralQuietConfig()
-
-# Initializing a model from the Mistral 7B style configuration
-model = MistralModel(configuration)
-
-# Accessing the model configuration
-configuration = model.config
-
-
-## INITIALIZE MODEL
-
-# Initializing a Mistral 7B style configuration
-configuration = MistralConfig()
-
-# Initializing a model from the Mistral 7B style configuration
-model = MistralModel(configuration)
-
-# Accessing the model configuration
-configuration = model.config
-
-
-## INITIALIZE MODEL-Examples
-
-# Download model and configuration from huggingface.co and cache.
-model = MistralModel.from_pretrained("mistralai/Mistral-7B-v0.1")
-# Model was saved using *save_pretrained('./test/saved_model/')* (for example purposes, not runnable).
-model = MistralModel.from_pretrained("./test/saved_model/")
-# Update configuration during loading.
-model = MistralModel.from_pretrained("mistralai/Mistral-7B-v0.1", output_attentions=True)
-assert model.config.output_attentions == True
-# Loading from a TF checkpoint file instead of a PyTorch model (slower, for example purposes, not runnable).
-config = MistralConfig.from_json_file("./tf_model/my_tf_model_config.json")
-model = MistralModel.from_pretrained("./tf_model/my_tf_checkpoint.ckpt.index", from_tf=True, config=config)
-# Loading from a Flax checkpoint file instead of a PyTorch model (slower)
-model = MistralModel.from_pretrained("mistralai/Mistral-7B-v0.1", from_flax=True)
-################################  MistralForCausalLM ##############################
-
-## MistralForCausalLM
-
-model = MistralForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1")
-tokenizer = MistralTokenizerFast.from_pretrained("mistralai/Mistral-7B-v0.1")
-
-prompt = "Hey, are you conscious? Can you talk to me?"
-inputs = tokenizer(prompt, return_tensors="pt")
-
-# Generate
-generate_ids = model.generate(inputs.input_ids, max_length=30)
-tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
-## "Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
-
-################################  MistralForSequenceClassification ##############################
-
-### MistralForSequenceClassification - single-label classification:
-
-tokenizer = MistralTokenizerFast.from_pretrained("mistralai/Mistral-7B-v0.1")
-model = MistralForSequenceClassification.from_pretrained("mistralai/Mistral-7B-v0.1")
-
-inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
-
-with torch.no_grad():
-    logits = model(**inputs).logits
-
-predicted_class_id = logits.argmax().item()
-
-# To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
-num_labels = len(model.config.id2label)
-model = MistralForSequenceClassification.from_pretrained("mistralai/Mistral-7B-v0.1", num_labels=num_labels)
-
-labels = torch.tensor([1])
-loss = model(**inputs, labels=labels).loss
-
-
-### MistralForSequenceClassification - multi-label classification:
-
-
-tokenizer = MistralTokenizerFast.from_pretrained("mistralai/Mistral-7B-v0.1")
-model = MistralForSequenceClassification.from_pretrained("mistralai/Mistral-7B-v0.1", problem_type="multi_label_classification")
-
-inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
-
-with torch.no_grad():
-    logits = model(**inputs).logits
-
-predicted_class_ids = torch.arange(0, logits.shape[-1])[torch.sigmoid(logits).squeeze(dim=0) > 0.5]
-
-# To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
-num_labels = len(model.config.id2label)
-model = MistralForSequenceClassification.from_pretrained(
-    "mistralai/Mistral-7B-v0.1", num_labels=num_labels, problem_type="multi_label_classification"
-)
-
-labels = torch.sum(
-    torch.nn.functional.one_hot(predicted_class_ids[None, :].clone(), num_classes=num_labels), dim=1
-).to(torch.float)
-loss = model(**inputs, labels=labels).loss
-
-################################  MistralForTokenClassification ##############################
-
-
-### MistralForTokenClassification
-
-tokenizer = MistralTokenizerFast.from_pretrained("mistralai/Mistral-7B-v0.1")
-model = MistralForTokenClassification.from_pretrained("mistralai/Mistral-7B-v0.1")
-
-inputs = tokenizer(
-    "HuggingFace is a company based in Paris and New York", add_special_tokens=False, return_tensors="pt"
-)
-
-with torch.no_grad():
-    logits = model(**inputs).logits
-
-predicted_token_class_ids = logits.argmax(-1)
-
-# Note that tokens are classified rather then input words which means that
-# there might be more predicted token classes than words.
-# Multiple token classes might account for the same word
-predicted_tokens_classes = [model.config.id2label[t.item()] for t in predicted_token_class_ids[0]]
-predicted_tokens_classes
-
-labels = predicted_token_class_ids
-loss = model(**inputs, labels=labels).loss
-round(loss.item(), 2)
-
-
-
-
-################################  MistralForQuestionAnswering ##############################
-
-
-tokenizer = MistralTokenizerFast.from_pretrained("mistralai/Mistral-7B-v0.1")
-model = MistralForQuestionAnswering.from_pretrained("mistralai/Mistral-7B-v0.1")
-
-question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"
-
-inputs = tokenizer(question, text, return_tensors="pt")
-with torch.no_grad():
-    outputs = model(**inputs)
-
-answer_start_index = outputs.start_logits.argmax()
-answer_end_index = outputs.end_logits.argmax()
-
-predict_answer_tokens = inputs.input_ids[0, answer_start_index : answer_end_index + 1]
-
-# target is "nice puppet"
-target_start_index = torch.tensor([14])
-target_end_index = torch.tensor([15])
-
-outputs = model(**inputs, start_positions=target_start_index, end_positions=target_end_index)
-loss = outputs.loss
-
-
-
-
-
-
-
-################################  Mixtral MOA  Models ##############################
-
-################################################################
-# Initializing a Mixtral 7B style configuration
-################################################################
-
-configuration = MixtralConfig()
-
-# Initializing a model from the Mixtral 7B style configuration
-model = MixtralModel(configuration)
-
-# Accessing the model configuration
-configuration = model.config
-
-################################################################
-### The base model can be used as follows:
-################################################################
-
-model = MixtralForCausalLM.from_pretrained("mistralai/Mixtral-8x7B-v0.1", device_map="auto")
-tokenizer = MistralTokenizerFast.from_pretrained("mistralai/Mixtral-8x7B-v0.1")
-
-prompt = "My favourite condiment is"
-
-model_inputs = tokenizer([prompt], return_tensors="pt").to("cuda")
-model.to("cpu")
-
-generated_ids = model.generate(**model_inputs, max_new_tokens=100, do_sample=True)
-tokenizer.batch_decode(generated_ids)[0]
-
-
-################################################################
-### The instruction tuned model can be used as follows:
-################################################################
-
-model = MixtralForCausalLM.from_pretrained("mistralai/Mixtral-8x7B-Instruct-v0.1", device_map="auto")
-tokenizer = MistralTokenizerFast.from_pretrained("mistralai/Mixtral-8x7B-Instruct-v0.1")
-
-messages = [
-    {"role": "user", "content": "What is your favourite condiment?"},
-    {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
-    {"role": "user", "content": "Do you have mayonnaise recipes?"}
-]
-
-model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
-
-generated_ids = model.generate(model_inputs, max_new_tokens=100, do_sample=True)
-tokenizer.batch_decode(generated_ids)[0]
-################################  end of language examples ##############################
-